Conventional deep learning methods for cerebral infarct segmentation rely on diffusion weighted images (DWI) only. Meanwhile, traditional cerebral diffusion lesion segmentation is typically based on a fixed apparent diffusion coefficient (ADC) threshold. It may be worthwhile to combine DWI and ADC images and use them as input for model training. The objective of this study is to develop a deep-learning segmentation model that takes DWI and ADC as input and produces a segmentation map as output and evaluate its performance.
This abstract and the presentation materials are available to members only; a login is required.