Deep learning radiomics nomograms predict Isocitrate dehydrogenase (IDH) genotypes in brain glioma: A multicenter study

Darui Li; Wanjun Hu; Laiyang Ma; Wenxia Yang; Yang Liu; Jie Zou; Xin Ge; Yuping Han; Tiejun Gan; Dan Cheng; Kai Ai; Guangyao Liu; Jing Zhang

doi:10.1016/j.mri.2024.110314

Deep learning radiomics nomograms predict Isocitrate dehydrogenase (IDH) genotypes in brain glioma: A multicenter study

Magn Reson Imaging. 2024 Dec 19:110314. doi: 10.1016/j.mri.2024.110314. Online ahead of print.

Authors

Darui Li¹, Wanjun Hu¹, Laiyang Ma¹, Wenxia Yang¹, Yang Liu¹, Jie Zou¹, Xin Ge¹, Yuping Han¹, Tiejun Gan¹, Dan Cheng², Kai Ai³, Guangyao Liu¹, Jing Zhang⁴

Affiliations

¹ Department of Nuclear Magnetic Resonance, The Second Hospital & Clinical Medical School, Lanzhou University, Lanzhou 730030, China; Gansu Province Clinical Research Center for Functional and Molecular Imaging, Lanzhou 730030, China.
² Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
³ Philips Healthcare, Xi'an, China.
⁴ Department of Nuclear Magnetic Resonance, The Second Hospital & Clinical Medical School, Lanzhou University, Lanzhou 730030, China; Gansu Province Clinical Research Center for Functional and Molecular Imaging, Lanzhou 730030, China. Electronic address: ery_zhangjing@lzu.edu.cn.

PMID: 39708927
DOI: 10.1016/j.mri.2024.110314

Abstract

Purpose: To explore the feasibility of Deep learning radiomics nomograms (DLRN) in predicting IDH genotype.

Methods: A total of 402 glioma patients from two independent centers were retrospectively included, and the data from center I was randomly divided into a training cohort (n = 239) and an internal validation cohort (n = 103) on a 7:3 basis. Center II served as an independent external validation cohort (n = 60). We developed a DLRN for IDH classification of gliomas based on T2 images. This hybrid model integrates deep learning features, radiomics features, and clinical features most relevant to IDH genotypes and finally classifies them using multivariate logistic regression analysis. We used the area under the curve (AUC) of the receiver operating characteristic (ROC) to evaluate the performance of the model and applied the DLRN score to the survival analysis of some of the follow-up glioma patients.

Results: The proposed model had an area under the curve (AUC) of 0.98 in an externally validated cohort, and DLRN scores were significantly associated with the overall survival of glioma patients.

Conclusions: Deep learning radiomics nomograms performed well in non-invasively predicting IDH mutation status in gliomas, assisting stratified management and targeted therapy for glioma patients.

Keywords: Deep learning; Glioma; Isocitrate dehydrogenase; Nomograms; Radiomics.