Meeting Banner
Abstract #2028

Suitability of Deep Weakly-supervised Learning to Detect Acute Ischemic Strokes and Hemorrhagic Infarctions Using Diffusion-weighted Imaging

Chen Cao1,2, Zhiyang Liu3, Guohua Liu3, Jinxia Zhu4, Song Jin1, and Shuang Xia5
1Key Laboratory for Cerebral Artery and Neural Degeneration of Tianjin, Radiology Department, Tianjin Huanhu Hospital, Tianjin, China, 2Radiology Department, First Central Clinical College, Tianjin Medical University, Tianjin, China, 3Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, College of Electronic Information and Optical Engineering, Nankai University, Tianjin, China, 4MR Collaboration, Siemens Healthcare Ltd, Beijing, China, 5Radiology Department, Tianjin First Central Hospital, Tianjin, China

We hypothesized that deep weakly-supervised learning could detect acute ischemic stroke (AIS) and hemorrhagic infarction (HI) lesions using diffusion-weighted imaging. Each image slice was assigned an annotation indicating whether or not the slice contained a lesion. The proposed method was trained on an AIS dataset using 417 patients with weakly-labeled lesions and evaluated on a dataset using 319 patients with fully-labeled lesions, which detected lesions with high accuracy. The method was trained on a HI dataset using 240 patients with weakly-labeled lesions and evaluated using 65 patients with fully-labeled lesions. Lesion detection sensitivities were 87.7% (AISs) and 86.2% (HIs).

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here