Unsupervised Deep Learning for Blood-Brain Barrier Leakage Detection in Diffuse Glioma Using Dynamic Contrast-enhanced MRI.

Journal: Radiology. Artificial intelligence
Published Date:

Abstract

Purpose To develop an unsupervised deep learning framework for generalizable blood-brain barrier leakage detection using dynamic contrast-enhanced MRI, without requiring pharmacokinetic models and arterial input function estimation. Materials and Methods This retrospective study included data from patients who underwent dynamic contrast-enhanced MRI between April 2010 and December 2020. An autoencoder-based anomaly detection approach identified one-dimensional voxel-wise time-series abnormal signals through reconstruction residuals, separating them into residual leakage signals (RLSs) and residual vascular signals. The RLS maps were evaluated and compared with the volume transfer constant () using the structural similarity index and correlation coefficient. Generalizability was tested on subsampled data, and isocitrate dehydrogenase () status classification performance was assessed using area under the receiver operating characteristic curve (AUC). Results A total of 274 patients (mean age, 54.4 years ± 14.6 [SD]; 164 male) were included in the study. RLS showed high structural similarity (structural similarity index, 0.91 ± 0.02) and correlation ( = 0.56; < .001) with . On subsampled data, RLS maps showed better correlation with RLS values from the original data (0.89 vs 0.72; < .001), higher peak signal-to-noise ratio (33.09 dB vs 28.94 dB; < .001), and higher structural similarity index (0.92 vs 0.87; < .001) compared with maps. RLS maps also outperformed maps in predicting mutation status (AUC, 0.87 [95% CI: 0.83, 0.91] vs 0.81 [95% CI: 0.76, 0.85]; = .02). Conclusion The unsupervised framework effectively detected blood-brain barrier leakage without pharmacokinetic models and arterial input function. Dynamic Contrast-enhanced MRI, Unsupervised Learning, Feature Detection, Blood-Brain Barrier Leakage Detection © RSNA, 2025 See also commentary by Júdice de Mattos Farina and Kuriki in this issue.

Authors

  • Joon Jang
    Department of Biomedical Sciences, Seoul National University, Seoul, South Korea.
  • Kyu Sung Choi
    Graduate School of Medical Science and Engineering, Korea Advanced Institute for Science and Technology (KAIST), Daejeon, Republic of Korea.
  • Junhyeok Lee
    Department of Software Convergence, Kyung Hee University, Yongin 17104, Korea.
  • Hyochul Lee
    Department of Biomedical Sciences, Seoul National University, Seoul, Korea.
  • Inpyeong Hwang
    Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea.
  • Jung Hyun Park
    2Department of Food Science and Technology, Yeungnam University, Gyeongsan, Gyeongsanbuk-do 38541 Republic of Korea.
  • Jin Wook Chung
    Department of Radiology, Seoul National University Hospital, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea.
  • Seung Hong Choi
    From the Graduate School of Medical Science and Engineering (K.H.K., S.H.P.) and Department of Bio and Brain Engineering (S.H.P.), Korea Advanced Institute of Science and Technology, Room 1002, CMS (E16) Building, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea; Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea (S.H.C.); Department of Radiology, Seoul National University College of Medicine, and Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea (S.H.C.); and Center for Nanoparticle Research, Institute for Basic Science, Seoul, Republic of Korea (S.H.C.).
  • Hyeonjin Kim
    Department of Biomedical Sciences, Seoul National University, Seoul, Korea.