Generative AI in glioma: Ensuring diversity in training image phenotypes to improve diagnostic performance for IDH mutation prediction
- 22 January 2024
- journal article
- research article
- Published by Oxford University Press (OUP) in Neuro-Oncology
- Vol. 26 (6) , 1124-1135
Abstract
Background: This study evaluated whether generative artificial intelligence (AI)-based augmentation (GAA) can provide diverse and realistic imaging phenotypes and improve deep learning-based classification of isocitrate dehydrogenase (IDH) type in glioma compared with neuroradiologists. Methods: For model development, 565 patients (346 IDH-wildtype, 219 IDH-mutant) with paired contrast-enhanced T1 and FLAIR MRI scans were collected from tertiary hospitals and The Cancer Imaging Archive. Performance was tested on internal (119, 78 IDH-wildtype, 41 IDH-mutant [IDH1 and 2]) and external test sets (108, 72 IDH-wildtype, 36 IDH-mutant). GAA was developed using a score-based diffusion model and ResNet50 classifier. The optimal GAA was selected in comparison with the null model. Two neuroradiologists (R1, R2) assessed realism, diversity of imaging phenotypes, and predicted IDH mutation. The performance of a classifier trained with optimal GAA was compared with that of neuroradiologists using the area under the receiver operating characteristics curve (AUC). The effect of tumor size and contrast enhancement on GAA performance was tested. Results: Generated images demonstrated realism (Turing’s test: 47.5–50.5%) and diversity indicating IDH type. Optimal GAA was achieved with augmentation with 110 000 generated slices (AUC: 0.938). The classifier trained with optimal GAA demonstrated significantly higher AUC values than neuroradiologists in both the internal (R1, P = .003; R2, P < .001) and external test sets (R1, P < .01; R2, P < .001). GAA with large-sized tumors or predominant enhancement showed comparable performance to optimal GAA (internal test: AUC 0.956 and 0.922; external test: 0.810 and 0.749). Conclusions: The application of generative AI with realistic and diverse images provided better diagnostic performance than neuroradiologists for predicting IDH type in glioma.Keywords
Funding Information
- Korean government (RS-2023-00208227)
- Ministry of Health & Welfare, Republic of Korea (HI21C1161)
This publication has 26 references indexed in Scilit:
- Oncological Applications of Deep Learning Generative Adversarial NetworksJAMA Oncology, 2022
- Reproducible imaging-based prediction of molecular subtype and risk stratification of gliomas across different experience levels using a structured reporting systemEuropean Radiology, 2021
- Improving classification accuracy using data augmentation on small data setsExpert Systems with Applications, 2020
- Automated brain extraction of multisequence MRI using artificial neural networksHuman Brain Mapping, 2019
- Conventional MR-based Preoperative Nomograms for Prediction of IDH/1p19q Subtype in Low-Grade GliomaAcademic Radiology, 2019
- The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summaryActa Neuropathologica, 2016
- MRI findings and pathological features in early-stage glioblastomaJournal of Neuro-Oncology, 2015
- Visualizing and Understanding Convolutional Networks2014
- Correlation of IDH1/2 mutation with clinicopathologic factors and prognosis in anaplastic gliomas: a report of 203 patients from ChinaJournal of Cancer Research and Clinical Oncology, 2013
- A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation2005