Journal Article

A deep learning model for differentiating paediatric intracranial germ cell tumour subtypes and predicting survival with MRI: a multicentre prospective study

Zhuo, Zhizheng, Liu, Xing, Li, Bo, Haller, Sven, Weng, Jinyuan, Wang, Zheng, Li, Yanong, Bai, Harrison X., Zhu, Mingwang, Li, Jane, Qiu, Xiaoguang, Liu, Yaou

2024

Overview

Background The pretherapeutic differentiation of subtypes of primary intracranial germ cell tumours (iGCTs), including germinomas (GEs) and nongerminomatous germ cell tumours (NGGCTs), is essential for clinical practice because of distinct treatment strategies and prognostic profiles of these diseases. This study aimed to develop a deep learning model, iGNet, to assist in the differentiation and prognostication of iGCT subtypes by employing pretherapeutic MR T2-weighted imaging. Methods The iGNet model, which is based on the nnUNet architecture, was developed using a retrospective dataset of 280 pathologically confirmed iGCT patients. The training dataset included 83 GEs and 117 NGGCTs, while the retrospective internal test dataset included 31 GEs and 49 NGGCTs. The model’s diagnostic performance was then assessed with the area under the receiver operating characteristic curve (AUC) in a prospective internal dataset ( n  = 22) and two external datasets ( n  = 22 and 20). Next, we compared the diagnostic performance of six neuroradiologists with or without the assistance of iGNet. Finally, the predictive ability of the output of iGNet for progression-free and overall survival was assessed and compared to that of the pathological diagnosis. Results iGNet achieved high diagnostic performance, with AUCs between 0.869 and 0.950 across the four test datasets. With the assistance of iGNet, the six neuroradiologists’ diagnostic AUCs (averages of the four test datasets) increased by 9.22% to 17.90%. There was no significant difference between the output of iGNet and the results of pathological diagnosis in predicting progression-free and overall survival ( P  = .889). Conclusions By leveraging pretherapeutic MR imaging data, iGNet accurately differentiates iGCT subtypes, facilitating prognostic evaluation and increasing the potential for tailored treatment. Graphical Abstract

• Publisher: BioMed Central,BioMed Central Ltd,Springer Nature B.V,BMC
• Subject: Adolescent / Artificial intelligence / Biomarkers / Biomedicine / Biopsy / Brain cancer / Brain Neoplasms - diagnostic imaging / Brain Neoplasms - mortality / Brain Neoplasms - pathology / Brain tumors / Cell differentiation / Chemotherapy / Child / Child, Preschool / Clinical decision making / Datasets / Deep Learning / Deep learning (DL) / Depth profiling / Diagnosis / Diagnostic model / Diagnostic systems / Female / Health services / Humans / Identification and classification / Magnetic resonance imaging / Magnetic resonance imaging (MRI) / Magnetic Resonance Imaging - methods / Male / Medical diagnosis / Medical imaging / Medical prognosis / Medical research / Medicine / Medicine & Public Health / Medicine, Experimental / Neoplasms, Germ Cell and Embryonal - diagnostic imaging / Neoplasms, Germ Cell and Embryonal - mortality / Neoplasms, Germ Cell and Embryonal - pathology / Pathology / Patient outcomes / Patients / Pediatric research / Pediatrics / Performance evaluation / Performance prediction / Physiological aspects / Primary intracranial germ cell tumours (iGCTs) / Prognosis / Prognostic evaluation / Prospective Studies / Radiation therapy / Retrospective Studies / Review boards / Survival / Survival Analysis / Tumors