Due to the diversity of brain anatomy and the scarcity of annotated data, supervised anomaly detection for brain MRI remains challenging, driving the development of unsupervised anomaly detection (UAD) approaches. Current UAD methods typically utilize synthetically generated noise perturbations on healthy MRIs to train generative models for normal anatomy reconstruction, enabling anomaly detection via residual maps. However, such simulated anomalies lack the biophysical fidelity and morphological complexity characteristic of true clinical lesions. To advance UAD in brain MRI, we conduct the first systematic frequency-domain analysis of pathological signatures, revealing two key properties: (1) anomalies exhibit unique frequency patterns distinguishable from normal anatomy, and (2) low-frequency signals maintain consistent representations across healthy scans. These insights motivate our Frequency-Decomposition Preprocessing (FDP) framework—the first UAD method to leverage frequency-domain reconstruction for simultaneous pathology suppression and anatomical preservation. FDP can integrate seamlessly with existing anomaly simulation techniques, consistently enhancing detection performance across diverse architectures while maintaining diagnostic fidelity. Experimental results demonstrate that FDP consistently improves anomaly detection performance when integrated with existing methods. Notably, FDP achieves a 17.63% increase in DICE score with LDM while maintaining robust improvements across multiple baselines.

While Large Language Models (LLMs) are emerging as a promising direction in computational pathology, the substantial computational cost of giga-pixel Whole Slide Images (WSIs) necessitates the use of Multi-Instance Learning (MIL) to enable effective modeling. A key challenge is that pathological tasks typically provide only bag-level labels, while instance-level descriptions generated by LLMs often suffer from bias due to a lack of fine-grained medical knowledge. To address this, we propose that constructing task-specific pathological entity prototypes is crucial for learning generalizable features and enhancing model interpretability. Furthermore, existing vision-language MIL methods often employ unidirectional guidance, limiting cross-modal synergy. In this paper, we introduce a novel approach, Multimodal Prototype-based Multi-Instance Learning, that promotes bidirectional interaction through a balanced information compression scheme. Specifically, we leverage a frozen LLM to generate task-specific pathological entity descriptions, which are learned as text prototypes. Concurrently, the vision branch learns instance-level prototypes to mitigate the model's reliance on redundant data. For the fusion stage, we employ the Stereoscopic Optimal Transport (SOT) algorithm, which is based on a similarity metric, thereby facilitating broader semantic alignment in a higher-dimensional space. We conduct few-shot classification and explainability experiments on three distinct cancer datasets, and the results demonstrate the superior generalization capabilities of our proposed method.

• Propose MorphoNet framework to capture morphological patterns and long-range tissue structures in WSIs. • Develop a Morphological Sub-Region Grouping mechanism to model WSIs as spatially coherent sub-regions. • Introduce a spatial-aware clustering approach and a sub-region aggregation strategy to derive sub-region embeddings. • Achieve superior performance across 10 public benchmarks, outperforming state-of-the-art methods in tumor subtyping and survival prediction. Representation learning of Whole slide image (WSI) is fundamental to computational pathology, enabling tasks such as tumor subtyping, survival prediction, and cancer grading. Existing methods typically tile WSIs into thousands of small patches and aggregate patch features into slide-level embeddings, but this patch-centric paradigm suffers from redundancy and suboptimal spatial modeling. Built upon these patch-level embeddings, Multiple Instance Learning (MIL) methods overfit to scattered discriminative patches, graph-based models mainly capture local neighborhoods, and prototype-based approaches often ignore spatial coherence and under-represent rare tissue patterns. To address these challenges, we propose MorphoNet, a Morph ological structure learning Net work that captures long-range spatial tissue relationships while extracting informative morphological patterns. The key idea of MorphoNet is Morphological Sub-Region Grouping (MSRG), which clusters spatially adjacent patches with similar appearance into compact sub-region embeddings, reducing redundancy and forming semantically coherent morphological units. Sub-region graph is then constructed and processed by a lightweight Graph Neural Network (GNN) to model contextual dependencies and derive slide-level representations. Importantly, MSRG is a plug-and-play module that can be integrated into MIL, graph-based, and prototype-based pipelines, consistently improving their performance. Experiments on ten public benchmarks demonstrate that MorphoNet achieves superior performance on tumor subtyping and survival prediction. Our code is available at https://github.com/fuying-wang/MorphoNet .

The diagnosis of cancer primarily relies on pathological slides stained with hematoxylin and eosin (HE). These slides are typically prepared from tissue samples that have been fixed in formalin and embedded in paraffin (FFPE). However, the traditional process of staining FFPE samples with HE is time-consuming and resource-intensive. Recent advances in virtual staining technologies, driven by digital pathology and generative models, offer a promising alternative. However, the blurred structures in FFPE images pose unique challenges to achieving high-quality FFPE-to-HE virtual staining. In this context, we developed a novel Multiple Cell Semantics-guided supervised generative adversarial model, MCS-Stain. Specifically, the guidance consists of three components: 1) pretrained cell semantic guidance, aligning the powerful intermediate features of real and virtual images, embedded in the pretrained cell segmentation model (PCSM); 2) cell mask guidance, introducing comprehensible cell information which serves as part of the input to the discriminator through channel concatenation; 3) dynamic cell semantic guidance, aligning the dynamic intermediate features embedded in the generator during training. The comparative results on FFPE-to-HE datasets demonstrated that MCS-Stain outperforms existing state-of-the-art (SOTA) methods with substantial qualitative and quantitative improvements. Results across various PCSMs and data sources further confirmed its effectiveness and robustness. Notably, the dynamic cell semantic exhibits strong potential beyond FFPE-to-HE virtual staining, further demonstrated by virtual staining from HE images to immunohistochemical (IHC) images. In general, MCS-Stain presents a promising avenue to advance virtual staining techniques. Code is available at https://github.com/huyihuang/MCS-Stain.

Significant disparities between the features of natural images and those inherent to histopathological images make it challenging to directly apply and transfer pre-trained models from natural images to histopathology tasks. Moreover, the frequent lack of annotations in histopathology patch images has driven researchers to explore self-supervised learning methods like mask reconstruction for learning representations from large amounts of unlabeled data. Crucially, previous mask-based efforts in self-supervised learning have often overlooked the spatial interactions among entities, which are essential for constructing accurate representations of pathological entities. To address these challenges, constructing graphs of entities is a promising approach. In addition, the diffusion reconstruction strategy has recently shown superior performance through its random intensity noise addition technique to enhance the robust learned representation. Therefore, we introduce H-MGDM, a novel self-supervised Histopathology image representation learning method through the Dynamic Entity-Masked Graph Diffusion Model. Specifically, we propose to use complementary subgraphs as latent diffusion conditions and self-supervised targets respectively during pre-training. We note that the graph can embed entities' topological relationships and enhance representation. Dynamic conditions and targets can improve pathological fine reconstruction. Our model has conducted pretraining experiments on three large histopathological datasets. The advanced predictive performance and interpretability of H-MGDM are clearly evaluated on comprehensive downstream tasks such as classification and survival analysis on six datasets.

International audience

Diffusion-based virtual staining methods of histopathology images have demonstrated outstanding potential for stain normalization and cross-dye staining (e.g., hematoxylin-eosin to immunohistochemistry). However, achieving pathology-correct cross-dye virtual staining with versatile tone controls poses significant challenges due to the difficulty of decoupling the given pathology and tone conditions. This issue would cause non-pathologic regions to be mistakenly stained like pathologic ones, and vice versa, which we term “pathology leakage.” To address this issue, we propose diffusion virtual staining Transformer (D-VST), a new framework with versatile tone control for cross-dye virtual staining. Specifically, we introduce a pathology encoder in conjunction with a tone encoder, combined with a two-stage curriculum learning scheme that decouples pathology and tone conditions, to enable tone control while eliminating pathology leakage. Further, to extend our method for billion-pixel whole slide image (WSI) staining, we introduce a novel frequency-aware adaptive patch sampling strategy for high-quality yet efficient inference of ultra-high resolution images in a zero-shot manner. Integrating these two innovative components facilitates a pathology-correct, tone-controllable, cross-dye WSI virtual staining process. Extensive experiments on three virtual staining tasks that involve translating between four different dyes demonstrate the superiority of our approach in generating high-quality and pathologically accurate images compared to existing methods based on generative adversarial networks and diffusion models. Our code and trained models will be released.

Medical vision-language alignment through cross-modal contrastive learning shows promising performance in image-text matching tasks, such as retrieval and zero-shot classification. However, conventional cross-modal contrastive learning (CLIP-based) methods suffer from suboptimal visual representation capabilities, which also limits their effectiveness in vision-language alignment. In contrast, although the models pretrained via multimodal masked modeling struggle with direct cross-modal matching, they excel in visual representation. To address this contradiction, we propose ALTA (ALign Through Adapting), an efficient medical vision-language alignment method that utilizes only about 8% of the trainable parameters and less than 1/5 of the computational consumption required for masked record modeling. ALTA achieves superior performance in vision-language matching tasks like retrieval and zero-shot classification by adapting the pretrained vision model from masked record modeling. Additionally, we integrate temporal-multiview radiograph inputs to enhance the information consistency between radiographs and their corresponding descriptions in reports, further improving the vision-language alignment. Experimental evaluations show that ALTA outperforms the best-performing counterpart by over 4% absolute points in text-to-image accuracy and approximately 6% absolute points in image-to-text retrieval accuracy. The adaptation of vision-language models during efficient alignment also promotes better vision and language understanding. Code is publicly available at https://github.com/DopamineLcy/ALTA.

Multimodal Federated Learning (MFL) has emerged as a collaborative paradigm for training models across decentralized devices, harnessing various data modalities to facilitate effective learning while respecting data ownership. In this realm, notably, a pivotal shift from homogeneous to heterogeneous MFL has taken place. While the former assumes uniformity in input modalities across clients, the latter accommodates modality-incongruous setups, which is often the case in practical situations. For example, while some advanced medical institutions have the luxury of utilizing both MRI and CT for disease diagnosis, remote hospitals often find themselves constrained to employ CT exclusively due to its cost-effectiveness. Although heterogeneous MFL can apply to a broader scenario, it introduces a new challenge: modality-heterogeneous client drift, arising from diverse modality-coupled local optimization. To address this, we introduce FedMM, a simple yet effective approach. During local optimization, FedMM employs modality dropout, randomly masking available modalities, and promoting weight alignment while preserving model expressivity on its original modality combination. To enhance the modality dropout process, FedMM incorporates a task-specific inter- and intra-modal regularizer, which acts as an additional constraint, forcing that weight distribution remains more consistent across diverse input modalities and therefore eases the optimization process with modality dropout enabled. By combining them, our approach holistically addresses client drift. It fosters convergence among client models while considering each client's unique input modalities, enhancing heterogeneous MFL performance. Comprehensive evaluations in three medical image segmentation datasets demonstrate FedMM's superiority over state-of-the-art heterogeneous MFL methods.

Anatomical abnormality detection and report generation of chest X-ray (CXR) are two essential tasks in clinical practice. The former aims at localizing and characterizing cardiopulmonary radiological findings in CXRs, while the latter summarizes the findings in a detailed report for further diagnosis and treatment. Existing methods often focused on either task separately, ignoring their correlation. This work proposes a co-evolutionary abnormality detection and report generation (CoE-DG) framework. The framework utilizes both fully labeled (with bounding box annotations and clinical reports) and weakly labeled (with reports only) data to achieve mutual promotion between the abnormality detection and report generation tasks. Specifically, we introduce a bi-directional information interaction strategy with generator-guided information propagation (GIP) and detector-guided information propagation (DIP). For semi-supervised abnormality detection, GIP takes the informative feature extracted by the generator as an auxiliary input to the detector and uses the generator's prediction to refine the detector's pseudo labels. We further propose an intra-image-modal self-adaptive non-maximum suppression module (SA-NMS). This module dynamically rectifies pseudo detection labels generated by the teacher detection model with high-confidence predictions by the student. Inversely, for report generation, DIP takes the abnormalities' categories and locations predicted by the detector as input and guidance for the generator to improve the generated reports. Finally, a co-evolutionary training strategy is implemented to iteratively conduct GIP and DIP and consistently improve both tasks' performance. Experimental results on two public CXR datasets demonstrate CoE-DG's superior performance to several up-to-date object detection, report generation, and unified models. Our code is available at https://github.com/jinghanSunn/CoE-DG.

Learning contextual features such as interactions among various biological entities is vital for whole slide images (WSI)-based cancer diagnosis and prognosis. Graph-based methods have surpassed traditional multi-instance learning in WSI analysis by robustly integrating local pathological and contextual interaction features. However, the high resolution of WSIs often leads to large, noisy graphs. This can result in shortcut learning and overfitting due to the disproportionate graph size relative to WSI datasets. To overcome these issues, we propose a novel Task-Aware Disentanglement Graph approach (TAD-Graph) for more efficient WSI analysis. TAD-Graph operates on WSI graph representations, effectively identifying and disentangling informative subgraphs to enhance contextual feature extraction. Specifically, we inject stochasticity into the edge connections of the WSI graph and separate the WSI graph into task-relevant and task-irrelevant subgraphs. The disentanglement procedure is optimized using a graph information bottleneck-based objective, with added constraints on the task-irrelevant subgraph to reduce spurious correlations from task-relevant subgraphs to labels. TAD-Graph outperforms existing methods in three WSI analysis tasks across six benchmark datasets. Furthermore, our analysis using pathological concept-based metrics demonstrates TAD-Graph's ability to not only improve predictive accuracy but also provide interpretive insights and aid in potential biomarker identification. Our code is publicly available at https://github.com/fuying-wang/TAD-Graph.

Most existing federated learning (FL) methods for medical image analysis only considered intramodal heterogeneity, limiting their applicability to multimodal imaging applications. In practice, it is not uncommon that some FL participants only possess a subset of the complete imaging modalities, posing inter-modal heterogeneity as a challenge to effectively training a global model on all participants’ data. In addition, each participant would expect to obtain a personalized model tailored for its local data characteristics from the FL in such a scenario. In this work, we propose a new FL framework with federated modality-specific encoders and multimodal anchors (FedMEMA) to simultaneously address the two concurrent issues. Above all, FedMEMA employs an exclusive encoder for each modality to account for the inter-modal heterogeneity in the first place. In the meantime, while the encoders are shared by the participants, the decoders are personalized to meet individual needs. Specifically, a server with full-modal data employs a fusion decoder to aggregate and fuse representations from all modality-specific encoders, thus bridging the modalities to optimize the encoders via backpropagation reversely. Meanwhile, multiple anchors are extracted from the fused multimodal representations and distributed to the clients in addition to the encoder parameters. On the other end, the clients with incomplete modalities calibrate their missing-modal representations toward the global full-modal anchors via scaled dot-product cross-attention, making up the information loss due to absent modalities while adapting the representations of present ones. FedMEMA is validated on the BraTS 2020 benchmark for multimodal brain tumor segmentation. Results show that it outperforms various up-to-date methods for multimodal and personalized FL and that its novel designs are effective. Our code is available.

Multiple instance learning is an effective paradigm for whole slide image (WSI) classification, where labels are only provided at the bag level. However, instance-level prediction is also crucial as it offers insights into fine-grained regions of interest. Existing multiple instance learning methods either solely focus on training a bag classifier or have the insufficient capability of exploring instance prediction. In this work, we propose a novel model-agnostic framework to boost existing multiple instance learning models, to improve the WSI classification performance in both bag and instance levels. Specifically, we propose a counterfactual inference-based sub-bag assessment method and a hierarchical instance searching strategy to help to search reliable instances and obtain their accurate pseudo labels. Furthermore, an instance classifier is well-trained to produce accurate predictions. The instance embedding it generates is treated as a prompt to refine the instance feature for bag prediction. This framework is model-agnostic, capable of adapting to existing multiple instance learning models, including those without specific mechanisms like attention. Extensive experiments on three datasets demonstrate the competitive performance of our method. Code will be available at https://github.com/centurion-crawler/CIMIL.

Instance segmentation plays a vital role in the morphological quantification of biomedical entities such as tissues and cells, enabling precise identification and delineation of different structures. Current methods often address the challenges of touching, overlapping or crossing instances through individual modeling, while neglecting the intrinsic interrelation between these conditions. In this work, we propose a Gradient Anomaly-aware Biomedical Instance Segmentation approach (GAInS), which leverages instance gradient information to perceive local gradient anomaly regions, thus modeling the spatial relationship between instances and refining local region segmentation. Specifically, GAInS is firstly built on a Gradient Anomaly Mapping Module (GAMM), which encodes the radial fields of instances through window sliding to obtain instance gradient anomaly maps. To efficiently refine boundaries and regions with gradient anomaly attention, we propose an Adaptive Local Refinement Module (ALRM) with a gradient anomaly-aware loss function. Extensive comparisons and ablation experiments in three biomedical scenarios demonstrate that our proposed GAInS outperforms other state-of-the-art (SOTA) instance segmentation methods. The code is available at https://github.com/DeepGAInS/GAInS.

Whole Slide Image (WSI) classification is often formu-lated as a Multiple Instance Learning (MIL) problem. Re-cently, Vision-Language Models (VLMs) have demonstrated remarkable performance in WSI classification. However, existing methods leverage coarse-grained pathogenetic de-scriptions for visual representation supervision, which are insufficient to capture the complex visual appearance of pathogenetic images, hindering the generalizability of mod-els on diverse downstream tasks. Additionally, processing high-resolution WSIs can be computationally expensive. In this paper, we propose a novel “Fine-grained Visual-Semantic Interaction” (FiVE) framework for WSI classi-fication. It is designed to enhance the model's general-izability by leveraging the interaction between localized visual patterns and fine-grained pathological semantics. Specifically, with meticulously designed queries, we start by utilizing a large language model to extract fine-grained pathological descriptions from various non-standardized raw reports. The output descriptions are then reconstructed into fine-grained labels used for training. By introducing a Task-specific Fine-grained Semantics (TFS) module, we enable prompts to capture crucial visual information in WSIs, which enhances representation learning and aug-ments generalization capabilities significantly. Further-more, given that pathological visual patterns are redun-dantly distributed across tissue slices, we sample a subset of visual instances during training. Our method demon-strates robust generalizability and strong transferability, dominantly outperforming the counterparts on the TCGA Lung Cancer dataset with at least 9.19% higher accu-racy in few-shot experiments. The code is available at: https://github.com/lslrius/WSI_FiVE.

Non-displaced femoral neck fracture (NFF) is a common type of hip fracture. Diagnosis and detection of NFF is a challenging task since fractures appear in stochastic directions and are accompanied by repetitive texture. Previous work paid little attention to the directional characteristics of fractures. In this study, we apply a shift rectangle window based transformer framework to automatically detect NFF. Specifically, both vertical rectangle windows and horizontal rectangle windows are constructed to capture directional features. Meanwhile, we introduce the deformable self-attention blocks and a pseudo-RGB preprocess into our framework. Furthermore, we build a mutilcenter dataset including 1606 radiographs to evaluate our framework. We performed one comparative experiment and two ablation studies. Experimental results demonstrate that our framework surpasses existing approaches in terms of accuracy, specificity, sensitivity, and AUC.

Natural images often contain multiple shadow regions, and existing video shadow detection methods tend to fail in fully identifying all shadow regions, since they mainly learned temporal features at single-scale and single memory. In this work, we develop a novel convolutional neural network (CNN) to learn motion-guided multi-scale memory features to obtain multi-scale temporal information based on multiple network memories for boosting video shadow detection. To do so, our network first constructs three memories (i.e., a global memory, a local memory, and a motion memory) to combine spatial context and object motion for detecting shadows. Based on these three memories, we then devise a multi-scale motion-guided long-short transformer (MMLT) module to learn multi-scale temporal and motion memory features for predicting a shadow detection map of the input video frame. Our MMLT module includes a dense-scale long transformer (DLT), a dense-scale short transformer (DST), and a dense-scale motion transformer (DMT) to read three memories for learning multi-scale transformer features. Our DLT, DST, and DMT consist of a set of memory-read pooling attention (MPA) blocks and densely connect these output features of multiple MPA blocks to learn multi-scale transformer features since the scales of these output features are varied. By doing so, we can more accurately identify multiple shadow regions with different sizes from the input video. Moreover, we devise a self-supervised pretext task to pre-training the feature encoder for enhancing the downstream video shadow detection. Experimental results on three benchmark datasets show that our video shadow detection network quantitatively and qualitatively outperforms 26 state-of-the-art methods.

Medical image segmentation is crucial in clinical diagnosis, helping physicians identify and analyze medical conditions. However, this task is often accompanied by challenges like sensitive data, privacy concerns, and expensive annotations. Current research focuses on personalized collaborative training of medical segmentation systems, ignoring that obtaining segmentation annotations is time-consuming and laborious. Achieving a perfect balance between annotation cost and segmentation performance while ensuring local model personalization has become a valuable direction. Therefore, this study introduces a novel Model-Heterogeneous Semi-Supervised Federated (HSSF) Learning framework. It proposes Regularity Condensation and Regularity Fusion to transfer autonomously selective knowledge to ensure the personalization between sites. In addition, to efficiently utilize unlabeled data and reduce the annotation burden, it proposes a Self-Assessment (SA) module and a Reliable Pseudo-Label Generation (RPG) module. The SA module generates self-assessment confidence in real-time based on model performance, and the RPG module generates reliable pseudo-label based on SA confidence. We evaluate our model separately on the Skin Lesion and Polyp Lesion datasets. The results show that our model performs better than other methods characterized by heterogeneity. Moreover, it exhibits highly commendable performance even in homogeneous designs, most notably in region-based metrics. The full range of resources can be readily accessed through the designated repository located at HSSF(github.com) on the platform of GitHub.

Personalized federated learning (PFL) addresses the data heterogeneity challenge faced by general federated learning (GFL). Rather than learning a single global model, with PFL a collection of models are adapted to the unique feature distribution of each site. However, current PFL methods rarely consider self-attention networks which can handle data heterogeneity by long-range dependency modeling and they do not utilize prediction inconsistencies in local models as an indicator of site uniqueness. In this paper, we propose FedDP, a novel fed erated learning scheme with d ual p ersonalization, which improves model personalization from both feature and prediction aspects to boost image segmentation results. We leverage long-range dependencies by designing a local query (LQ) that decouples the query embedding layer out of each local model, whose parameters are trained privately to better adapt to the respective feature distribution of the site. We then propose inconsistency-guided calibration (IGC), which exploits the inter-site prediction inconsistencies to accommodate the model learning concentration. By encouraging a model to penalize pixels with larger inconsistencies, we better tailor prediction-level patterns to each local site. Experimentally, we compare FedDP with the state-of-the-art PFL methods on two popular medical image segmentation tasks with different modalities, where our results consistently outperform others on both tasks. Our code and models are available at https://github.com/jcwang123/PFL-Seg-Trans.

Automatic universal lesion segmentation (ULS) from Computed Tomography (CT) images can ease the burden of radiologists and provide a more accurate assessment than the current Response Evaluation Criteria In Solid Tumors (RECIST) guideline measurement. However, this task is underdeveloped due to the absence of large-scale pixel-wise labeled data. This paper presents a weakly-supervised learning framework to utilize the large-scale existing lesion databases in hospital Picture Archiving and Communication Systems (PACS) for ULS. Unlike previous methods to construct pseudo surrogate masks for fully supervised training through shallow interactive segmentation techniques, we propose to unearth the implicit information from RECIST annotations and thus design a unified RECIST-induced reliable learning (RiRL) framework. Particularly, we introduce a novel label generation procedure and an on-the-fly soft label propagation strategy to avoid noisy training and poor generalization problems. The former, named RECIST-induced geometric labeling, uses clinical characteristics of RECIST to preliminarily and reliably propagate the label. With the labeling process, a trimap divides the lesion slices into three regions, including certain foreground, background, and unclear regions, which consequently enables a strong and reliable supervision signal on a wide region. A topological knowledge-driven graph is built to conduct the on-the-fly label propagation for the optimal segmentation boundary to further optimize the segmentation boundary. Experimental results on a public benchmark dataset demonstrate that the proposed method surpasses the SOTA RECIST-based ULS methods by a large margin. Our approach surpasses SOTA approaches over 2.0%, 1.5%, 1.4%, and 1.6% Dice with ResNet101, ResNet50, HRNet, and ResNest50 backbones.

Multimodal magnetic resonance imaging (MRI) provides complementary information for sub-region analysis of brain tumors. Plenty of methods have been proposed for automatic brain tumor segmentation using four common MRI modalities and achieved remarkable performance. In practice, however, it is common to have one or more modalities missing due to image corruption, artifacts, acquisition protocols, allergy to contrast agents, or simply cost. In this work, we propose a novel two-stage framework for brain tumor segmentation with missing modalities. In the first stage, a multimodal masked autoencoder (M3AE) is proposed, where both random modalities (i.e., modality dropout) and random patches of the remaining modalities are masked for a reconstruction task, for self-supervised learning of robust multimodal representations against missing modalities. To this end, we name our framework M3AE. Meanwhile, we employ model inversion to optimize a representative full-modal image at marginal extra cost, which will be used to substitute for the missing modalities and boost performance during inference. Then in the second stage, a memory-efficient self distillation is proposed to distill knowledge between heterogenous missing-modal situations while fine-tuning the model for supervised segmentation. Our M3AE belongs to the ‘catch-all’ genre where a single model can be applied to all possible subsets of modalities, thus is economic for both training and deployment. Extensive experiments on BraTS 2018 and 2020 datasets demonstrate its superior performance to existing state-of-the-art methods with missing modalities, as well as the efficacy of its components. Our code is available at: https://github.com/ccarliu/m3ae.

BACKGROUND: Metagenomic sequencing is an unbiased approach that can potentially detect all the known and unidentified strains in pathogen detection. Recently, nanopore sequencing has been emerging as a highly potential tool for rapid pathogen detection due to its fast turnaround time. However, identifying pathogen within species is nontrivial for nanopore sequencing data due to the high sequencing error rate. RESULTS: We developed the core gene alleles metagenome strain identification (cgMSI) tool, which uses a two-stage maximum a posteriori probability estimation method to detect pathogens at strain level from nanopore metagenomic sequencing data at low computational cost. The cgMSI tool can accurately identify strains and estimate relative abundance at 1× coverage. CONCLUSIONS: We developed cgMSI for nanopore metagenomic pathogen detection within species. cgMSI is available at https://github.com/ZHU-XU-xmu/cgMSI .

Automated detecting lung infections from computed tomography (CT) data plays an important role for combating coronavirus 2019 (COVID-19). However, there are still some challenges for developing AI system: 1) most current COVID-19 infection segmentation methods mainly relied on 2-D CT images, which lack 3-D sequential constraint; 2) existing 3-D CT segmentation methods focus on single-scale representations, which do not achieve the multiple level receptive field sizes on 3-D volume; and 3) the emergent breaking out of COVID-19 makes it hard to annotate sufficient CT volumes for training deep model. To address these issues, we first build a multiple dimensional-attention convolutional neural network (MDA-CNN) to aggregate multiscale information along different dimension of input feature maps and impose supervision on multiple predictions from different convolutional neural networks (CNNs) layers. Second, we assign this MDA-CNN as a basic network into a novel dual multiscale mean teacher network (DM [Formula: see text]-Net) for semi-supervised COVID-19 lung infection segmentation on CT volumes by leveraging unlabeled data and exploring the multiscale information. Our DM [Formula: see text]-Net encourages multiple predictions at different CNN layers from the student and teacher networks to be consistent for computing a multiscale consistency loss on unlabeled data, which is then added to the supervised loss on the labeled data from multiple predictions of MDA-CNN. Third, we collect two COVID-19 segmentation datasets to evaluate our method. The experimental results show that our network consistently outperforms the compared state-of-the-art methods.

Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community. Given the ability to exploit long-term dependencies, transformers are promising to help atypical convolutional neural networks to learn more contextualized visual representations. However, most of recently proposed transformer-based segmentation approaches simply treated transformers as assisted modules to help encode global context into convolutional representations. To address this issue, we introduce nnFormer (i.e., not-another transFormer), a 3D transformer for volumetric medical image segmentation. nnFormer not only exploits the combination of interleaved convolution and self-attention operations, but also introduces local and global volume-based self-attention mechanism to learn volume representations. Moreover, nnFormer proposes to use skip attention to replace the traditional concatenation/summation operations in skip connections in U-Net like architecture. Experiments show that nnFormer significantly outperforms previous transformer-based counterparts by large margins on three public datasets. Compared to nnUNet, the most widely recognized convnet-based 3D medical segmentation model, nnFormer produces significantly lower HD95 and is much more computationally efficient. Furthermore, we show that nnFormer and nnUNet are highly complementary to each other in model ensembling. Codes and models of nnFormer are available at https://git.io/JSf3i.

Cancer survival prediction requires exploiting related multimodal information (e.g., pathological, clinical and genomic features, etc.) and it is even more challenging in clinical practices due to the incompleteness of patient's multimodal data. Furthermore, existing methods lack sufficient intra- and inter-modal interactions, and suffer from significant performance degradation caused by missing modalities. This manuscript proposes a novel hybrid graph convolutional network, entitled HGCN, which is equipped with an online masked autoencoder paradigm for robust multimodal cancer survival prediction. Particularly, we pioneer modeling the patient's multimodal data into flexible and interpretable multimodal graphs with modality-specific preprocessing. HGCN integrates the advantages of graph convolutional networks (GCNs) and a hypergraph convolutional network (HCN) through node message passing and a hyperedge mixing mechanism to facilitate intra-modal and inter-modal interactions between multimodal graphs. With HGCN, the potential for multimodal data to create more reliable predictions of patient's survival risk is dramatically increased compared to prior methods. Most importantly, to compensate for missing patient modalities in clinical scenarios, we incorporated an online masked autoencoder paradigm into HGCN, which can effectively capture intrinsic dependence between modalities and seamlessly generate missing hyperedges for model inference. Extensive experiments and analysis on six cancer cohorts from TCGA show that our method significantly outperforms the state-of-the-arts in both complete and missing modal settings. Our codes are made available at https://github.com/lin-lcx/HGCN.

Skin lesion segmentation from dermoscopy images is of great significance in the quantitative analysis of skin cancers, which is yet challenging even for dermatologists due to the inherent issues, i.e., considerable size, shape and color variation, and ambiguous boundaries. Recent vision transformers have shown promising performance in handling the variation through global context modeling. Still, they have not thoroughly solved the problem of ambiguous boundaries as they ignore the complementary usage of the boundary knowledge and global contexts. In this paper, we propose a novel cross-scale boundary-aware transformer, XBound-Former, to simultaneously address the variation and boundary problems of skin lesion segmentation. XBound-Former is a purely attention-based network and catches boundary knowledge via three specially designed learners. First, we propose an implicit boundary learner (im-Bound) to constrain the network attention on the points with noticeable boundary variation, enhancing the local context modeling while maintaining the global context. Second, we propose an explicit boundary learner (ex-Bound) to extract the boundary knowledge at multiple scales and convert it into embeddings explicitly. Third, based on the learned multi-scale boundary embeddings, we propose a cross-scale boundary learner (X-Bound) to simultaneously address the problem of ambiguous and multi-scale boundaries by using learned boundary embedding from one scale to guide the boundary-aware attention on the other scales. We evaluate the model on two skin lesion datasets and one polyp lesion dataset, where our model consistently outperforms other convolution- and transformer-based models, especially on the boundary-wise metrics. All resources could be found in https://github.com/jcwang123/xboundformer.

The fusion of multi-modal medical data is essential to assist medical experts to make treatment decisions for precision medicine. For example, combining the whole slide histopathological images (WSIs) and tabular clinical data can more accurately predict the lymph node metastasis (LNM) of papillary thyroid carcinoma before surgery to avoid unnecessary lymph node resection. However, the huge-sized WSI provides much more high-dimensional information than low-dimensional tabular clinical data, making the information alignment challenging in the multi-modal WSI analysis tasks. This paper presents a novel transformer-guided multi-modal multi-instance learning framework to predict lymph node metastasis from both WSIs and tabular clinical data. We first propose an effective multi-instance grouping scheme, named siamese attention-based feature grouping (SAG), to group high-dimensional WSIs into representative low-dimensional feature embeddings for fusion. We then design a novel bottleneck shared-specific feature transfer module (BSFT) to explore the shared and specific features between different modalities, where a few learnable bottleneck tokens are utilized for knowledge transfer between modalities. Moreover, a modal adaptation and orthogonal projection scheme were incorporated to further encourage BSFT to learn shared and specific features from multi-modal data. Finally, the shared and specific features are dynamically aggregated via an attention mechanism for slide-level prediction. Experimental results on our collected lymph node metastasis dataset demonstrate the efficiency of our proposed components and our framework achieves the best performance with AUC (area under the curve) of 97.34%, outperforming the state-of-the-art methods by over 1.27%.

Multi-instance learning (MIL) is widely adop- ted for automatic whole slide image (WSI) analysis and it usually consists of two stages, i.e., instance feature extraction and feature aggregation. However, due to the "weak supervision" of slide-level labels, the feature aggregation stage would suffer from severe over-fitting in training an effective MIL model. In this case, mining more information from limited slide-level data is pivotal to WSI analysis. Different from previous works on improving instance feature extraction, this paper investigates how to exploit the latent relationship of different instances (patches) to combat overfitting in MIL for more generalizable WSI classification. In particular, we propose a novel Multi-instance Rein- forcement Contrastive Learning framework (MuRCL) to deeply mine the inherent semantic relationships of different patches to advance WSI classification. Specifically, the proposed framework is first trained in a self-supervised manner and then finetuned with WSI slide-level labels. We formulate the first stage as a contrastive learning (CL) process, where positive/negative discriminative feature sets are constructed from the same patch-level feature bags of WSIs. To facilitate the CL training, we design a novel reinforcement learning-based agent to progressively update the selection of discriminative feature sets according to an online reward for slide-level feature aggregation. Then, we further update the model with labeled WSI data to regularize the learned features for the final WSI classification. Experimental results on three public WSI classification datasets (Camelyon16, TCGA-Lung and TCGA-Kidney) demonstrate that the proposed MuRCL outperforms state-of-the-art MIL models. In addition, MuRCL can achieve comparable performance to other state-of-the-art MIL models on TCGA-Esca dataset.

Current representation learning methods for whole slide image (WSI) with pyramidal resolutions are inherently homogeneous and flat, which cannot fully exploit the multiscale and heterogeneous diagnostic information of different structures for comprehensive analysis. This paper presents a novel graph neural network-based multiple instance learning framework (i.e., H^2-MIL) to learn hierarchical representation from a heterogeneous graph with different resolutions for WSI analysis. A heterogeneous graph with the “resolution” attribute is constructed to explicitly model the feature and spatial-scaling relationship of multi-resolution patches. We then design a novel resolution-aware attention convolution (RAConv) block to learn compact yet discriminative representation from the graph, which tackles the heterogeneity of node neighbors with different resolutions and yields more reliable message passing. More importantly, to explore the task-related structured information of WSI pyramid, we elaborately design a novel iterative hierarchical pooling (IHPool) module to progressively aggregate the heterogeneous graph based on scaling relationships of different nodes. We evaluated our method on two public WSI datasets from the TCGA project, i.e., esophageal cancer and kidney cancer. Experimental results show that our method clearly outperforms the state-of-the-art methods on both tumor typing and staging tasks.

Unsupervised pretraining based on contrastive learning has made significant progress recently and showed comparable or even superior transfer learning performance to traditional supervised pretraining on various tasks. In this work, we first empirically investigate when and why unsupervised pretraining surpasses supervised counterparts for image classification tasks with a series of control experiments. Besides the commonly used accuracy, we further analyze the results qualitatively with the class activation maps and assess the learned representations quantitatively with the representation entropy and uniformity. Our core finding is that it is the amount of information effectively perceived by the learning model that is crucial to transfer learning, instead of absolute size of the dataset. Based on this finding, we propose Classification Activation Map guided contrastive (CAMtrast) learning which better utilizes the label supervsion to strengthen supervised pretraining, by making the networks perceive more information from the training images. CAMtrast is evaluated with three fundamental visual learning tasks: image recognition, object detection, and semantic segmentation, on various public datasets. Experimental results show that our CAMtrast effectively improves the performance of supervised pretraining, and that its performance is superior to both unsupervised counterparts and a recent related work which similarly attempted improving supervised pretraining.

Automatic delineation of organ-at-risk (OAR) and gross-tumor-volume (GTV) is of great significance for radiotherapy planning. However, it is a challenging task to learn powerful representations for accurate delineation under limited pixel (voxel)-wise annotations. Contrastive learning at pixel-level can alleviate the dependency on annotations by learning dense representations from unlabeled data. Recent studies in this direction design various contrastive losses on the feature maps, to yield discriminative features for each pixel in the map. However, pixels in the same map inevitably share semantics to be closer than they actually are, which may affect the discrimination of pixels in the same map and lead to the unfair comparison to pixels in other maps. To address these issues, we propose a separated region-level contrastive learning scheme, namely SepaReg, the core of which is to separate each image into regions and encode each region separately. Specifically, SepaReg comprises two components: a structure-aware image separation (SIS) module and an intra- and inter-organ distillation (IID) module. The SIS is proposed to operate on the image set to rebuild a region set under the guidance of structural information. The inter-organ representation will be learned from this set via typical contrastive losses cross regions. On the other hand, the IID is proposed to tackle the quantity imbalance in the region set as tiny organs may produce fewer regions, by exploiting intra-organ representations. We conducted extensive experiments to evaluate the proposed model on a public dataset and two private datasets. The experimental results demonstrate the effectiveness of the proposed model, consistently achieving better performance than state-of-the-art approaches. Code is available at https://github.com/jcwang123/Separate_CL.

Survival prediction of esophageal cancer is an essential task for doctors to make personalized cancer treatment plans. However, handcrafted features from medical images need prior medical knowledge, which is usually limited and not complete, yielding unsatisfying survival predictions. To address these challenges, we propose a novel and efficient deep learning-based survival prediction framework for evaluating clinical outcomes before concurrent chemoradiotherapy. The proposed model consists of two key components: a 3D Coordinate Attention Convolutional Autoencoder (CACA) and an uncertainty-based jointly Optimizing Cox Model (UOCM). The CACA is built upon an autoencoder structure with 3D coordinate attention layers, capturing latent representations and encoding 3D spatial characteristics with precise positional information. Additionally, we designed an Uncertainty-based jointly Optimizing Cox Model, which jointly optimizes the CACA and survival prediction task. The survival prediction task models the interactions between a patient's feature signatures and clinical outcome to predict a reliable hazard ratio of patients. To verify the effectiveness of our model, we conducted extensive experiments on a dataset including computed tomography of 285 patients with esophageal cancer. Experimental results demonstrated that the proposed method achieved a C-index of 0.72, outperforming the state-of-the-art method.

The gold standard for diagnosing lymph node metastasis of papillary thyroid carcinoma is to analyze the whole slide histopathological images (WSIs). Due to the large size of WSIs, recent computer-aided diagnosis approaches adopt the multi-instance learning (MIL) strategy and the key part is how to effectively aggregate the information of different instances (patches). In this paper, a novel transformer-guided framework is proposed to predict lymph node metastasis from WSIs, where we incorporate the transformer mechanism to improve the accuracy from three different aspects. First, we propose an effective transformer-based module for discriminative patch feature extraction, including a lightweight feature extractor with a pruned transformer (Tiny-ViT) and a clustering-based instance selection scheme. Next, we propose a new Transformer-MIL module to capture the relationship of different discriminative patches with sparse distribution on WSIs and better nonlinearly aggregate patch-level features into the slide-level prediction. Considering that the slide-level annotation is relatively limited to training a robust Transformer-MIL, we utilize the pathological relationship between the primary tumor and its lymph node metastasis and develop an effective attention-based mutual knowledge distillation (AMKD) paradigm. Experimental results on our collected WSI dataset demonstrate the efficiency of the proposed Transformer-MIL and attention-based knowledge distillation. Our method outperforms the state-of-the-art methods by over 2.72% in AUC (area under the curve).

Low-shot (one/few-shot) segmentation has attracted increasing attention as it works well with limited annotation. State-of-the-art low-shot segmentation methods on natural images usually focus on implicit representation learning for each novel class, such as learning prototypes, deriving guidance features via masked average pooling, and segmenting using cosine similarity in feature space. We argue that low-shot segmentation on medical images should step further to explicitly learn dense correspondences between images to utilize the anatomical similarity. The core ideas are inspired by the classical practice of multi-atlas segmentation, where the indispensable parts of atlas-based segmentation, i.e., registration, label propagation, and label fusion are unified into a single framework in our work. Specifically, we propose two alternative baselines, i.e., the Siamese-Baseline and Individual-Difference-Aware Baseline, where the former is targeted at anatomically stable structures (such as brain tissues), and the latter possesses a strong generalization ability to organs suffering large morphological variations (such as abdominal organs). In summary, this work sets up a benchmark for low-shot 3D medical image segmentation and sheds light on further understanding of atlas-based few-shot segmentation.

Metagenomics data provide rich information for the detection of foodborne pathogens from food and environmental samples that are mixed with complex background bacteria strains. While pathogen detection from metagenomic sequencing data has become an activity of increasing interest, shotgun sequencing of uncultured food samples typically produces data that contain reads from many different organisms, making accurate strain typing a challenging task. Particularly, as many pathogens may contain a common set of genes that are highly similar to those from normal bacteria in food samples, traditional strain-level abundance profiling approaches do not perform well at detecting pathogens of very low abundance levels. To overcome this limitation, we propose an abundance correction method based on species-specific genomic regions to achieve high sensitivity and high specificity in target pathogen detection at low abundance.

Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization; algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions. In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts).

Saliency detection is a fundamental and challenging task in computer vision, which aims at distinguishing the most conspicuous objects or regions in an image. Existing deep-learning methods mainly rely on the entire image to learn the global context information for saliency detection, which loses the spatial relation and results in ambiguity in predicting saliency maps. In this paper, we propose a novel deep sub-region network (DSR-Net) equipped with a sequence of sub-region dilated blocks (SRDB) by aggregating multi-scale salient context information of multiple sub-regions, such that the global context information from the whole image and local contexts from sub-regions are fused together, making the saliency prediction more accurate. Our SRDB separates the input feature map at different layers of a convolutional neural network (CNN) into different sub-regions and then designs a parallel ASPP module to refine feature maps at each sub-region. Experiments on the five widely-used saliency benchmark datasets demonstrate that our network outperforms recent state-of-the-art saliency detectors quantitatively and qualitatively on all the benchmarks.

We introduce a one-shot segmentation method to alleviate the burden of manual annotation for medical images. The main idea is to treat one-shot segmentation as a classical atlas-based segmentation problem, where voxel-wise correspondence from the atlas to the unlabelled data is learned. Subsequently, segmentation label of the atlas can be transferred to the unlabelled data with the learned correspondence. However, since ground truth correspondence between images is usually unavailable, the learning system must be well-supervised to avoid mode collapse and convergence failure. To overcome this difficulty, we resort to the forward-backward consistency, which is widely used in correspondence problems, and additionally learn the backward correspondences from the warped atlases back to the original atlas. This cycle-correspondence learning design enables a variety of extra, cycle-consistency-based supervision signals to make the training process stable, while also boost the performance. We demonstrate the superiority of our method over both deep learning-based one-shot segmentation methods and a classical multi-atlas segmentation method via thorough experiments.

Fully convolutional neural networks have made promising progress in joint liver and liver tumor segmentation. Instead of following the debates over 2D versus 3D networks (for example, pursuing the balance between large-scale 2D pretraining and 3D context), in this paper, we novelly identify the wide variation in the ratio between intra- and inter-slice resolutions as a crucial obstacle to the performance. To tackle the mismatch between the intra- and inter-slice information, we propose a slice-aware 2.5D network that emphasizes extracting discriminative features utilizing not only in-plane semantics but also out-of-plane coherence for each separate slice. Specifically, we present a slice-wise multi-input multi-output architecture to instantiate such a design paradigm, which contains a Multi-Branch Decoder (MD) with a Slice-centric Attention Block (SAB) for learning slice-specific features and a Densely Connected Dice (DCD) loss to regularize the inter-slice predictions to be coherent and continuous. Based on the aforementioned innovations, we achieve state-of-the-art results on the MICCAI 2017 Liver Tumor Segmentation (LiTS) dataset. Besides, we also test our model on the ISBI 2019 Segmentation of THoracic Organs at Risk (SegTHOR) dataset, and the result proves the robustness and generalizability of the proposed method in other segmentation tasks.

Lymph node metastasis is one of the most significant diagnostic indicators in breast cancer, which is traditionally observed under the microscope by pathologists. In recent years, computerized histology diagnosis has become one of the most rapidly expanding directions in the field of medical image computing, which aims to alleviate pathologists' workload and simultaneously reduce misdiagnosis rate. However, automatic detection of lymph node metastases from whole slide images remains a challenging problem, due to the large-scale data with enormous resolutions and existence of hard mimics resulting in a large number of false positives. In this paper, we propose a novel framework by leveraging fully convolutional networks for efficient inference to meet the speed requirement for clinical practice, while reconstructing dense predictions under different offsets for ensuring accurate detection on both microand macro-metastases. Incorporating with the strategies of asynchronous sample prefetching and hard negative mining, the network can be effectively trained. Extensive experiments on the benchmark dataset of 2016 Camelyon Grand Challenge corroborated the efficacy of our method. Compared with the state-of-the-art methods, our method achieved superior performance with a faster speed on the tumor localization task and even surpassed human performance on the WSI classification task.

Enhancement of vessels in medical images is still an unsolved problem. Multiscale approaches were proposed to improve the vessel enhancement effect based on the structure size and image resolution. Vessel enhancing diffusion (VED) filter is one of the multiscale approaches, which was based on the scale space theory. VED performs well on enhancing vessel structures but cannot preserve complex structures such as the vessel junctions. In this paper, a structure-preserving diffusion tensor is defined in the diffusion equation, which brings a structure-preserving vessel enhancing diffusion filter. Through the multiscale framework, the proposed method enhances the vessel structures especially the complex structure such as junctions. Experimental evaluation performed on various vessel data sets demonstrated the effectiveness of the proposed method.