v156: Proceedings of COMPAY 2021

2026-06-10 · Source: Proceedings of Machine Learning Research · Field: Science & Research — Artificial Intelligence & Machine Learning, Health & Medical Research · Depth: Expert, short

Summary

The MICCAI Workshop on Computational Pathology (Volume 156, 2021) presented significant advancements in applying artificial intelligence to digital pathology, focusing on enhancing diagnostic and prognostic capabilities. Papers explored diverse deep learning and multiple instance learning (MIL) approaches for tasks such as molecular subtype prediction in breast cancer, ER & PR status prediction from H&E Whole Slide Images (WSIs), and glioma sub-type classification. Key methodologies included improving Mask R-CNN for nuclei instance segmentation, multi-scale regional attention Deeplab3+ for plasma cell segmentation, and deep learning for interpretable end-to-end survival prediction in gastrointestinal cancer histopathology. Innovations also covered random multi-channel image synthesis for multiplexed immunofluorescence, robust quad-tree based WSI registration, unsupervised domain adaptation for histopathological cell segmentation, and graph analytics toolkits like HistoCartography. The workshop highlighted a broad spectrum of computational techniques, including self-supervised learning for dMMR/MSI detection and sparse convolutional context-aware MIL, demonstrating progress across various cancer types and imaging modalities.

Key takeaway

This MICCAI workshop volume highlights significant deep learning advances in computational pathology, addressing critical tasks from nuclei segmentation and cancer classification to molecular subtype and survival prediction. Papers introduce novel methods like SparseConvMIL, Multi-scale Graph Networks, and self-supervised learning, improving accuracy and interpretability across H&E and multiplexed imaging. These innovations offer pathologists and researchers tools for enhanced diagnostic precision, biomarker discovery, and prognostic assessment in various cancers, including breast, gastrointestinal, and thyroid.

Topics

• Computational Pathology
• Deep Learning
• Whole Slide Imaging
• Multiple Instance Learning
• Cancer Diagnosis

Code references

• bmdeep/SegPC2021
• butkej/MIL4Cyto
• KatherLab/Survival
• histocartography/histocartography
• MarvinLer/SparseConvMIL

Best for: Computer Vision Engineer, AI Scientist, Machine Learning Engineer, Research Scientist

Related on AIssential

• v254: Proceedings of MICCAI COMPAYL 2024 — Volume 254 presents the proceedings of the MICCAI Workshop on Computational Pathology held on October 6, 2024, in Marrakesh, Morocco, showcasing advancements in applying artificial intelligence to histopathology.
• v227: Proceedings of Medical Imaging with Deep Learning 2023 — Volume 227 of "Medical Imaging with Deep Learning," held in Nashville, TN, USA, from July 10-12, 2023, presents significant advancements in applying deep learning across diverse medical imaging challenges.
• Efficient AI-Driven Multi-Section Whole Slide Image Analysis for Biochemical Recurrence Prediction in Prostate Cancer — A novel AI framework predicts prostate cancer biochemical recurrence using multi-section whole slide images, outperforming clinical benchmarks.
• Meta-encoder: a unified integration framework for multiple pathological foundation models in cancer detection — The Meta-Encoder integrates multiple pathological foundation models to improve cancer detection and molecular characterization.
• Mitosis Detection in the Wild: Multi-Tumor and Context-Aware Generalization in the MIDOG 2025 Challenge — Automated mitosis detection models exhibit significant generalization gaps "in the wild" beyond curated hotspot regions.
• Label-free multiphoton microscopy and machine learning for recognition of hepatocellular carcinoma — Label-free multiphoton microscopy combined with machine learning accurately identifies hepatocellular carcinoma.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Proceedings of Machine Learning Research.