DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning
DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning
复制标题
DOI：
10.1117/1.jmi.5.3.036501
复制
发表时间：
2018-07-01
影响因子：
2.4
通讯作者：
Summers, Ronald M.
中科院分区：
文献类型：
--
作者：
Yan, Ke;Wang, Xiaosong;Summers, Ronald M.
提取、获取和构建大规模带注释的放射图像数据集是一个非常重要但具有挑战性的问题。同时，大量的临床注释被收集并存储在医院的图片存档和通信系统（PACS）中。这些类型的注释，在PACS中也被称为书签，通常由放射科医生在他们的日常工作流程中标记，以突出重要的图像发现，可以作为以后研究的参考。我们建议对这些丰富的回顾性医学数据进行挖掘和收获，以构建大规模的病变图像数据集。我们的流程是可伸缩的，并且需要最少的手工注释工作。我们在我们的研究所挖掘书签来开发DeepLesion，这是一个数据集，包含来自4,427名独特患者的10,594项研究的32,120个CT切片中的32,735个病灶。该数据集中有多种病变类型，如肺结节、肝脏肿瘤、肿大的淋巴结等。它具有在各种医学图像应用中使用的潜力。使用DeepLesion，我们训练了一个通用的病变检测器，可以用一个统一的框架找到所有类型的病变。在这项具有挑战性的任务中，所提出的病变检测器在每张图像有5个假阳性的情况下达到了81.1%的灵敏度。(C) 2018年中国光学仪器工程师学会（SPIE）
Extracting, harvesting, and building large-scale annotated radiological image datasets is a greatly important yet challenging problem. Meanwhile, vast amounts of clinical annotations have been collected and stored in hospitals' picture archiving and communication systems (PACS). These types of annotations, also known as bookmarks in PACS, are usually marked by radiologists during their daily workflow to highlight significant image findings that may serve as reference for later studies. We propose to mine and harvest these abundant retrospective medical data to build a large-scale lesion image dataset. Our process is scalable and requires minimum manual annotation effort. We mine bookmarks in our institute to develop DeepLesion, a dataset with 32,735 lesions in 32,120 CT slices from 10,594 studies of 4,427 unique patients. There are a variety of lesion types in this dataset, such as lung nodules, liver tumors, enlarged lymph nodes, and so on. It has the potential to be used in various medical image applications. Using DeepLesion, we train a universal lesion detector that can find all types of lesions with one unified framework. In this challenging task, the proposed lesion detector achieves a sensitivity of 81.1% with five false positives per image. (C) 2018 Society of Photo-Optical Instrumentation Engineers (SPIE)