Analysis of Dimensional Influence of Convolutional Neural Networks for Histopathological Cancer Classification

TL;DR

This paper investigates how scaling the width, depth, and resolution of CNNs affects their ability to classify histopathological cancer images, demonstrating that compound scaling yields the best results.

Contribution

It introduces a systematic analysis of dimensional scaling in CNN architectures for cancer classification, highlighting the effectiveness of compound scaling.

Findings

High-resolution inputs improve classification accuracy.

Compound scaling outperforms individual dimension scaling.

Complex cancer scans require deep, wide, high-resolution CNNs.

Abstract

Convolutional Neural Networks can be designed with different levels of complexity depending upon the task at hand. This paper analyzes the effect of dimensional changes to the CNN architecture on its performance on the task of Histopathological Cancer Classification. The research starts with a baseline 10-layer CNN model with (3 X 3) convolution filters. Thereafter, the baseline architecture is scaled in multiple dimensions including width, depth, resolution and a combination of all of these. Width scaling involves inculcating greater number of neurons per CNN layer, whereas depth scaling involves deepening the hierarchical layered structure. Resolution scaling is performed by increasing the dimensions of the input image, and compound scaling involves a hybrid combination of width, depth and resolution scaling. The results indicate that histopathological cancer scans are very complex in nature and hence require high resolution images fed to a large hierarchy of Convolution, MaxPooling, Dropout and Batch Normalization layers to extract all the intricacies and perform perfect classification. Since compound scaling the baseline model ensures that all the three dimensions: width, depth and resolution are scaled, the best performance is obtained with compound scaling. This research shows that better performance of CNN models is achieved by compound scaling of the baseline model for the task of Histopathological Cancer Classification.