Detection of Breast Cancer in Digital Mammograms by Using Artificial Intelligence

Abstract

Abstract Background Daily reading of a large number of normal mammograms ni breast cancer screening programs is a tedious task reducing the attractiveness of the field. The advent of Artificial Intelligence (AI) in medical imaging could, however, provide means to improve the efficiency of mammography screening. Objective Our study aims to emphasize the role of AI system as an aid in detection of breast cancer in digital mammograms. Patients and Methods The main source of data for this study were the mammography studies on the picture archiving and communications system (PACS) of theradiology department, i n Shams university hospitals of the patients referred to the radiology department at Ain Shams university hospitals for screening mammography. Results Our study showed that the improvement in diagnosticperformance and reading times with AI support was observed for the radiologists who were least experienced with mammography while the Al is increased the reading times and had no effect on diagnostic performance on the more experienced radiologists. Conclusion Using the AI as an aid has proven to improve the overall performance of less experienced radiologists allowing them to reach expert like levels of diagnostic performance in the detection of breast cancer at mammography by using an AI computer system for support without the need for additional reading time.