Segmentation of breast tumors using cutting-edge semantic segmentation models

ABSTRACT

Early detection of breast cancer is the most important area of mammography research at the moment. It is critical to use computer-aided diagnosis to screen for and prevent breast cancer. In this study, the effectiveness of cutting-edge deep segmentation models for mammography in the detection of breast tumors was investigated. A medical images dataset was compiled and annotated at Lady Reading Hospital, one of the largest teaching hospitals in Pakistan in collaboration with the local health specialists, radiologists, and technologists. A comparison was made between the performance of the segmentation techniques used, and the model that performed the best in detecting tumors and normal breast regions was selected. The evaluation metrics, such as the mean IoU, pixel accuracy, and an in-depth experimental evaluation were used as performance parameters. This investigation determined how well semantic segmentation techniques were performed based on two datasets (cityscapes and mammograms) in this study. The global Dilation 10 semantic segmentation model outperformed the other three semantic segmentation models with a pixel accuracy of 92.98 percent in comparison tests. This paper demonstrates the efficacy of pixel-wise image segmentation techniques and their superiority to other techniques by outperforming other current state-of-the-art automatic image segmentation models.

KEYWORDS:

• Semantic segmentation
• image processing
• image classification
• Deep learning
• breast tumor detection
• mammography

Acknowledgments

This research was funded by the National Nature Science Foundation of China (Grant No. 62174148), National Key Research and Development Program (NKRDP Grant No. SQ2021YFE010807, Grant No. 2016YFE0118400), Zhengzhou 1125 Innovation Project (Grant No. ZZ2018-45), and Ningbo 2025 Key Innovation Project (Grant No. 2019B10129).

Disclosure statement

No potential conflict of interest was reported by the author(s).