Segmenting 3D blood vessels is a critical yet challenging task in medical image analysis. This is due to significant imaging modality-specific variations in artifacts, vascular patterns and scales, signal-to-noise ratios, and background tissues. These variations, along with domain gaps arising from varying imaging protocols, limit the generalization of existing supervised learning-based methods, requiring tedious voxel-level annotations for each dataset separately. While foundation models promise to alleviate this limitation, they typically fail to generalize to the task of blood vessel segmentation, posing a unique, complex problem. In this work, we present vesselFM, a foundation model designed specifically for the broad task of 3D blood vessel segmentation. Unlike previous models, vesselFM can effortlessly generalize to unseen domains. To achieve zero-shot generalization, we train vesselFM on three heterogeneous data sources: a large, curated annotated dataset, data generated by a domain randomization scheme, and data sampled from a flow matching-based generative model. Extensive evaluations show that vesselFM outperforms state-of-the-art medical image segmentation foundation models across four (pre-)clinically relevant imaging modalities in zero-, one-, and few-shot scenarios, therefore providing a universal solution for 3D blood vessel segmentation.

Current state-of-the-art generative models map noise to data distributions by matching flows or scores. A key limitation of these models is their inability to readily integrate available partial observations and additional priors. In contrast, energy-based models (EBMs) address this by incorporating corresponding scalar energy terms. Here, we propose Energy Matching, a framework that endows flow-based approaches with the flexibility of EBMs. Far from the data manifold, samples move from noise to data along irrotational, optimal transport paths. As they approach the data manifold, an entropic energy term guides the system into a Boltzmann equilibrium distribution, explicitly capturing the underlying likelihood structure of the data. We parameterize these dynamics with a single time-independent scalar field, which serves as both a powerful generator and a flexible prior for effective regularization of inverse problems. The present method substantially outperforms existing EBMs on CIFAR-10 and ImageNet generation in terms of fidelity, while retaining simulation-free training of transport-based approaches away from the data manifold. Furthermore, we leverage the flexibility of the method to introduce an interaction energy that supports the exploration of diverse modes, which we demonstrate in a controlled protein generation setting. This approach learns a scalar potential energy, without time conditioning, auxiliary generators, or additional networks, marking a significant departure from recent EBM methods. We believe this simplified yet rigorous formulation significantly advances EBMs capabilities and paves the way for their wider adoption in generative modeling in diverse domains.

Recent progress in vision-language modeling for 3D medical imaging has been fueled by large-scale computed tomography (CT) corpora with paired free-text reports, stronger architectures, and powerful pretrained models. This has enabled applications such as automated report generation and text-conditioned 3D image synthesis. Yet, current approaches struggle with high-resolution, long-sequence volumes: contrastive pretraining often yields vision encoders that are misaligned with clinical language, and slice-wise tokenization blurs fine anatomy, reducing diagnostic performance on downstream tasks. We introduce BTB3D (Better Tokens for Better 3D), a causal convolutional encoder-decoder that unifies 2D and 3D training and inference while producing compact, frequency-aware volumetric tokens. A three-stage training curriculum enables (i) local reconstruction, (ii) overlapping-window tiling, and (iii) long-context decoder refinement, during which the model learns from short slice excerpts yet generalizes to scans exceeding $300$ slices without additional memory overhead. BTB3D sets a new state-of-the-art on two key tasks: it improves BLEU scores and increases clinical F1 by 40\% over CT2Rep, CT-CHAT, and Merlin for report generation; and it reduces FID by 75\% and halves FVD compared to GenerateCT and MedSyn for text-to-CT synthesis, producing anatomically consistent $512\times512\times241$ volumes. These results confirm that precise three-dimensional tokenization, rather than larger language backbones alone, is essential for scalable vision-language modeling in 3D medical imaging. The codebase is available at: https://github.com/ibrahimethemhamamci/BTB3D

Direct image-to-graph transformation is a challenging task that involves solving object detection and relationship prediction in a single model. Due to this task's complexity, large training datasets are rare in many domains, making the training of deep-learning methods challenging. This data sparsity necessitates transfer learning strategies akin to the state-of-the-art in general computer vision. In this work, we introduce a set of methods enabling cross-domain and cross-dimension learning for image-to-graph trans-formers. We propose (1) a regularized edge sampling loss to effectively learn object relations in multiple domains with different numbers of edges, (2) a domain adaptation frame-work for image-to-graph transformers aligning image- and graph-level features from different domains, and (3) a projection function that allows using 2D data for training 3D transformers. We demonstrate our method's utility in cross-domain and cross-dimension experiments, where we utilize labeled data from 2D road networks for simultaneous learning in vastly different target domains. Our method consistently outperforms standard transfer learning and self-supervised pretraining on challenging benchmarks, such as retinal or whole-brain vessel graph extraction.11Code: github.com/AlexanderHBerger/cross-dim_i2g

Cardiovascular diseases (CVD) can be diagnosed using various diagnostic modalities. The electrocardiogram (ECG) is a cost-effective and widely available diagnostic aid that provides functional information of the heart. However, its ability to classify and spatially localise CVD is limited. In contrast, cardiac magnetic resonance (CMR) imaging provides detailed structural information of the heart and thus enables evidence-based diagnosis of CVD, but long scan times and high costs limit its use in clinical routine. In this work, we present a deep learning strategy for cost-effective and comprehensive cardiac screening solely from ECG. Our approach combines multimodal contrastive learning with masked data modelling to transfer domain-specific information from CMR imaging to ECG representations. In extensive experiments using data from 40,044 UK Biobank subjects, we demonstrate the utility and generalisability of our method for subject-specific risk prediction of CVD and the prediction of cardiac phenotypes using only ECG data. Specifically, our novel multimodal pre-training paradigm improves performance by up to 12.19% for risk prediction and 27.59% for phenotype prediction. In a qualitative analysis, we demonstrate that our learned ECG representations incorporate information from CMR image regions of interest. Our entire pipeline is publicly available at https://github.com/oetu/MMCL-ECG-CMR.

Cardiac magnetic resonance (CMR) imaging is the gold standard for non-invasive cardiac assessment, offering rich spatio-temporal views of the heart’s anatomy and physiology. Patient-level health factors, such as demographics, metabolic, and lifestyle, are known to substantially influence cardiovascular health and disease risk, yet remain uncaptured by CMR alone. To holistically understand cardiac health and to enable the best possible interpretation of an individual’s disease risk, CMR and patient-level factors must be jointly exploited within an integrated framework. Recent multi-modal approaches have begun to bridge this gap, yet they often rely on limited spatio-temporal data and focus on isolated clinical tasks, thereby hindering the development of a comprehensive representation for cardiac/health evaluation. To overcome these limitations, we introduce ViTa , a step toward foundation models that delivers a comprehensive representation of the heart and a precise interpretation of individual disease risk. Leveraging data from 42,000 UK Biobank participants, ViTa integrates 3D+T cine stacks from short-axis and long-axis views, enabling a complete capture of the cardiac cycle. These imaging data are then fused with detailed tabular patient-level factors, enabling context-aware insights. This multi-modal paradigm supports a wide spectrum of downstream tasks, including cardiac phenotype and physiological feature prediction, segmentation, and classification of cardiac/metabolic diseases within a single unified framework. By learning a shared latent representation that bridges rich imaging features and patient context, ViTa moves beyond traditional, task-specific models toward a universal, patient-specific understanding of cardiac health, highlighting its potential to advance clinical utility and scalability in cardiac analysis. 2

Ultra-wideband raster-scan optoacoustic mesoscopy (RSOM) is a novel modality that has demonstrated unprecedented ability to visualize epidermal and dermal structures in-vivo. However, an automatic and quantitative analysis of three-dimensional RSOM datasets remains unexplored. In this work we present our framework: Deep Learning RSOM Analysis Pipeline (DeepRAP), to analyze and quantify morphological skin features recorded by RSOM and extract imaging biomarkers for disease characterization. DeepRAP uses a multi-network segmentation strategy based on convolutional neural networks with transfer learning. This strategy enabled the automatic recognition of skin layers and subsequent segmentation of dermal microvasculature with an accuracy equivalent to human assessment. DeepRAP was validated against manual segmentation on 25 psoriasis patients under treatment and our biomarker extraction was shown to characterize disease severity and progression well with a strong correlation to physician evaluation and histology. In a unique validation experiment, we applied DeepRAP in a time series sequence of occlusion-induced hyperemia from 10 healthy volunteers. We observe how the biomarkers decrease and recover during the occlusion and release process, demonstrating accurate performance and reproducibility of DeepRAP. Furthermore, we analyzed a cohort of 75 volunteers and defined a relationship between aging and microvascular features in-vivo. More precisely, this study revealed that fine microvascular features in the dermal layer have the strongest correlation to age. The ability of our newly developed framework to enable the rapid study of human skin morphology and microvasculature in-vivo promises to replace biopsy studies, increasing the translational potential of RSOM.

Recent transformer-based offline video instance segmentation (VIS) approaches achieve encouraging results and significantly outperform online approaches. However, their reliance on the whole video and the immense computational complexity caused by full Spatio-temporal attention limit them in real-life applications such as processing lengthy videos. In this paper, we propose a single-stage transformer-based efficient online VIS framework named InstanceFormer, which is especially suitable for long and challenging videos. We propose three novel components to model short-term and long-term dependency and temporal coherence. First, we propagate the representation, location, and semantic information of prior instances to model short-term changes. Second, we propose a novel memory cross-attention in the decoder, which allows the network to look into earlier instances within a certain temporal window. Finally, we employ a temporal contrastive loss to impose coherence in the representation of an instance across all frames. Memory attention and temporal coherence are particularly beneficial to long-range dependency modeling, including challenging scenarios like occlusion. The proposed InstanceFormer outperforms previous online benchmark methods by a large margin across multiple datasets. Most importantly, InstanceFormer surpasses offline approaches for challenging and long datasets such as YouTube-VIS-2021 and OVIS. Code is available at https://github.com/rajatkoner08/InstanceFormer.

The skeleton of a digital image is a compact representation of its topology, geometry, and scale. It has utility in many computer vision applications, such as image description, segmentation, and registration. However, skeletonization has only seen limited use in contemporary deep learning solutions. Most existing skeletonization algorithms are not differentiable, making it impossible to integrate them with gradient-based optimization. Compatible algorithms based on morphological operations and neural networks have been proposed, but their results often deviate from the geometry and topology of the true medial axis. This work introduces the first three-dimensional skeletonization algorithm that is both compatible with gradient-based optimization and preserves an object’s topology. Our method is exclusively based on matrix additions and multiplications, convolutional operations, basic non-linear functions, and sampling from a uniform probability distribution, allowing it to be easily implemented in any major deep learning library. In benchmarking experiments, we prove the advantages of our skeletonization algorithm compared to non-differentiable, morphological, and neural-network-based baselines. Finally, we demonstrate the utility of our algorithm by integrating it with two medical image processing applications that use gradient-based optimization: deep-learning-based blood vessel segmentation, and multimodal registration of the mandible in computed tomography and magnetic resonance images.

Segmentation models predominantly optimize pixel-overlap-based loss, an objective that is actually inadequate for many segmentation tasks. In recent years, their limitations fueled a growing interest in topology-aware methods, which aim to recover the topology of the segmented structures. However, so far, existing methods only consider global topological properties, ignoring the need to preserve topological features spatially, which is crucial for accurate segmentation. We introduce the concept of induced matchings from persistent homology to achieve a spatially correct matching between persistence barcodes in a segmentation setting. Based on this concept, we define the Betti matching error as an interpretable, topologically and feature-wise accurate metric for image segmentations, which resolves the limitations of the Betti number error. Our Betti matching error is differentiable and efficient to use as a loss function. We demonstrate that it improves the topological performance of segmentation networks significantly across six diverse datasets while preserving the performance with respect to traditional scores. Our code is publicly available (https://github.com/nstucki/Betti-matching/).

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094.

Novel multimodal imaging methods are capable of generating extensive, super high resolution datasets for preclinical research. Yet, a massive lack of annotations prevents the broad use of deep learning to analyze such data. In this paper, we introduce a novel generative method which leverages real anatomical information to generate realistic image-label pairs of tumours. We construct a dualpathway generator, for the anatomical image and label, trained in a cycle-consistent setup, constrained by an independent, pretrained segmentor. Our method performs two concurrent tasks: domain adaptation and semantic synthesis, which, to our knowledge, has not been done before. The generated images yield significant quantitative improvement compared to existing methods that specialize in either of these tasks. To validate the quality of synthesis, we train segmentation networks on a dataset augmented with the synthetic data, substantially improving the segmentation over the baseline.

Modeling of brain tumor dynamics has the potential to advance therapeutic planning. Current modeling approaches resort to numerical solvers that simulate the tumor progression according to a given differential equation. Using highly-efficient numerical solvers, a single forward simulation takes up to a few minutes of compute. At the same time, clinical applications of tumor modeling often imply solving an inverse problem, requiring up to tens of thousands of forward model evaluations when used for a Bayesian model personalization via sampling. This results in a total inference time prohibitively expensive for clinical translation. While recent data-driven approaches become capable of emulating physics simulation, they tend to fail in generalizing over the variability of the boundary conditions imposed by the patient-specific anatomy. In this paper, we propose a learnable surrogate for simulating tumor growth which maps the biophysical model parameters directly to simulation outputs, i.e. the local tumor cell densities, whilst respecting patient geometry. We test the neural solver in a Bayesian model personalization task for a cohort of glioma patients. Bayesian inference using the proposed surrogate yields estimates analogous to those obtained by solving the forward model with a regular numerical solver. The near real-time computation cost renders the proposed method suitable for clinical settings. The code is available at https://github.com/IvanEz/tumor-surrogate.

Accurate segmentation of tubular, network-like structures, such as vessels, neurons, or roads, is relevant to many fields of research. For such structures, the topology is their most important characteristic; particularly preserving connectedness: in the case of vascular networks, missing a connected vessel entirely alters the blood-flow dynamics. We introduce a novel similarity measure termed centerlineDice (short clDice), which is calculated on the inter-section of the segmentation masks and their (morphological) skeleta. We theoretically prove that clDice guarantees topology preservation up to homotopy equivalence for binary 2D and 3D segmentation. Extending this, we pro-pose a computationally efficient, differentiable loss function (soft-clDice) for training arbitrary neural segmentation networks. We benchmark the soft-clDice loss on five public datasets, including vessels, roads and neurons (2D and 3D). Training on soft-clDice leads to segmentation with more accurate connectivity information, higher graph similarity, and better volumetric scores.

The aim of this paper is to provide a comprehensive overview of the MICCAI 2020 AutoImplant Challenge. The approaches and publications submitted and accepted within the challenge will be summarized and reported, highlighting common algorithmic trends and algorithmic diversity. Furthermore, the evaluation results will be presented, compared and discussed in regard to the challenge aim: seeking for low cost, fast and fully automated solutions for cranial implant design. Based on feedback from collaborating neurosurgeons, this paper concludes by stating open issues and post-challenge requirements for intra-operative use. The codes can be found at https://github.com/Jianningli/tmi.

We develop two techniques based on alternating minimization and alternating directions method of multipliers for phase retrieval (PR) by employing a variable-splitting approach in a maximum likelihood estimation framework. This leads to an additional equality constraint, which is incorporated in the optimization framework using a quadratic penalty. Both algorithms are iterative, wherein the updates are computed in closed-form. Experimental results show that: (i) the proposed techniques converge faster than the state-of-the-art PR algorithms; (ii) the complexity is comparable to the state of the art; and (iii) the performance does not depend critically on the choice of the penalty parameter. We also show how sparsity can be incorporated within the variable splitting framework and demonstrate concrete applications to image reconstruction in frequency-domain optical-coherence tomography.

The typical approach for solving the problem of single-image super-resolution (SR) is to learn a nonlinear mapping between the low-resolution (LR) and high-resolution (HR) representations of images in a training set. Training-based approaches can be tuned to give high accuracy on a given class of images, but they call for retraining if the HR → LR generative model deviates or if the test images belong to a different class, which limits their applicability. On the other hand, we propose a solution that does not require a training dataset. Our method relies on constructing a dynamic convolutional network (DCN) to learn the relation between the consecutive scales of Gaussian and Laplacian pyramids. The relation is in turn used to predict the detail at a finer scale, thus leading to SR. Comparisons with state-of-the-art techniques on standard datasets show that the proposed DCN approach results in about 0.8 and 0.3 dB gain in peak signal-to-noise ratio for 2× and 3× SR, respectively. The structural similarity index is on par with the competing techniques.