Feature based Sequential Classifier with Attention Mechanism

TL;DR

This paper introduces DeepCIN, a hierarchical deep learning pipeline that models the vertical distribution of abnormalities in cervical histopathology images to improve CIN classification accuracy to pathologist-level performance.

Contribution

The novel hierarchical network pipeline combines sequence generation and attention-based fusion to analyze spatial distribution of features in histopathology images for CIN grading.

Findings

Achieves pathologist-level accuracy in CIN classification.

Effectively models bottom-to-top feature relationships in epithelium.

Outperforms existing methods in automated CIN grading.

Abstract

Cervical cancer is one of the deadliest cancers affecting women globally. Cervical intraepithelial neoplasia (CIN) assessment using histopathological examination of cervical biopsy slides is subject to interobserver variability. Automated processing of digitized histopathology slides has the potential for more accurate classification for CIN grades from normal to increasing grades of pre-malignancy: CIN1, CIN2 and CIN3. Cervix disease is generally understood to progress from the bottom (basement membrane) to the top of the epithelium. To model this relationship of disease severity to spatial distribution of abnormalities, we propose a network pipeline, DeepCIN, to analyze high-resolution epithelium images (manually extracted from whole-slide images) hierarchically by focusing on localized vertical regions and fusing this local information for determining Normal/CIN classification. The pipeline contains two classifier networks: 1) a cross-sectional, vertical segment-level sequence generator (two-stage encoder model) is trained using weak supervision to generate feature sequences from the vertical segments to preserve the bottom-to-top feature relationships in the epithelium image data; 2) an attention-based fusion network image-level classifier predicting the final CIN grade by merging vertical segment sequences. The model produces the CIN classification results and also determines the vertical segment contributions to CIN grade prediction. Experiments show that DeepCIN achieves pathologist-level CIN classification accuracy.