Stepwise Transfer Learning for Expert-Level Pediatric Brain Tumor MRI Segmentation in a Limited Data Scenario

Aidan Boyd, Zezhong Ye, Sanjay Prabhu, Michael C Tjong, Yining Zha, Anna Zapaischykova, Sridhar Vajapeyam, Paul J Catalano, Hasaan Hayat, Rishi Chopra, Kevin X Liu, Ali Nabavizadeh, Adam Resnick, Sabine Mueller, Daphne Haas-Kogan, Hugo J W L Aerts, Tina Poussaint, Benjamin H Kann*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

39 Downloads (Pure)

Abstract

Purpose: To develop, externally test, and evaluate clinical acceptability of a deep learning pediatric brain tumor segmentation model using stepwise transfer learning. Materials and Methods: In this retrospective study, the authors leveraged two T2-weighted MRI datasets (May 2001 through December 2015) from a national brain tumor consortium (n = 184; median age, 7 years [range, 1–23 years]; 94 male patients) and a pediatric cancer center (n = 100; median age, 8 years [range, 1–19 years]; 47 male patients) to develop and evaluate deep learning neural networks for pediatric low-grade glioma segmentation using a stepwise transfer learning approach to maximize performance in a limited data scenario. The best model was externally tested on an independent test set and subjected to randomized blinded evaluation by three clinicians, wherein they assessed clinical acceptability of expert-and artificial intelligence (AI)–generated segmentations via 10-point Likert scales and Turing tests. Results: The best AI model used in-domain stepwise transfer learning (median Dice score coefficient, 0.88 [IQR, 0.72–0.91] vs 0.812 [IQR, 0.56–0.89] for baseline model; P = .049). With external testing, the AI model yielded excellent accuracy using reference standards from three clinical experts (median Dice similarity coefficients: expert 1, 0.83 [IQR, 0.75–0.90]; expert 2, 0.81 [IQR, 0.70–0.89]; expert 3, 0.81 [IQR, 0.68–0.88]; mean accuracy, 0.82). For clinical benchmarking (n = 100 scans), experts rated AI-based segmentations higher on average compared with other experts (median Likert score, 9 [IQR, 7–9] vs 7 [IQR 7–9]) and rated more AI segmentations as clinically acceptable (80.2% vs 65.4%). Experts correctly predicted the origin of AI segmentations in an average of 26.0% of cases. Conclusion: Stepwise transfer learning enabled expert-level automated pediatric brain tumor autosegmentation and volumetric measurement with a high level of clinical acceptability.

Original languageEnglish
Article numbere230254
JournalRadiology: Artificial Intelligence
Volume6
Issue number4
Early online date10 Jul 2024
DOIs
Publication statusPublished - Jul 2024

Fingerprint

Dive into the research topics of 'Stepwise Transfer Learning for Expert-Level Pediatric Brain Tumor MRI Segmentation in a Limited Data Scenario'. Together they form a unique fingerprint.

Cite this