Generative AI in glioma: ensuring diversity in training image phenotypes to improve diagnostic performance for IDH mutation prediction

Hye Hyeon Moon; Jiheon Jeong; Ji Eun Park; Namkug Kim; Changyong Choi; Young-Hoon Kim; Sang Woo Song; Chang-Ki Hong; Jeong Hoon Kim; Ho Sung Kim

doi:10.1093/neuonc/noae012

Generative AI in glioma: ensuring diversity in training image phenotypes to improve diagnostic performance for IDH mutation prediction

Neuro Oncol. 2024 Jan 22:noae012. doi: 10.1093/neuonc/noae012. Online ahead of print.

Authors

Hye Hyeon Moon¹, Jiheon Jeong^{2

3}, Ji Eun Park¹, Namkug Kim^{1

2}, Changyong Choi^{2

3}, Young-Hoon Kim⁴, Sang Woo Song⁴, Chang-Ki Hong⁴, Jeong Hoon Kim⁴, Ho Sung Kim¹

Affiliations

¹ Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea.
² Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea.
³ Department of Biomedical Engineering, Asan Medical Institute of Convergence Science of Technology, Asan Medical Center, College of Medicine, University of Ulsan, Seoul, Korea.
⁴ Department of Neurosurgery, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea.

PMID: 38253989
DOI: 10.1093/neuonc/noae012

Abstract

Background: This study evaluated whether generative artificial intelligence-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 hospital 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 score-based diffusion model and ResNet50 classifier. The optimal GAA was selected in comparison with 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 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: Application of generative AI with realistic and diverse images provided better diagnostic performance than neuroradiologists for predicting IDH type in glioma.

Keywords: Artificial Intelligence; deep learning; glioma; isocitrate dehydrogenase; magnetic resonance imaging.