Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification (2016-12-18T00:00:00.000000Z)

TL;DR

Experimental results on the INbreast dataset demonstrate the robustness of proposed deep networks compared to previous work using segmentation and detection annotations in the training.

Abstract

Mammogram classification is directly related to computer-aided diagnosis of breast cancer. Traditional methods requires great effort to annotate the training data by costly manual labeling and specialized computational models to detect these annotations during test. Inspired by the success of using deep convolutional features for natural image analysis and multi-instance learning for labeling a set of instances/patches, we propose end-to-end trained deep multiinstance networks for mass classification based on whole mammogram without the aforementioned costly need to annotate the training data. 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 deep networks compared to previous work using segmentation and detection annotations in the training.

Authors

Xiaohui Xie

7 papers

Wentao Zhu

5 papers

Y. S. Vang

3 papers

TL;DR

Abstract

Authors

References30 items

Adversarial Deep Structural Networks for Mammographic Mass Segmentation

The Automated Learning of Deep Features for Breast Mass Classification from Mammograms

Learning from Experts: Developing Transferable Deep Features for Patient-Level Lung Cancer Prediction

A deep feature based framework for breast masses classification

Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks

Multi-Instance Deep Learning: Discover Discriminative Local Anatomies for Bodypart Recognition

Breast Cancer Screening for Women at Average Risk: 2015 Guideline Update From the American Cancer Society.

Unregistered Multiview Mammogram Analysis with Pre-trained Deep Learning Models

From Group to Individual Labels Using Deep Features

Hierarchical Extreme Learning Machine for unsupervised representation learning

Deep multiple instance learning for image classification and auto-annotation

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

Mammogram classification using two dimensional discrete wavelet transform and gray-level co-occurrence matrix for detection of breast cancer

Adam: A Method for Stochastic Optimization

ImageNet classification with deep convolutional neural networks

INbreast: toward a full-field digital mammographic database.

Multi-instance multi-label learning

Digital Mammographic Computer Aided Diagnosis (CAD) using Adaptive Level Set Segmentation

Marginalized Multi-Instance Kernels

Use of border information in the classification of mammographic masses

Multiple instance learning with generalized support vector machines

Solving the Multiple Instance Problem with Axis-Parallel Rectangles

Large scale deep learning for computer aided detection of mammographic lesions

Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique

Inbreast-database masses characterization. XXIII CBEB

THE DIGITAL DATABASE FOR SCREENING MAMMOGRAPHY

Gradient-based learning applied to document recognition

The Mammographic Image Analysis Society digital mammogram database

A Threshold Selection Method from Gray-Level Histograms

American cancer society. what are the key statistics about breast cancer?

Field of Study

Journal Information

Name

Venue Information

Name

Type

URL