ㅇ 제목 : 의료 도메인 딥러닝 기술 적용에 관한 연구

ㅇ 일시 : 5/29(월), 16:00

ㅇ 장소 : ETRI 7동 386호

ㅇ 강사 : 이기성 교수(루지에나주립대학)

요약 :

Detection of suspicious regions in mammogram images and the subsequent diagnosis of these regions remains a challenging problem in the medical world. There still exists an alarming rate of misdiagnosis of breast cancer. In this talk, I will present a new framework for automated breast cancer detection and diagnosis, called BC-DROID, which provides automated region of interest detection and diagnosis using convolutional neural networks. BC-DROID achieves a detection accuracy of up to 90% and a classification accuracy of 93.5% (AUC of 92.315%). I will also describe performance evaluation results of various deep learning frameworks over different hardware environments.