Detection and Segmentation of Tissue Markers in Mammography: Studying their Impact on an AI Breast Cancer Detection System

Abstract

Breast cancer is the leading cause of cancer death among women. Accordingly, appropriate screening protocols for early diagnosis and treatment are crucial to fight against this disease. Artificial intelligence (AI) plays a significant role in screening mammograms and helping radiologists identify potential abnormalities. When a breast anomaly is detected, a biopsy is taken and a tissue marker is placed in the affected area, serving as a reference point for future treatments. To ensure reliability, it is crucial to comprehend how these tissue markers contribute to the process of breast cancer detection using AI systems. To this end, this study initially presents an image processing algorithm that facilitates the creation of an annotated dataset comprising images with tissue markers. This dataset is then used to develop a deep learning approach that is capable of discriminating mammograms with tissue markers, as well as of segmenting these objects. The study concludes with a methodology for analyzing the performance of an AI system in breast cancer screening. This framework does a comparison between the AI system's detected anomalous regions and the locations of tissue markers. The results highlight the strong performance of the deep learning model in both the segmentation and detection of mammograms with tissue markers. Moreover, the findings demonstrated that regardless of the presence of clips, AI systems can identify potential abnormalities with a reduced probability of marking tissue markers.