Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images

TL;DR

Y-Net is a novel neural network that jointly performs tissue segmentation and discriminative map generation, significantly improving breast biopsy image diagnosis accuracy while reducing model complexity.

Contribution

It introduces Y-Net, an extension of U-Net with a parallel discriminative map branch and modular convolutional blocks, achieving state-of-the-art accuracy with fewer parameters.

Findings

Y-Net achieves state-of-the-art segmentation accuracy.

Y-Net uses 6.6x fewer parameters than competitors.

Discriminative masks improve diagnostic classification by 7%.

Abstract

In this paper, we introduce a conceptually simple network for generating discriminative tissue-level segmentation masks for the purpose of breast cancer diagnosis. Our method efficiently segments different types of tissues in breast biopsy images while simultaneously predicting a discriminative map for identifying important areas in an image. Our network, Y-Net, extends and generalizes U-Net by adding a parallel branch for discriminative map generation and by supporting convolutional block modularity, which allows the user to adjust network efficiency without altering the network topology. Y-Net delivers state-of-the-art segmentation accuracy while learning 6.6x fewer parameters than its closest competitors. The addition of descriptive power from Y-Net's discriminative segmentation masks improve diagnostic classification accuracy by 7% over state-of-the-art methods for diagnostic classification. Source code is available at: https://sacmehta.github.io/YNet.