BREAST CANCER CAD SYSTEM BY USING TRANSFER LEARNING AND ENHANCED ROI

Print

ABSTRACT

Computer systems are being employed in specialized professions such as medical diagnosis to alleviate some of the costs and to improve dependability and scalability. This paper implements a computer aided breast cancer diagnosis system. It utilizes the publicly available mini MIAS mammography image dataset. Images are preprocessed to clean isolate breast tissue region. Extracted regions are used to adjust and verify a pretrained convolutional deep neural network, the GoogLeNet. The implemented model shows good performance results compared to other published works with accuracy of 86.6%, sensitivity of 75% and specificity of 88.9%. 

FULL TEXT

HOW TO CITE THIS PAPER

Al-Huseiny, M. S., & Sajit, A. S. (2022). Breast cancer CAD system by using transfer learning and enhanced ROI. Applied Computer Science, 18(1), 99-111. https://doi.org/10.23743/acs-2022-08
Al-Huseiny, Muayed S, and Ahmed S Sajit. "Breast Cancer Cad System by Using Transfer Learning and Enhanced Roi." Applied Computer Science 18, no. 1 (2022): 99-111.
M. S. Al-Huseiny and A. S. Sajit, "Breast cancer CAD system by using transfer learning and enhanced ROI," Applied Computer Science, vol. 18, no. 1, pp. 99-111, 2022, doi: 10.23743/acs-2022-08.
Al-Huseiny MS, Sajit AS. Breast cancer CAD system by using transfer learning and enhanced ROI. Applied Computer Science. 2022;18(1):99-111.