Breast Cancer Detection using Explainable AI and Quantum Neural Network

Abstract

The number one cancer type for women happens to be breast cancer. Women of any age are more likely to have this disorder because of where they live, their hormones, and the way they live. Women are more likely to be hurt by this. Many more women will have a better chance of living if breast cancer is found earlier. Computers can detect breast cancer early, improve treatment, and increase survival. Therefore, in this article, three models are proposed for the segmentation and classification of breast cancer. The DeepLabv3 model is trained on the fine-tuned hyperparameters for segmentation. The results are computed on BUSIS and DDSM datasets with the accuracy of 99% and 98% respectively. After that for classification of the breast cancer on different magnification levels. The explainable XAI model is designed on the selected fifteen layers and trained on the fine-tuned hyperparameters for breast cancer classification. This model provides the accuracy of. To analyze the classification outcomes quantum neural network is designed on the selected layers, number of Qubits, and hyperparameters. The classification results are computed on the BreakHis publicly dataset at magnification levels of 40x, 100x, 200x, and 400x. The proposed XAI model provides an accuracy of 96.67% and 100% using a quantum neural network for breast cancer classification.