Survival prediction of cancers is crucial for clinical practice, as it informs mortality risks and influences treatment plans. However, a static model trained on a single dataset fails to adapt to the dynamically evolving clinical environment and continuous data streams, limiting its practical utility. While continual learning (CL) offers a solution to learn dynamically from new datasets, existing CL methods primarily focus on unimodal inputs and suffer from severe catastrophic forgetting in survival prediction. In real-world scenarios, multimodal inputs often provide comprehensive and complementary information, such as whole slide images and genomics; and neglecting inter-modal correlations negatively impacts the performance. To address the two challenges of catastrophic forgetting and complex inter-modal interactions between gigapixel whole slide images and genomics, we propose ConSurv, the first multimodal continual learning (MMCL) method for survival analysis. ConSurv incorporates two key components: Multi-staged Mixture of Experts (MS-MoE) and Feature Constrained Replay (FCR). MS-MoE captures both task-shared and task-specific knowledge at different learning stages of the network, including two modality encoders and the modality fusion component, learning inter-modal relationships. FCR further enhances learned knowledge and mitigates forgetting by restricting feature deviation of previous data at different levels, including encoder-level features of two modalities and the fusion-level representations. Additionally, we introduce a new benchmark integrating four datasets, Multimodal Survival Analysis Incremental Learning (MSAIL), for comprehensive evaluation in the CL setting. Extensive experiments demonstrate that ConSurv outperforms competing methods across multiple metrics.

Computational pathology, which involves analyzing whole slide images for automated cancer diagnosis, relies on multiple instance learning, where performance depends heavily on the feature extractor and aggregator. Recent Pathology Foundation Models (PFMs), pretrained on large-scale histopathology data, have significantly enhanced both the extractor and aggregator, but they lack a systematic analysis framework. In this survey, we present a hierarchical taxonomy organizing PFMs through a top-down philosophy applicable to foundation model analysis in any domain: model scope, model pretraining, and model design. Additionally, we systematically categorize PFM evaluation tasks into slide-level, patch-level, multimodal, and biological tasks, providing comprehensive benchmarking criteria. Our analysis identifies critical challenges in both PFM development (pathology-specific methodology, end-to-end pretraining, data-model scalability) and utilization (effective adaptation, model maintenance), paving the way for future directions in this promising field. Resources referenced in this survey are available at https://github.com/BearCleverProud/AwesomeWSI.

Multiple Instance Learning (MIL) and transformers are increasingly popular in histopathology Whole Slide Image (WSI) classification. However, unlike human pathologists who selectively observe specific regions of histopathology tissues under different magnifications, most methods do not incorporate multiple resolutions of the WSIs, hierarchically and attentively, thereby leading to a loss of focus on the WSIs and information from other resolutions. To resolve this issue, we propose a Hierarchical Attention-Guided Multiple Instance Learning framework to fully exploit the WSIs. This framework can dynamically and attentively discover the discriminative regions across multiple resolutions of the WSIs. Within this framework, an Integrated Attention Transformer is proposed to further enhance the performance of the transformer and obtain a more holistic WSI (bag) representation. This transformer consists of multiple Integrated Attention Modules, which is the combination of a transformer layer and an aggregation module that produces a bag representation based on every instance representation in that bag. The experimental results show that our method achieved state-of-the-art performances on multiple datasets, including Camelyon16, TCGA-RCC, TCGA-NSCLC, and an in-house IMGC dataset. The code is available at https://github.com/BearCleverProud/HAG-MIL.

Extraction of meaningful information from large experimental data sets is a key element in bioinformatics research. One of the challenges is to identify genomic markers in Hepatitis B Virus (HBV) that are associated with HCC (liver cancer) development by comparing the complete genomic sequences of HBV among patients with HCC and those without HCC. In this study, a data mining framework, which includes molecular evolution analysis, clustering, feature selection, classifier learning, and classification, is introduced. Our research group has collected HBV DNA sequences, either genotype B or C, from over 200 patients specifically for this project. In the molecular evolution analysis and clustering, three subgroups have been identified in genotype C and a clustering method has been developed to separate the subgroups. In the feature selection process, potential markers are selected based on Information Gain for further classifier learning. Then, meaningful rules are learned by our algorithm called the Rule Learning, which is based on Evolutionary Algorithm. Also, a new classification method by Nonlinear Integral has been developed. Good performance of this method comes from the use of the fuzzy measure and the relevant nonlinear integral. The nonadditivity of the fuzzy measure reflects the importance of the feature attributes as well as their interactions. These two classifiers give explicit information on the importance of the individual mutated sites and their interactions toward the classification (potential causes of liver cancer in our case). A thorough comparison study of these two methods with existing methods is detailed. For genotype B, genotype C subgroups C1, C2, and C3, important mutation markers (sites) have been found, respectively. These two classification methods have been applied to classify never-seen-before examples for validation. The results show that the classification methods have more than 70 percent accuracy and 80 percent sensitivity for most data sets, which are considered high as an initial scanning method for liver cancer diagnosis.