Improved Segmentation and Detection Sensitivity of Diffusion-weighted Stroke Lesions with Synthetically Enhanced Deep Learning

To compare the segmentation and detection performance of a deep learning model trained on a database of human-labeled clinical stroke lesions on diffusion-weighted (DW) images to a model trained on the same database enhanced with synthetic stroke lesions. In this institutional review board–approved study, a stroke database of 962 cases (mean patient age standard deviation, 65 years 17; 255 male patients; 449 scans with DW positive stroke lesions) and a normal database of 2027 patients (mean age, 38 years 24; 1088 female patients) were used. Brain volumes with synthetic stroke lesions on DW images were produced by warping the relative signal increase of real strokes to normal brain volumes. A generic three-dimensional (3D) U-Net was trained on four different databases to generate four different models: (a) 375 neuroradiologist-labeled clinical DW positive stroke cases (CDB); (b) 2000 synthetic cases (S2DB); (c) CDB plus 2000 synthetic cases (CS2DB); and (d) CDB plus 40 000 synthetic cases (CS40DB). The models were tested on 20% (n 192) of the cases of the stroke database, which were excluded from the training set.