Evaluating Performance of a Deep Learning Multilabel Segmentation Model to Quantify Acute and Chronic Brain Lesions at MRI after Stroke and Predict Prognosis

Authors: Tianyu Tang, Ying Cui, Chunqiang Lu, Huiming Li, Jiaying Zhou, Xiaoyu Zhang, Yujie Zhou, Ying Zhang, Yi Zhang, Yuhao Xu, Yuefeng Li, Shenghong Ju

Published: 2025-03-26

DOI: 10.1148/ryai.240072

Source: Full article

---

Abstract

The proposed multilabel deep learning segmentation model identified and quantified acute and chronic brain lesions on multisequence MR images in patients with acute ischemic stroke, and model-extracted radiologic features combined with clinical variables predicted short-term prognosis.