Accurate histopathological image segmentation is crucial for precise disease diagnosis and prognosis. Yet, challenges like staining variations, imaging conditions, and tissue diversity impede model generalization across domains, such as different institutes or organs. Traditional domain generalization (DG) techniques, such as data augmentation and feature alignment, excel in classification tasks but face challenges in segmentation tasks due to their dense prediction requirements. These tasks are particularly computationally demanding, and are complicated due to the fine-grained feature variability that arises from the domain differences in histopathological images. To tackle this, we propose the Shallow-Deep Synergy (SDS) approach for the U-Net-based segmentation framework, which capitalizes on the distinctive characteristics of both shallow and deep layers of the U-Net. Specifically, we introduce the fine-grained domain variations in image intensities and textures for shallow layers, while focusing on aligning the pixel-level classification decision boundaries in deep layers by adjusting the optimization trajectory through class-wise gradient and feature alignment. Moreover, the SDS is equipped with a big-batch strategy further boosting alignment efficiency, achieving high accuracy without substantial GPU memory. Extensive experiments conducted on two histopathological segmentation datasets, each representing different domain types, demonstrate that the proposed SDS achieves superior generalization performance compared to existing domain generalization methods, even being competitive with intra-domain models in some cases.

Thanks to the huge accumulation of Electronic Health Records (EHRs), numerous deep learning based predictive models were proposed for this task. Among them, most of the existing state-of-the-art (SOTA) models were built with recurrent neural networks (RNNs). Regardless of their success, RNN-based models mainly suffer from three limitations. (i) Accuracy: the prediction accuracy of RNN-based models drops quickly as the length of EHR sequences increases. (ii) Efficiency: the recurrence property of RNN-based models makes the computation parallelization impossible, and accordingly hurts the efficiency of such models in practice. (iii) Interpretability: the outputs of RNN-based models are difficult to explain due to the unexplainable nature of deep models. In this paper, we resort to the recently advanced attention mechanism to model the dependencies between inputs and outputs, which overcomes shortages of RNN-based models in accuracy and efficiency. As for interpretability, we model the relationships with two linear mappings from the input to the output, which account for two important factors—one is for context-aware information and the other is for time-aware representation—of capturing discriminative features in learning patient’s representations. We empirically demonstrate the effectiveness of the proposed model in both accuracy and computational efficiency, meanwhile, analyze and discuss the reasonability of each explanation approach.

Leukemia classification relies on a detailed cytomorphological examination of Bone Marrow (BM) smear. However, applying existing deep-learning methods to it is facing two significant limitations. Firstly, these methods require large-scale datasets with expert annotations at the cell level for good results and typically suffer from poor generalization. Secondly, they simply treat the BM cytomorphological examination as a multi-class cell classification task, thus failing to exploit the correlation among leukemia subtypes over different hierarchies. Therefore, BM cytomorphological estimation as a time-consuming and repetitive process still needs to be done manually by experienced cytologists. Recently, Multi-Instance Learning (MIL) has achieved much progress in data-efficient medical image processing, which only requires patient-level labels (which can be extracted from the clinical reports). In this paper, we propose a hierarchical MIL framework and equip it with Information Bottleneck (IB) to tackle the above limitations. First, to handle the patient-level label, our hierarchical MIL framework uses attention-based learning to identify cells with high diagnostic values for leukemia classification in different hierarchies. Then, following the information bottleneck principle, we propose a hierarchical IB to constrain and refine the representations of different hierarchies for better accuracy and generalization. By applying our framework to a large-scale childhood acute leukemia dataset with corresponding BM smear images and clinical reports, we show that it can identify diagnostic-related cells without the need for cell-level annotations and outperforms other comparison methods. Furthermore, the evaluation conducted on an independent test cohort demonstrates the high generalizability of our framework.

Multiple instance learning (MIL)-based methods have become the mainstream for processing the megapixel-sized whole slide image (WSI) with pyramid structure in the field of digital pathology. The current MIL-based methods usually crop a large number of patches from WSI at the highest magnification, resulting in a lot of redundancy in the input and feature space. Moreover, the spatial relations between patches can not be sufficiently modeled, which may weaken the model's discriminative ability on fine-grained features. To solve the above limitations, we propose a Multi-scale Graph Transformer (MG-Trans) with information bottleneck for whole slide image classification. MG-Trans is composed of three modules: patch anchoring module (PAM), dynamic structure information learning module (SILM), and multi-scale information bottleneck module (MIBM). Specifically, PAM utilizes the class attention map generated from the multi-head self-attention of vision Transformer to identify and sample the informative patches. SILM explicitly introduces the local tissue structure information into the Transformer block to sufficiently model the spatial relations between patches. MIBM effectively fuses the multi-scale patch features by utilizing the principle of information bottleneck to generate a robust and compact bag-level representation. Besides, we also propose a semantic consistency loss to stabilize the training of the whole model. Extensive studies on three subtyping datasets and seven gene mutation detection datasets demonstrate the superiority of MG-Trans.

Pathological primary tumor (pT) stage focuses on the infiltration degree of the primary tumor to surrounding tissues, which relates to the prognosis and treatment choices. The pT staging relies on the field-of-views from multiple magnifications in the gigapixel images, which makes pixel-level annotation difficult. Therefore, this task is usually formulated as a weakly supervised whole slide image (WSI) classification task with the slide-level label. Existing weakly-supervised classification methods mainly follow the multiple instance learning paradigm, which takes the patches from single magnification as the instances and extracts their morphological features independently. However, they cannot progressively represent the contextual information from multiple magnifications, which is critical for pT staging. Therefore, we propose a structure-aware hierarchical graph-based multi-instance learning framework (SGMF) inspired by the diagnostic process of pathologists. Specifically, a novel graph-based instance organization method is proposed, namely structure-aware hierarchical graph (SAHG), to represent the WSI. Based on that, we design a novel hierarchical attention-based graph representation (HAGR) network to capture the critical patterns for pT staging by learning cross-scale spatial features. Finally, the top nodes of SAHG are aggregated by a global attention layer for bag-level representation. Extensive studies on three large-scale multi-center pT staging datasets with two different cancer types demonstrate the effectiveness of SGMF, which outperforms state-of-the-art up to 5.6% in the F1 score.

Computational Pathology (CPATH) offers the possibility for highly accurate and low-cost automated pathological diagnosis. However, the high time cost of model inference is one of the main issues limiting the application of CPATH methods. Due to the large size of Whole-Slide Image (WSI), commonly used CPATH methods divided a WSI into a large number of image patches at relatively high magnification, then predicted each image patch individually, which is time-consuming. In this paper, we propose a novel Uncertainty-based Model Acceleration (UMA) method for reducing the time cost of model inference, thereby relieving the deployment burden of CPATH applications. Enlightened by the slide-viewing process of pathologists, only a few high-uncertain regions are regarded as “suspicious” regions that need to be predicted at high magnification, and most of the regions in WSI are predicted at low magnification, thereby reducing the times of image patch extraction and prediction. Meanwhile, uncertainty estimation ensures prediction accuracy at low magnification. We take two fundamental CPATH classification tasks (i.e., cancer region detection and subtyping) as examples. Extensive experiments on two large-scale renal cell carcinoma classification datasets demonstrate that our UMA can significantly reduce the time cost of model inference while maintaining competitive classification performance.

Predicting drug combinations according to patients' electronic health records is an essential task in intelligent healthcare systems, which can assist clinicians in ordering safe and effective prescriptions. However, existing work either missed/underutilized the important information lying in the drug molecule structure in drug encoding or has insufficient control over Drug-Drug Interactions (DDIs) rates within the predictions. To address these limitations, we propose CSEDrug, which enhances the drug encoding and DDIs controlling by leveraging multi-faceted drug knowledge, including molecule structures of drugs, Synergistic DDIs (SDDIs), and Antagonistic DDIs (ADDIs). We integrate these types of knowledge into CSEDrug by a graph-based drug encoder and multiple loss functions, including a novel triplet learning loss and a comprehensive DDI controllable loss. We evaluate the performance of CSEDrug in terms of accuracy, effectiveness, and safety on the public MIMIC-III dataset. The experimental results demonstrate that CSEDrug outperforms several state-of-the-art methods and achieves a 2.93% and a 2.77% increase in the Jaccard similarity scores and F1 scores, meanwhile, a 0.68% reduction of the ADDI rate (safer drug combinations), and 0.69% improvement of the SDDI rate (more effective drug combinations).

Patient similarity measurement is an essential step in discovering clinically meaningful subgroups and building case retrieval systems. Most existing studies implement this procedure using similarity measurement algorithms on the multivariate clinical time-series (input space) or the low-dimensional patient representation (representation space) learned by a representation learning model. However, they either suffer from the adverse effects of irrelevant variables in the data or fail to assess the fine-grained similarity underneath the disease progress. In this paper, we propose a method to measure more fine-grained patient similarity in the state space, where each patient is represented by a series of state representations that reveal the dynamic health status. We discuss three desiderata, including stability, personality, and interpretability, for the state representations, and on this basis, develop a supervised predictive model that learns good state representations for identifying similar patients and predicting patient outcomes. Experimental results on the publicly available dataset MIMIC-III show that our method offers a promising direction for precisely identifying similar patients at the state trajectory level, as well as accurately predicting outcomes.

Tissue segmentation is an essential task in computational pathology. However, relevant datasets for such a pixel-level classification task are hard to obtain due to the difficulty of annotation, bringing obstacles for training a deep learning-based segmentation model. Recently, contrastive learning has provided a feasible solution for mitigating the heavy reliance of deep learning models on annotation. Nevertheless, applying contrastive loss to the most abstract image representations, existing contrastive learning frameworks focus on global features, therefore, are less capable of encoding finer-grained features (e.g., pixel-level discrimination) for the tissue segmentation task. Enlightened by domain knowledge, we design three contrastive learning tasks with multi-granularity views (from global to local) for encoding necessary features into representations without accessing annotations. Specifically, we construct: (1) an image-level task to capture the difference between tissue components, i.e., encoding the component discrimination; (2) a superpixel-level task to learn discriminative representations of local regions with different tissue components, i.e., encoding the prototype discrimination; (3) a pixel-level task to encourage similar representations of different tissue components within a local region, i.e., encoding the spatial smoothness. Through our global-to-local pre-training strategy, the learned representations can reasonably capture the domain-specific and fine-grained patterns, making them easily transferable to various tissue segmentation tasks in histopathological images. We conduct extensive experiments on two tissue segmentation datasets, while considering two real-world scenarios with limited or sparse annotations. The experimental results demonstrate that our framework is superior to existing contrastive learning methods and can be easily combined with weakly supervised and semi-supervised segmentation methods.

Clinical time-series is receiving long-term attention in data mining and machine learning communities and has boosted a variety of data-driven applications. Identifying similar patients or subgroups from clinical time-series is an essential step to design tailored treatments in clinical practice. However, most of the existing methods are either purely unsupervised that tend to neglect the patient outcome information or cannot generate personalized patient representation through supervised learning, thus may fail to identify ‘truly similar patients’ (i.e., patients who similar in both outcomes and individual outcome-related clinical variables). To tackle these limitations, we propose a novel predictive clinical time-series analysis framework. Specifically, our framework uses task-specific information to rule out the task-irrelevant factors in each patient data individually and generates the contribution scores that reveal the factors’ importance for the patient outcome. Then a patient representation construction method is proposed to generate task-related and personalized representations by combining remained factors and their contribution scores. At last, similarity measurement or cluster analysis can be conducted. We evaluate our framework on three real-world clinical time-series datasets, empirically demonstrate that our framework achieves improvements in prediction performance, similarity measurement, and clustering, thus potentially benefiting patient-similarity-based precision medicine applications.

Deep learning has proved to be a powerful tool for medical image analysis in recent years. Data imbalance is a common problem in medical images. Dice Loss is widely used in medical image segmentation tasks to address the data imbalance problem. However, it only addresses the imbalance problem between foreground and background yet overlooks another imbalance between easy and hard examples that also severely affects the training process of a learning model. Empirically speaking, an easy example generally contributes less to the overall loss than a hard example. However, in practice, compared with hard examples, a large number of easy examples will be generated from a medical image and will dominate the training model, resulting in sub-optimal training or worse. To tackle this problem, we propose a novel Focal Dice Loss to alleviate the imbalance between hard examples and easy examples. Focal Dice Loss is able to reduce the contribution from easy examples and make the model focus on hard examples through our proposed novel balanced sampling strategy during the training process. Furthermore, to evaluate the effectiveness of our proposed loss functions, we conduct extensive experiments on two real-world medical image datasets with 2D and 3D convolutional neural networks. The experimental results show that our proposed Focal Dice Loss brings a significant improvement in segmentation performance compared to Dice Loss. Moreover, we find that our proposed Focal Dice Loss can effectively alleviate the over-fitting problem.

Building a predictive model based on historical Electronic Health Records (EHRs) for personalized healthcare has become an active research area. Benefiting from the powerful ability of feature extraction, deep learning (DL) approaches have achieved promising performance in many clinical prediction tasks. However, due to the lack of interpretability and trustworthiness, it is difficult to apply DL in real clinical cases of decision making. To address this, in this paper, we propose an interpretable and trustworthy predictive model~(INPREM) for healthcare. Firstly, INPREM is designed as a linear model for interpretability while encoding non-linear relationships into the learning weights for modeling the dependencies between and within each visit. This enables us to obtain the contribution matrix of the input variables, which is served as the evidence of the prediction result(s), and help physicians understand why the model gives such a prediction, thereby making the model more interpretable. Secondly, for trustworthiness, we place a random gate (which follows a Bernoulli distribution to turn on or off) over each weight of the model, as well as an additional branch to estimate data noises. With the help of the Monto Carlo sampling and an objective function accounting for data noises, the model can capture the uncertainty of each prediction. The captured uncertainty, in turn, allows physicians to know how confident the model is, thus making the model more trustworthy. We empirically demonstrate that the proposed INPREM outperforms existing approaches with a significant margin. A case study is also presented to show how the contribution matrix and the captured uncertainty are used to assist physicians in making robust decisions.

Predicting the future health conditions of patients based on Electronic Health Records (EHR) is an important research topic. Due to the temporal nature of EHR data, the major challenge is how to properly model the sequences of patient visits. Recurrent Neural Networks (RNNs) with attention mechanisms are widely employed to address this challenge, but often vulnerable to data insufficiency. Lately, predictive models with the guidance of medical knowledge have been proposed to solve this problem and achieve superior performance. Although these models learn reasonable embeddings (infused with knowledge) for clinical variables, they are not able to fully make use of the underlying information in the knowledge graph. To address this, we propose an end-to-end robust solution, namely Graph Neural networks based Diagnosis Prediction (GNDP), to predict future conditions for patients. Compared with existing methods, GNDP learns the spatial and temporal patterns from patients' sequential graph, in which the domain knowledge is naturally infused. We evaluate our GNDP model against a set of state-of-the-art methods on two real-world EHR datasets and the results demonstrate that our approach significantly outperforms the baseline methods.

Medical images are widely used in the medical domain for the diagnosis and treatment of diseases. Reading a medical image and summarizing its insights is a routine, yet nonetheless time-consuming task, which often represents a bottleneck in the clinical diagnosis process. Automatic report generation can relieve the issues. However, generating medical reports presents two major challenges: (i) it is hard to accurately detect all the abnormalities simultaneously, especially the rare diseases; (ii) a medical image report consists of many paragraphs and sentences, which are longer than natural image captions. We present a new framework to accurately detect the abnormalities and automatically generate medical reports. The report generation model is based on hierarchical recurrent neural network (HRNN). We introduce a topic matching mechanism to HRNN, so as to make generated reports more accurate and diverse. The soft attention mechanism is also introduced to HRNN model. Experimental results on two image-paragraph pair datasets show that our framework outperforms all the state-of-art methods.

Thanks to the widespread adoption of Electronic Health Record (EHR) systems, a variety of data-driven clinical risk prediction approaches have been spawned in recent years. However, there remain three challenges, which if addressed would improve the performance and applicability of such models. (i) Due to the limited data sharing between different health care institutions, the EHR data collected by a single institution is often inadequate or missing some visits records. The limited number of data cannot meet the large sample required of recent approaches especially deep learning models. In addition, the missing records (due to visiting different institution) may contain important health condition of the patient, which if ignored would cause prediction bias. (ii) Few existing approaches take clinical knowledge into account. The auxiliary knowledge if included can greatly reduce the data dependency of many modern learning algorithms. (iii) Most existing deep learning based methods are unable to identify the contribution of each medical event to the final results, which prohibits such models from being widely accepted in practical clinical applications. In this paper, we propose an interpretable and knowledge-guided deep model to address these challenges. Specifically, we distill knowledge from a clinical knowledge graph both explicitly and implicitly, which can not only supplement inadequate patient records but also guide the predicting process of the model. Furthermore, skip-connections and attention mechanisms are adopted to improve the interpretability of our model. In the context of heart failure prediction task, our model outperforms several state-of-the-art methods. Finally, a series of case studies are presented to prove the interpretability of our model.