What question did this study set out to answer?

This research aims to develop an AI pipeline to predict AIS grades based on MRI radiomic features in TCSCI patients.

March 10, 2026Open Access

Severity Prediction of Traumatic Cervical Spinal Cord Injury With an AI Model Based on MRI Radiomics

CWChunshuai WuNantong University CLChaochen LiNanjing Forestry University GXGuanhua XuQingdao University

Puntos clave

This research aims to develop an AI pipeline to predict AIS grades based on MRI radiomic features in TCSCI patients.
Included 189 TCSCI patients who underwent MRI within 48 hours post-injury.
Developed an AI model encompassing image segmentation and radiomic feature extraction from manually defined regions.
MRI images were used to train, validate, and test the model on specific imaging tasks, including AIS grade prediction.
Optimized UCTransnet network achieved promising segmentation results (mDICE: 0.777, mIOU: 0.646).
Em-En ensemble model outperformed others in predicting AIS grades with high sensitivity and specificity.
The model provides preliminary quantitative indicators of injury severity compared to traditional approaches.

Resumen

ABSTRACT Background Traumatic cervical spinal cord injury (TCSCI) often leads to significant patient paralysis. Current clinical diagnosis relies heavily on empirical interpretation of magnetic resonance imaging (MRI) and the American Spinal Injury Association Impairment Scale (AIS) grade, lacking robust quantitative markers to precisely reflect injury severity. This study aimed to build an artificial intelligence (AI) pipeline for AIS grade prediction based on radiomic features extracted from manually defined regions. Methods We included 189 patients with TCSCI who underwent MRI within 48 h post‐injury. MRI images from 130 patients were used for developing an AI model encompassing image segmentation. Radiomic features were extracted from manually delineated volumes of interest (VOIs). T2‐weighted imaging (T2WI) sagittal images were randomly divided into training ( n = 104), validation ( n = 13), and test ( n = 13) sets for segmentation. A total of 183 patients (excluding AIS E) were included in the AIS grade prediction task. Model performance was evaluated using mean dice similarity coefficient (mDICE), mean intersection over union (mIOU), mean specificity, and mean sensitivity. Results An optimized UCTransnet network, leveraging a Transformer architecture for formal training, combined with a U‐Net++ network for pretraining, achieved promising results in segmenting the spinal cord injury site on T2WI sagittal images (mDICE: 0.777 ± 0.021, mIOU: 0.646 ± 0.025, mean specificity: 0.998 ± 0.001, mean sensitivity: 0.895 ± 0.015). Subsequently, an ensemble model (we named Em‐En) constructed using selected radiomic features from the manual VOIs demonstrated superior performance for predicting AIS grades in terms of sensitivity, specificity, accuracy, and clinical decision‐making benefit compared to other tested models. Conclusions This study presents an AI‐assisted pipeline for predicting the severity of TCSCI. The developed resources provide a theoretical foundation for the clinical application of AI‐assisted diagnostic methods, potentially lowering the interpretation barrier for MRI and offering clinicians preliminary quantitative indicators of injury severity. The source code is publicly available.

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo