CELNet: Evidence Localization for Pathology Images using Weakly Supervised Learning

Abstract

Despite deep convolutional neural networks boost the performance of image classification and segmentation in digital pathology analysis, they are usually weak in interpretability for clinical applications or require heavy annotations to achieve object localization. To overcome this problem, we propose a weakly supervised learning-based approach that can effectively learn to localize the discriminative evidence for a diagnostic label from weakly labeled training data. Experimental results show that our proposed method can reliably pinpoint the location of cancerous evidence supporting the decision of interest, while still achieving a competitive performance on glimpse-level and slide-level histopathologic cancer detection tasks.

arXiv commentAccepted for MICCAI 2019

References in corpus (4)

• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• Detecting Cancer Metastases on Gigapixel Pathology Images
• Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules
• Improving High Resolution Histology Image Classification with Deep Spatial Fusion Network

Cited by in corpus (3)

• Deep neural network models for computational histopathology: A survey
• Survey of XAI in digital pathology
• Gigapixel Histopathological Image Analysis using Attention-based Neural Networks