Cross-Cancer Knowledge Transfer in WSI-based Prognosis Prediction

• URL: http://arxiv.org/abs/2508.13482v2
• Date: Thu, 25 Sep 2025 07:16:02 GMT
• Title: Cross-Cancer Knowledge Transfer in WSI-based Prognosis Prediction
• Authors: Pei Liu, Luping Ji, Jiaxiang Gou, Xiangxiang Zeng,
• Abstract summary: Whole-Slide Image (WSI) is an important tool for estimating cancer prognosis.<n>This paper makes a paradigm shift to knowledge transfer and presents the first preliminary yet systematic study on cross-cancer prognosis knowledge transfer in WSIs.
• Score: 26.98955103296043
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Whole-Slide Image (WSI) is an important tool for estimating cancer prognosis. Current studies generally follow a conventional cancer-specific paradigm where one cancer corresponds to one model. However, it naturally struggles to scale to rare tumors and cannot utilize the knowledge of other cancers. Although a multi-task learning-like framework has been studied recently, it usually has high demands on computational resources and needs considerable costs in iterative training on ultra-large multi-cancer WSI datasets. To this end, this paper makes a paradigm shift to knowledge transfer and presents the first preliminary yet systematic study on cross-cancer prognosis knowledge transfer in WSIs, called CROPKT. It has three major parts: (i) we curate a large dataset (UNI2-h-DSS) with 26 cancers and use it to measure the transferability of WSI-based prognostic knowledge across different cancers (including rare tumors); (ii) beyond a simple evaluation merely for benchmark, we design a range of experiments to gain deeper insights into the underlying mechanism of transferability; (iii) we further show the utility of cross-cancer knowledge transfer, by proposing a routing-based baseline approach (ROUPKT) that could often efficiently utilize the knowledge transferred from off-the-shelf models of other cancers. We hope CROPKT could serve as an inception and lay the foundation for this nascent paradigm, i.e., WSI-based prognosis prediction with cross-cancer knowledge transfer. Our source code is available at https://github.com/liupei101/CROPKT.

Related papers

• A Contrastive Learning Framework for Breast Cancer Detection [0.0]
  This study introduces a Contrastive Learning (CL) framework, which excels with smaller labeled datasets.<n>We observed a 96.7% accuracy in detecting breast cancer on benchmark datasets INbreast and MIAS.
  arXiv  Detail & Related papers  (2025-09-24T18:43:38Z)
• Multimodal Cancer Modeling in the Age of Foundation Model Embeddings [1.7983573166060747]
  We train classical machine learning models over free-text embeddings of cancer data.<n>We demonstrate the ease and additive effect of multimodal fusion, outperforming unimodal models.<n>We show the benefit of including pathology report text and rigorously evaluate the effect of model-based text summarization and hallucination.
  arXiv  Detail & Related papers  (2025-05-12T15:47:21Z)
• Pathological Prior-Guided Multiple Instance Learning For Mitigating Catastrophic Forgetting in Breast Cancer Whole Slide Image Classification [50.899861205016265]
  We propose a new framework PaGMIL to mitigate catastrophic forgetting in breast cancer WSI classification.<n>Our framework introduces two key components into the common MIL model architecture.<n>We evaluate the continual learning performance of PaGMIL across several public breast cancer datasets.
  arXiv  Detail & Related papers  (2025-03-08T04:51:58Z)
• Transfer Learning Strategies for Pathological Foundation Models: A Systematic Evaluation in Brain Tumor Classification [8.170992842607339]
  Foundation models pretrained on large-scale pathology datasets have shown promising results across various diagnostic tasks.<n>We analyzed 254 cases comprising five major tumor types: glioblastoma, astrocytoma, oligodendroglioma, primary central nervous system lymphoma, and metastatic tumors.<n>We found that foundation models demonstrated robust classification performance with as few as 10 patches per case, despite the traditional assumption that extensive per-case image sampling is necessary.
  arXiv  Detail & Related papers  (2025-01-19T11:18:34Z)
• Survival Prediction Across Diverse Cancer Types Using Neural Networks [40.392772795903795]
  Gastric cancer and Colon adenocarcinoma represent widespread and challenging malignancies. Medical community has embraced the 5-year survival rate as a vital metric for estimating patient outcomes. This study introduces a pioneering approach to enhance survival prediction models for gastric and Colon adenocarcinoma patients.
  arXiv  Detail & Related papers  (2024-04-11T21:47:13Z)
• Knowledge-Informed Machine Learning for Cancer Diagnosis and Prognosis: A review [2.2268038840298714]
  We review the state-of-the-art machine learning studies that adopted the fusion of biomedical knowledge and data. We provide an overview of diverse forms of knowledge representation and current strategies of knowledge integration into machine learning pipelines.
  arXiv  Detail & Related papers  (2024-01-12T07:01:36Z)
• Cancer-Net PCa-Gen: Synthesis of Realistic Prostate Diffusion Weighted Imaging Data via Anatomic-Conditional Controlled Latent Diffusion [68.45407109385306]
  In Canada, prostate cancer is the most common form of cancer in men and accounted for 20% of new cancer cases for this demographic in 2022. There has been significant interest in the development of deep neural networks for prostate cancer diagnosis, prognosis, and treatment planning using diffusion weighted imaging (DWI) data. In this study, we explore the efficacy of latent diffusion for generating realistic prostate DWI data through the introduction of an anatomic-conditional controlled latent diffusion strategy.
  arXiv  Detail & Related papers  (2023-11-30T15:11:03Z)
• MGCT: Mutual-Guided Cross-Modality Transformer for Survival Outcome Prediction using Integrative Histopathology-Genomic Features [2.3942863352287787]
  Mutual-Guided Cross-Modality Transformer (MGCT) is a weakly-supervised, attention-based multimodal learning framework. We propose MGCT to combine histology features and genomic features to model the genotype-phenotype interactions within the tumor microenvironment.
  arXiv  Detail & Related papers  (2023-11-20T10:49:32Z)
• RACR-MIL: Rank-aware contextual reasoning for weakly supervised grading of squamous cell carcinoma using whole slide images [0.5190659258584331]
  Squamous cell carcinoma is the most common cancer subtype, with an increasing incidence and a significant impact on cancer-related mortality.<n>We propose RACR-MIL, the first weakly-supervised SCC grading approach achieving robust generalization across multiple anatomies.<n>Our model achieves state-of-the-art performance across multiple SCC datasets, achieving 3-9% higher grading accuracy, resilience to class imbalance, and up to 16% improved tumor localization.
  arXiv  Detail & Related papers  (2023-08-29T20:25:49Z)
• Post-Hoc Explainability of BI-RADS Descriptors in a Multi-task Framework for Breast Cancer Detection and Segmentation [48.08423125835335]
  MT-BI-RADS is a novel explainable deep learning approach for tumor detection in Breast Ultrasound (BUS) images. It offers three levels of explanations to enable radiologists to comprehend the decision-making process in predicting tumor malignancy.
  arXiv  Detail & Related papers  (2023-08-27T22:07:42Z)
• Automated Knowledge Modeling for Cancer Clinical Practice Guidelines [1.1083289076967895]
  Clinical Practice Guidelines (CPGs) for cancer diseases evolve rapidly due to new evidence generated by active research. Currently, CPGs are primarily published in a document format that is ill-suited for managing this developing knowledge. This work proposes an automated method for extraction of knowledge from NCCN CPGs in Oncology.
  arXiv  Detail & Related papers  (2023-07-15T18:07:08Z)
• Deep Reinforcement Learning Framework for Thoracic Diseases Classification via Prior Knowledge Guidance [49.87607548975686]
  The scarcity of labeled data for related diseases poses a huge challenge to an accurate diagnosis. We propose a novel deep reinforcement learning framework, which introduces prior knowledge to direct the learning of diagnostic agents. Our approach's performance was demonstrated using the well-known NIHX-ray 14 and CheXpert datasets.
  arXiv  Detail & Related papers  (2023-06-02T01:46:31Z)
• Cancer-Net BCa-S: Breast Cancer Grade Prediction using Volumetric Deep Radiomic Features from Synthetic Correlated Diffusion Imaging [82.74877848011798]
  The prevalence of breast cancer continues to grow, affecting about 300,000 females in the United States in 2023. The gold-standard Scarff-Bloom-Richardson (SBR) grade has been shown to consistently indicate a patient's response to chemotherapy. In this paper, we study the efficacy of deep learning for breast cancer grading based on synthetic correlated diffusion (CDI$s$) imaging.
  arXiv  Detail & Related papers  (2023-04-12T15:08:34Z)
• A Multi-Institutional Open-Source Benchmark Dataset for Breast Cancer Clinical Decision Support using Synthetic Correlated Diffusion Imaging Data [82.74877848011798]
  Cancer-Net BCa is a multi-institutional open-source benchmark dataset of volumetric CDI$s$ imaging data of breast cancer patients. Cancer-Net BCa is publicly available as a part of a global open-source initiative dedicated to accelerating advancement in machine learning to aid clinicians in the fight against cancer.
  arXiv  Detail & Related papers  (2023-04-12T05:41:44Z)
• Meta-information-aware Dual-path Transformer for Differential Diagnosis of Multi-type Pancreatic Lesions in Multi-phase CT [41.199716328468895]
  We develop a dual-path transformer to exploit the feasibility of classification and segmentation of pancreatic lesions. The proposed method consists of a CNN-based segmentation path (S-path) and a transformer-based classification path (C-path) Our results show that our method can enable accurate classification and segmentation of the full taxonomy of pancreatic lesions.
  arXiv  Detail & Related papers  (2023-03-02T03:34:28Z)
• Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images [40.52487429030841]
  We propose Knowledge-enhanced Auto Diagnosis (KAD) to guide vision-supervised pre-training using paired chest X-rays and radiology reports. We evaluate KAD on four external X-ray datasets and demonstrate that its zero-shot performance is superior to that of fully-language models.
  arXiv  Detail & Related papers  (2023-02-27T18:53:10Z)
• Enhancing Clinical Support for Breast Cancer with Deep Learning Models using Synthetic Correlated Diffusion Imaging [66.63200823918429]
  We investigate enhancing clinical support for breast cancer with deep learning models. We leverage a volumetric convolutional neural network to learn deep radiomic features from a pre-treatment cohort. We find that the proposed approach can achieve better performance for both grade and post-treatment response prediction.
  arXiv  Detail & Related papers  (2022-11-10T03:02:12Z)
• Multiple Instance Neural Networks Based on Sparse Attention for Cancer Detection using T-cell Receptor Sequences [10.199698726118003]
  We propose multiple instance neural networks based on sparse attention (MINN-SA) to enhance the performance in cancer detection and explainability. MINN-SA yields the highest area under the ROC curve (AUC) scores on average measured across 10 different types of cancers.
  arXiv  Detail & Related papers  (2022-08-09T03:24:03Z)
• Self-transfer learning via patches: A prostate cancer triage approach based on bi-parametric MRI [1.3934382972253603]
  Prostate cancer (PCa) is the second most common cancer diagnosed among men worldwide. The current PCa diagnostic pathway comes at the cost of substantial overdiagnosis, leading to unnecessary treatment and further testing. We present a patch-based pre-training strategy to distinguish between clinically significant (cS) and non-clinically significant (ncS) lesions.
  arXiv  Detail & Related papers  (2021-07-22T17:02:38Z)
• Hierarchical Classification of Pulmonary Lesions: A Large-Scale Radio-Pathomics Study [38.78350161086617]
  Diagnosis of pulmonary lesions from computed tomography (CT) is important but challenging for clinical decision making in lung cancer related diseases. Deep learning has achieved great success in computer aided diagnosis (CADx) area for lung cancer, whereas it suffers from label ambiguity due to the difficulty in the radiological diagnosis. Considering that invasive pathological analysis serves as the clinical golden standard of lung cancer diagnosis, in this study, we solve the label ambiguity issue via a large-scale radio-pathomics dataset. This retrospective dataset, named Pulmonary-RadPath, enables development and validation of accurate deep learning systems to predict invasive pathological labels with a non-
  arXiv  Detail & Related papers  (2020-10-08T15:14:34Z)
• Stan: Small tumor-aware network for breast ultrasound image segmentation [68.8204255655161]
  We propose a novel deep learning architecture called Small Tumor-Aware Network (STAN) to improve the performance of segmenting tumors with different size. The proposed approach outperformed the state-of-the-art approaches in segmenting small breast tumors.
  arXiv  Detail & Related papers  (2020-02-03T22:25:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.