ABSTRACT

The breast cancer is one of the most common diseases affecting women worldwide, the World Health Organization reported that over ten thousands approx women died from the disease in 2020 alone, accounting for approximately 10% of all female cancer deaths. As a result, breast cancer diagnosis is one of the most pressing issues that must be addressed as soon as possible. Multiple image modalities, including mammography, echography, and magnetic resonance imaging (MRI), are used to diagnose breast tumours in this context. Chemotherapy is one of the most common treatments for this pathology. However, several side effects (hair loss, osteoporosis, vomiting, and so on) may occur as a result of this treatment, and cancer will not respond to it. The purpose of this paper is to propose a novel method for predicting breast tumour response to treatment, which consists of three major steps: 1. Tumor segmentation from MR images; 2. Feature extraction from segmented tumours to generate a complete and exploitable database; 3. Use of deep and machine learning architectures to compute tumor-response prediction models. The experimental findings are applied to a publicly available QIN Breast DCE-MRI dataset of breast cancer patients. Keywords: Artificial Intelligence, Breast Cancer, MRI, Tumour Received 26th March 2022; Revised 25th April 2022; Accepted 10th July 2022; Available online 1st Jan. 2023
Publication date: 01/01/2023

https://ijbpas.com/pdf/2023/January/MS_IJBPAS_2023_6803.pdf

Download PDF
https://doi.org/10.31032/IJBPAS/2023/12.1.6803