Abnormal Brachial Plexus Differentiation from Routine Magnetic Resonance Imaging: An AI-based Approach

• Published in: Neuroscience Vol. 546; pp. 178 - 187
• Main Authors: Cao, Weiguo, Howe, Benjamin M., Wright, Darryl E., Ramanathan, Sumana, Rhodes, Nicholas G., Korfiatis, Panagiotis, Amrami, Kimberly K., Spinner, Robert J., Kline, Timothy L.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 14.05.2024
• Subjects: artificial intelligence; brachial plexus; magnetic resonance imaging; radiomics; texture features; magnetic resonance imaging; AI; FN; FPR; FP; EMR; ROI; artificial intelligence; BP; MMN; radiomics; TPR; brachial plexus; texture features; TN; TP
• ISSN: 0306-4522; 1873-7544
• DOI: 10.1016/j.neuroscience.2024.03.017

[Display omitted] •189 patients relevant to BP were collected in our study,•the world’s first non-traumatic plexopathy dataset was constructed,•107 quantitative features of BP were extracted,•54 machine learning models were trained and evaluated,•the identification performance achieves the accuracy of 0.912 ± 0.016. Automatic abnormality identification of brachial plexus (BP) from normal magnetic resonance imaging to localize and identify a neurologic injury in clinical practice (MRI) is still a novel topic in brachial plexopathy. This study developed and evaluated an approach to differentiate abnormal BP with artificial intelligence (AI) over three commonly used MRI sequences, i.e. T1, FLUID sensitive and post-gadolinium sequences. A BP dataset was collected by radiological experts and a semi-supervised artificial intelligence method was used to segment the BP (based on nnU-net). Hereafter, a radiomics method was utilized to extract 107 shape and texture features from these ROIs. From various machine learning methods, we selected six widely recognized classifiers for training our Brachial plexus (BP) models and assessing their efficacy. To optimize these models, we introduced a dynamic feature selection approach aimed at discarding redundant and less informative features. Our experimental findings demonstrated that, in the context of identifying abnormal BP cases, shape features displayed heightened sensitivity compared to texture features. Notably, both the Logistic classifier and Bagging classifier outperformed other methods in our study. These evaluations illuminated the exceptional performance of our model trained on FLUID-sensitive sequences, which notably exceeded the results of both T1 and post-gadolinium sequences. Crucially, our analysis highlighted that both its classification accuracies and AUC score (area under the curve of receiver operating characteristics) over FLUID-sensitive sequence exceeded 90%. This outcome served as a robust experimental validation, affirming the substantial potential and strong feasibility of integrating AI into clinical practice.