Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification

Abstract

Mammogram classification is directly related to computer-aided diagnosis of breast cancer. Traditional methods rely on regions of interest (ROIs) which require great efforts to annotate. Inspired by the success of using deep convolutional features for natural image analysis and multi-instance learning (MIL) for labeling a set of instances/patches, we propose end-to-end trained deep multi-instance networks for mass classification based on whole mammogram without the aforementioned ROIs. We explore three different schemes to construct deep multi-instance networks for whole mammogram classification. Experimental results on the INbreast dataset demonstrate the robustness of proposed networks compared to previous work using segmentation and detection annotations.

MICCAI 2017 Camera Ready

Cited by in corpus (8)

• AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomy
• Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides
• All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification
• Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models
• Weakly and Semi Supervised Detection in Medical Imaging via Deep Dual Branch Net
• Introducing instance label correlation in multiple instance learning. Application to cancer detection on histopathological images
• Deformable Gabor Feature Networks for Biomedical Image Classification
• Multiple Instance Learning for Uplift Modeling