Analysis of Transferred Pre-Trained Deep Convolution Neural Networks in Breast Masses Recognition

TL;DR

This study investigates how freezing different layers of a pre-trained VGG19 CNN affects breast cancer detection accuracy and training efficiency using mammogram images.

Contribution

It systematically analyzes layer freezing strategies in VGG19 for improved breast cancer classification performance.

Findings

Freezing the first block of VGG19 yields the highest sensitivity of 95.64%.

Freezing certain layers reduces training time compared to full training.

Layer freezing can enhance detection accuracy in mammogram classification.

Abstract

Breast cancer detection based on pre-trained convolution neural network (CNN) has gained much interest among other conventional computer-based systems. In the past few years, CNN technology has been the most promising way to find cancer in mammogram scans. In this paper, the effect of layer freezing in a pre-trained CNN is investigated for breast cancer detection by classifying mammogram images as benign or malignant. Different VGG19 scenarios have been examined based on the number of convolution layer blocks that have been frozen. There are a total of six scenarios in this study. The primary benefits of this research are twofold: it improves the model's ability to detect breast cancer cases and it reduces the training time of VGG19 by freezing certain layers.To evaluate the performance of these scenarios, 1693 microbiological images of benign and malignant breast cancers were utilized. According to the reported results, the best recognition rate was obtained from a frozen first block of VGG19 with a sensitivity of 95.64 %, while the training of the entire VGG19 yielded 94.48%.