Title: Automatic pectoral muscles and artefacts removal in mammogram images for improved breast cancer diagnosis

Authors: Saguna Ingle; Amarsinh Vidhate; Sangita Chaudhari

Addresses: Department of Computer Engineering, Ramrao Adik Institute of Technology, D.Y. Patil (Deemed to be University), Navi Mumbai, India ' Department of Computer Engineering, Ramrao Adik Institute of Technology, D.Y. Patil (Deemed to be University), Navi Mumbai, India ' Department of Information Technology, Ramrao Adik Institute of Technology, D.Y. Patil (Deemed to be University), Navi Mumbai, India

Abstract: Breast cancer is leading cause of mortality among women compared to other types of cancers. Hence, early breast cancer diagnosis is crucial to the success of treatment. Various pathological and imaging tests are available for the diagnosis of breast cancer. However, it may introduce errors during detection and interpretation, leading to false-negative and false-positive results due to lack of pre-processing of it. To overcome this issue, we proposed a effective image pre-processing technique-based on Otsu's thresholding and single-seeded region growing (SSRG) to remove artefacts and segment the pectoral muscle from breast mammograms. To validate the proposed method, a publicly available MIAS dataset was utilised. The experimental finding showed that proposed technique improved 18% breast cancer detection accuracy compared to existing methods. The proposed methodology works efficiently for artefact removal and pectoral segmentation at different shapes and nonlinear patterns.

Keywords: breast cancer; artefacts; pectoral muscle; image processing; mammogram; image enhancement.

DOI: 10.1504/IJBRA.2024.142550

International Journal of Bioinformatics Research and Applications, 2024 Vol.20 No.6, pp.627 - 647

Received: 21 Sep 2023
Accepted: 18 Dec 2023
Published online: 08 Nov 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article