Cross-scale Attention Guided Multi-instance Learning for Crohn's Disease Diagnosis with Pathological Images

  title={Cross-scale Attention Guided Multi-instance Learning for Crohn's Disease Diagnosis with Pathological Images},
  author={Ruining Deng and Can Cui and Lucas W. Remedios and Shunxing Bao and R. Michael Womick and Sophie Chiron and Jia Li and Joseph T. Roland and Ken S. Lau and Qi Liu and Keith T. Wilson and Yao Wang and Lori A. Coburn and Bennett A. Landman and Yuankai Huo},
  journal={Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings},
  • Ruining DengC. Cui Yuankai Huo
  • Published 15 August 2022
  • Computer Science
  • Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings
Multi-instance learning (MIL) is widely used in the computer-aided interpretation of pathological Whole Slide Images (WSIs) to solve the lack of pixel-wise or patch-wise annotations. Often, this approach directly applies "natural image driven" MIL algorithms which overlook the multi-scale (i.e. pyramidal) nature of WSIs. Off-the-shelf MIL algorithms are typically deployed on a single-scale of WSIs (e.g., 20× magnification), while human pathologists usually aggregate the global and local… 

Figures and Tables from this paper



RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification

Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning

  • Bin LiYin LiK. Eliceiri
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
This work proposes a MIL-based method for WSI classification and tumor detection that does not require localized annotations, and introduces a novel MIL aggregator that models the relations of the instances in a dual-stream architecture with trainable distance measurement.

Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images

A new CNN-based cancer subtype classification method is developed by effectively combining multiple-instance, domain adversarial, and multi-scale learning frameworks in order to overcome practical difficulties.

Adaptive Weighting Multi-Field-Of-View CNN for Semantic Segmentation in Pathology

A novel semantic segmentation method, called Adaptive-Weighting-Multi-Field-of-View-CNN (AWMF-CNN), that can adaptively use image features from images with different magnifications to segment multiple cancer subtype regions in the input image.

WSISA: Making Survival Prediction from Whole Slide Histopathological Images

This paper proposes an effective Whole Slide Histopathological Images Survival Analysis framework (WSISA) that can efficiently exploit and utilize all discriminative patterns in WSIs to predict patients survival status and applies it to the survival predictions of glioma and non-small-cell lung cancer.

Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology

This work proposes to train an in-domain feature extractor on histology images using MoCo v2, a recent self-supervised learning algorithm and demonstrates that feature extractors trained via self- supervised learning can act as drop-in replacements to significantly improve existing machine learning techniques in histology.

SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification

It is demonstrated that conventional patch-based processing is redundant for certain WSI classification tasks where high resolution is only required in a minority of cases and a method is proposed for the selective use of high resolution processing based on the confidence of predictions on downscaled WSIs, called the Selective Objective Switch (SOS).

Patch-Based Convolutional Neural Network for Whole Slide Tissue Image Classification

A novel Expectation-Maximization (EM) based method is formulated that automatically locates discriminative patches robustly by utilizing the spatial relationships of patches and applies it to the classification of glioma and non-small-cell lung carcinoma cases into subtypes.

Multi-scale learning based segmentation of glands in digital colonrectal pathology images

A multi-scale learning based segmentation scheme for the glands in the colon-rectal digital pathology slides is proposed, which learns the gland and non-gland textures from a set of training images in various scales through a sparse dictionary representation.