期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 40, 期 1, 页码 59-70出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2020.3022034
关键词
Lesions; Proposals; Three-dimensional displays; Computed tomography; Training; Detectors; Biomedical imaging; Lesion harvesting; lesion detection; hard negative mining; pseudo 3D IoU
This research aims to collect missing annotations from lesion datasets at high precision using the Lesion-Harvester system. Through a new algorithm, additional lesions were discovered and tested on DeepLesion. The method provides a more accurate evaluation metric that better corresponds with real 3D IoU and significantly improves the performance of state-of-the-art detectors.
The acquisition of large-scale medical image data, necessary for training machine learning algorithms, is hampered by associated expert-driven annotation costs. Mining hospital archives can address this problem, but labels often incomplete or noisy, e.g., 50% of the lesions in DeepLesion are left unlabeled. Thus, effective label harvesting methods are critical. This is the goal of our work, where we introduce Lesion-Harvester-a powerful system to harvest missing annotations from lesion datasets at high precision. Accepting the need for some degree of expert labor, we use a small fully-labeled image subset to intelligently mine annotations from the remainder. To do this, we chain together a highly sensitive lesion proposal generator (LPG) and a very selective lesion proposal classifier (LPC). Using a new hard negative suppression loss, the resulting harvested and hard-negative proposals are then employed to iteratively finetune our LPG. While our framework is generic, we optimize our performance by proposing a new 3D contextual LPG and by using a global-local multi-view LPC. Experiments on DeepLesion demonstrate that Lesion-Harvester can discover an additional 9,805 lesions at a precision of 90%. We publicly release the harvested lesions, along with a new test set of completely annotated DeepLesion volumes. We also present a pseudo 3D IoU evaluation metric that corresponds much better to the real 3D IoU than current DeepLesion evaluation metrics. To quantify the downstream benefits of Lesion-Harvester we show that augmenting the DeepLesion annotations with our harvested lesions allows state-of-the-art detectors to boost their average precision by 7 to 10%.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据