Comparison of automated and manual DWI-ASPECTS in acute ischemic stroke: total and region-specific assessment.

XiaoQing ChengXiaoQin SuJiaQian ShiQuanHui LiuChangSheng ZhouZheng DongWei XingHaiTao LuChengWei PanXiuLi LiYiZhou YuLongJiang ZhangGuang Ming Lu

Published in: European radiology (2020)

• The eDWI-ASPECTS based on deep learning perform equally well as senior neuroradiologists' evaluations. • Among the individual ASPECTS regions, the M5, internal capsule, and caudate regions mainly affected the overall consistency. • Uncertain scoring rules and midline shift are the main reasons for regional inconsistency.

Keyphrases

deep learning
machine learning
high throughput
magnetic resonance imaging
computed tomography
single cell