aiqbench analysis
CRISP introduces an unsupervised framework that automates multi-slide pathology analysis by reducing redundancy and selecting representative patches to capture tumor heterogeneity. This approach matches or exceeds current standards that rely on single pathologist-selected slides, effectively addressing the inefficiency of processing gigapixel images without discarding critical data. For a tech audience, the key takeaway is the shift from subjective slide selection to an autonomous retrieval index that fully leverages spatially distinct tumor regions across entire case archives.
CRISP -- Clustering-Based Redundancy-Reduced Instance Sampling for Pathology Case Representation and Retrieval
arXiv:2605.24253v3 Announce Type: replace-cross Abstract: Digital pathology archives increasingly contain multiple whole-slide images (WSIs) per case, capturing spatially distinct tumor regions and reflecting intrinsic morphological heterogeneity. However, most existing approaches rely on a single pathologist-selected slide, thereby discarding potentially informative evidence distributed across the remaining WSIs. To date, no autonomous framework has been proposed for comprehensive multi-WSI case processing. Here, we present an unsupervised framework for case-level analysis that integrates information from all available slides within a case. Rather than relying on a single designated slide, the proposed approach constructs case-level representations by selectively distilling informative patches across WSIs. We introduce Clustering-Based Redundancy-Reduced Instance Sampling for Pathology (CRISP), a two-stage framework that first reduces redundancy within individual WSIs and subsequently applies clustering-based sampling to select a compact yet representative set of patches for the entire case. The resulting patch set captures case-level heterogeneity while avoiding exhaustive processing of gigapixel images, and directly serves as a retrieval index. Using two Mayo Clinic breast cancer datasets for diagnosis and treatment planning, we demonstrate that CRISP consistently matches or surpasses the current standard practice of combined model and pathologist slide selection for patient/case search and retrieval. By automating case-level processing and eliminating subjective WSI selection, CRISP potentially enables the exploitation of clinically relevant information distributed across multiple WSIs that is currently overlooked.
Abstract:Digital pathology archives increasingly contain multiple whole-slide images (WSIs) per case, capturing spatially distinct tumor regions and reflecting intrinsic morphological heterogeneity. However, most existing approaches rely on a single pathologist-selected slide, thereby discarding potentially informative evidence distributed across the remaining WSIs. To date, no autonomous framework has been proposed for comprehensive multi-WSI case processing. Here, we present an unsupervised framework for case-level analysis that integrates information from all available slides within a case. Rather than relying on a single designated slide, the proposed approach constructs case-level representations by selectively distilling informative patches across WSIs. We introduce Clustering-Based Redundancy-Reduced Instance Sampling for Pathology (CRISP), a two-stage framework that first reduces redundancy within individual WSIs and subsequently applies clustering-based sampling to select a compact yet representative set of patches for the entire case. The resulting patch set captures case-level heterogeneity while avoiding exhaustive processing of gigapixel images, and directly serves as a retrieval index. Using two Mayo Clinic breast cancer datasets for diagnosis and treatment planning, we demonstrate that CRISP consistently matches or surpasses the current standard practice of combined model and pathologist slide selection for patient/case search and retrieval. By automating case-level processing and eliminating subjective WSI selection, CRISP potentially enables the exploitation of clinically relevant information distributed across multiple WSIs that is currently overlooked.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
arXiv:2605.24253 [cs.CV]
(or arXiv:2605.24253v3 [cs.CV] for this version)
Full text under the publisher's open licence · 234 words
Related coverage
Building Blocks for Foundation Model Training and Inference on AWS
Hugging Face · May 11, 2026
[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026
Rethinking EEG-Based Disease Diagnosis: Decoupling Instance Representation Learning from Subject-Level Supervision
arXiv · Jul 31, 2026
How Intuit built an agentic disaster recovery assistant with Amazon Bedrock
AWS · Sep 4, 2026