Progressive auto-segmentation for cone-beam computed tomography-based online adaptive radiotherapy

作者：Hengrui Zhao, Xiao Liang, Boyu Meng, Michael Dohopolski, Choi ByongSu, Bin Cai, Mu‐Han Lin, Ti Bai, Dan Nguyen, Steve Jiang · 发表于：Physics and Imaging in Radiation Oncology · 年份：2024 · DOI：10.1016/j.phro.2024.100610 · 被引用次数：5 · 研究领域：Advanced Radiotherapy Techniques、Medical Imaging Techniques and Applications、Radiation Therapy and Dosimetry

Background and purpose: Accurate and automated segmentation of targets and organs-at-risk (OARs) is crucial for the successful clinical application of online adaptive radiotherapy (ART). Current methods for cone-beam computed tomography (CBCT) auto-segmentation face challenges, resulting in segmentations often failing to reach clinical acceptability. Current approaches for CBCT auto-segmentation overlook the wealth of information available from initial planning and prior adaptive fractions that could enhance segmentation precision. Materials and methods: We introduce a novel framework that incorporates data from a patient's initial plan and previous adaptive fractions, harnessing this additional temporal context to significantly refine the segmentation accuracy for the current fraction's CBCT images. We present LSTM-UNet, an innovative architecture that integrates Long Short-Term Memory (LSTM) units into the skip connections of the traditional U-Net framework to retain information from previous fractions. The models underwent initial pre-training with simulated data followed by fine-tuning on a clinical dataset. Results: Our proposed model's segmentation predictions yield an average Dice similarity coefficient of 79% from 8 Head & Neck organs and targets, compared to 52% from a baseline model without prior knowledge and 78% from a baseline model with prior knowledge but no memory. Conclusions: Our proposed model excels beyond baseline segmentation frameworks by effectively ut...