Diving Deep onto Discriminative Ensemble of Histological Hashing & Class-Specific Manifold Learning for Multi-class Breast Carcinoma Taxonomy

TL;DR

This paper introduces a deep learning framework that combines class-specific manifold learning and histological hashing to improve multi-class breast cancer classification accuracy and robustness, enabling near-real-time clinical analysis.

Contribution

It proposes a novel ensemble approach integrating manifold learning and hashing for histopathological image classification, achieving significant accuracy improvements over existing methods.

Findings

95.8% multi-classification accuracy on BreakHis dataset

2.8% overall performance improvement over state-of-the-art

99.3% recognition rate at 200X magnification

Abstract

Histopathological images (HI) encrypt resolution dependent heterogeneous textures & diverse color distribution variability, manifesting in micro-structural surface tissue convolutions. Also, inherently high coherency of cancerous cells poses significant challenges to breast cancer (BC) multi-classification. As such, multi-class stratification is sparsely explored & prior work mainly focus on benign & malignant tissue characterization only, which forestalls further quantitative analysis of subordinate classes like adenosis, mucinous carcinoma & fibroadenoma etc, for diagnostic competence. In this work, a fully-automated, near-real-time & computationally inexpensive robust multi-classification deep framework from HI is presented. The proposed scheme employs deep neural network (DNN) aided discriminative ensemble of holistic class-specific manifold learning (CSML) for underlying HI sub-space embedding & HI hashing based local shallow signatures. The model achieves 95.8% accuracy pertinent to multi-classification & 2.8% overall performance improvement & 38.2% enhancement for Lobular carcinoma (LC) sub-class recognition rate as compared to the existing state-of-the-art on well known BreakHis dataset is achieved. Also, 99.3% recognition rate at 200X & a sensitivity of 100% for binary grading at all magnification validates its suitability for clinical deployment in hand-held smart devices.