Multiscale Detection of Cancerous Tissue in High Resolution Slide Scans

TL;DR

This paper introduces a multi-scale CNN-based algorithm for detecting cancerous tissues in high-resolution slide scans, effectively handling a wide range of tumor sizes with improved accuracy and real-time performance.

Contribution

The paper proposes a novel multi-scale detection method that modifies CNN receptive fields and adaptive anchor boxes, enhancing detection of varied tumor sizes in pathology images.

Findings

Improved detection accuracy for small-scale tumor features.

Real-time analysis capability for high-resolution pathology images.

Effective handling of diverse tumor sizes in a single pass.

Abstract

We present an algorithm for multi-scale tumor (chimeric cell) detection in high resolution slide scans. The broad range of tumor sizes in our dataset pose a challenge for current Convolutional Neural Networks (CNN) which often fail when image features are very small (8 pixels). Our approach modifies the effective receptive field at different layers in a CNN so that objects with a broad range of varying scales can be detected in a single forward pass. We define rules for computing adaptive prior anchor boxes which we show are solvable under the equal proportion interval principle. Two mechanisms in our CNN architecture alleviate the effects of non-discriminative features prevalent in our data - a foveal detection algorithm that incorporates a cascade residual-inception module and a deconvolution module with additional context information. When integrated into a Single Shot MultiBox Detector (SSD), these additions permit more accurate detection of small-scale objects. The results permit efficient real-time analysis of medical images in pathology and related biomedical research fields.