Semisupervised Learning for Generalizable Intracranial Hemorrhage Detection and Segmentation.
Researchers
Journal
Modalities
Models
Abstract
“Just Accepted” papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop and evaluate a semisupervised learning model for intracranial hemorrhage detection and segmentation on an out-of-distribution head CT evaluation set. Materials and Methods This retrospective study used semisupervised learning to bootstrap performance. An initial “teacher” deep learning model was trained on 457 pixel-labeled head CT scans collected from one U.S. institution from 2010-2017 and used to generate pseudo-labels on a separate unlabeled corpus of 25,000 examinations from the RSNA and ASNR. A second “student” model was trained on this combined pixel-and pseudo-labeled dataset. Hyperparameter tuning was performed on a validation set of 93 scans. Testing for both classification (n = 481 examinations) and segmentation (n = 23 examinations, or 529 images) was performed on CQ500, a dataset of 481 scans performed in India, to evaluate out-of-distribution generalizability. The semisupervised model was compared with a baseline model trained on only labeled data using area under the receiver operating characteristic curve (AUC), Dice similarity coefficient (DSC), and average precision (AP) metrics. Results The semisupervised model achieved statistically significantly higher examination AUC on CQ500 compared with the baseline (0.939 [0.938, 0.940] versus 0.907 [0.906, 0.908]) (P = .009). It also achieved a higher DSC (0.829 [0.825, 0.833] versus 0.809 [0.803, 0.812]) (P = .012) and Pixel AP (0.848 [0.843, 0.853]) versus 0.828 [0.817, 0.828]) compared with the baseline. Conclusion The addition of unlabeled data in a semisupervised learning framework demonstrates stronger generalizability potential for intracranial hemorrhage detection and segmentation compared with a supervised baseline. ©RSNA, 2024.