The Segment Anything foundation model achieves favorable brain tumor auto-segmentation accuracy in MRI to support radiotherapy treatment planning

作者：Florian Putz, Sogand Beirami, Manuel Alexander Schmidt, Matthias Stefan May, Johanna Grigo, Thomas Weißmann, Philipp Schubert, Daniel Höfler, Ahmed Mohamed Gomaa, Ben Tkhayat Hassen, Sebastian Lettmaier, Benjamin Frey, Udo S. Gaipl, Luitpold Valentin Distel, Sabine Semrau, Christoph Bert, Rainer Fietkau, Yixing Huang · 发表于：Strahlentherapie und Onkologie · 年份：2024 · DOI：10.1007/s00066-024-02313-8 · 被引用次数：34 · 研究领域：Glioma Diagnosis and Treatment、Advanced Radiotherapy Techniques、Radiomics and Machine Learning in Medical Imaging

BACKGROUND: Promptable foundation auto-segmentation models like Segment Anything (SA, Meta AI, New York, USA) represent a novel class of universal deep learning auto-segmentation models that could be employed for interactive tumor auto-contouring in RT treatment planning. METHODS: Segment Anything was evaluated in an interactive point-to-mask auto-segmentation task for glioma brain tumor auto-contouring in 16,744 transverse slices from 369 MRI datasets (BraTS 2020 dataset). Up to nine interactive point prompts were automatically placed per slice. Tumor boundaries were auto-segmented on contrast-enhanced T1w sequences. Out of the three auto-contours predicted by SA, accuracy was evaluated for the contour with the highest calculated IoU (Intersection over Union, "oracle mask," simulating interactive model use with selection of the best tumor contour) and for the tumor contour with the highest model confidence ("suggested mask"). RESULTS: Mean best IoU (mbIoU) using the best predicted tumor contour (oracle mask) in full MRI slices was 0.762 (IQR 0.713-0.917). The best 2D mask was achieved after a mean of 6.6 interactive point prompts (IQR 5-9). Segmentation accuracy was significantly better for high- compared to low-grade glioma cases (mbIoU 0.789 vs. 0.668). Accuracy was worse using the suggested mask (0.572). Stacking best tumor segmentations from transverse MRI slices, mean 3D Dice score for tumor auto-contouring was 0.872, which was improved to 0.919 by combining axial, sagi...