서울대 / 신승연, 이경무*
Abstract
We propose a framework for localization and classification of masses in breast ultrasound (BUS) images. We have experimentally found that training convolutional neural network based mass detectors with large, weakly annotated datasets presents a non-trivial problem, while overfitting may occur with those trained with small, strongly annotated datasets. To overcome these problems, we use a weakly annotated dataset together with a smaller strongly annotated dataset in a hybrid manner. We propose a systematic weakly and semi-supervised training scenario with appropriate training loss selection. Experimental results show that the proposed method can successfully localize and classify masses with less annotation effort. The results trained with only 10 strongly annotated images along with weakly annotated images were comparable to results trained from 800 strongly annotated images, with the 95% confidence interval of difference -3.00%-5.00%, in terms of the correct localization (CorLoc) measure, which is the ratio of images with intersection over union with ground truth higher than 0.5. With the same number of strongly annotated images, additional weakly annotated images can be incorporated to give a 4.5% point increase in CorLoc, from 80.00% to 84.50% (with 95% confidence intervals 76.00%-83.75% and 81.00%-88.00%). The effects of different algorithmic details and varied amount of data are presented through ablative analysis.
Shin SY, Lee S, Yun ID, Kim SM, Lee KM.
편집위원
본 연구는, 초음파영상에서의 종괴(mass) 위치 파악 및 진단을 동시에 할 수 있는 딥러닝 기술로, weak and strong 두 가지 수준의 레이블 데이터를 활용하는 준지도학습을 기반으로 하여 학습데이터 레이블링에 대한 부담을 덜어줄 수 있고 셀프러닝을 통해 weak 레이블 데이터 정보의 활용도를 더욱 높일 수 있다는 점에서 의미가 큰 것으로 보인다. 학습데이터 레이블링의 복잡도가 높아 대량의 학습데이터 준비가 어려운 타의료영상 분야에서도 유용할 것으로 예상된다.
2019-04-17 16:04:40