Identifying IDH-mutant and 1p/19q noncodeleted astrocytomas from nonenhancing gliomas: Manual recognition followed by artificial intelligence recognition

• Published in: Neuro-oncology advances Vol. 6; no. 1; p. vdae013
• Main Authors: He, Lei, Zhang, Hong, Li, Tianshi, Yang, Jianing, Zhou, Yanpeng, Wang, Jiaxiang, Saidaer, Tuerhong, Bai, Xiaoyan, Liu, Xing, Wang, Yinyan, Wang, Lei
• Format: Journal Article
• Language: English
• Published: US Oxford University Press 01.01.2024
• Subjects: Clinical Investigations; astrocytoma; machine learning; MRI; nonenhancing glioma; T2-FLAIR mismatch
• ISSN: 2632-2498; 2632-2498
• DOI: 10.1093/noajnl/vdae013

Abstract Background The T2-FLAIR mismatch sign (T2FM) has nearly 100% specificity for predicting IDH-mutant and 1p/19q noncodeleted astrocytomas (astrocytomas). However, only 18.2%–56.0% of astrocytomas demonstrate a positive T2FM. Methods must be considered for distinguishing astrocytomas from negative T2FM gliomas. In this study, positive T2FM gliomas were manually distinguished from nonenhancing gliomas, and then a support vector machine (SVM) classification model was used to distinguish astrocytomas from negative T2FM gliomas. Methods Nonenhancing gliomas (regardless of pathological type or grade) diagnosed between January 2022 and October 2022 (N = 300) and November 2022 and March 2023 (N = 196) will comprise the training and validation sets, respectively. Our method for distinguishing astrocytomas from nonenhancing gliomas was examined and validated using the training set and validation set. Results The specificity of T2FM for predicting astrocytomas was 100% in both the training and validation sets, while the sensitivity was 42.75% and 67.22%, respectively. Using a classification model of SVM based on radiomics features, among negative T2FM gliomas, the accuracy was above 85% when the prediction score was greater than 0.70 in identifying astrocytomas and above 95% when the prediction score was less than 0.30 in identifying nonastrocytomas. Conclusions Manual screening of positive T2FM gliomas, followed by the SVM classification model to differentiate astrocytomas from negative T2FM gliomas, may be a more effective method for identifying astrocytomas in nonenhancing gliomas.