Clinically Applicable Segmentation of Head and Neck Anatomy for Radiotherapy: Deep Learning Algorithm Development and Validation Study

作者：Stanislav Nikolov, Sam Blackwell, Alexei Zverovitch, R. Mendes, Michelle Livne, Jeffrey De Fauw, Yojan Patel, Clemens Meyer, Harry Askham, Bernardino Romera‐Paredes, Christopher Kelly, Alan Karthikesalingam, Carlton Chu, Dawn Carnell, C.S. Boon, D. D’Souza, Syed Moinuddin, Bethany Garie, Yasmin McQuinlan, Sarah Ireland, Kiarna Hampton, Krystle Fuller, Hugh Montgomery, Geraint Rees, Mustafa Suleyman, Trevor Back, Cían Hughes, Joseph R. Ledsam, Olaf Ronneberger · 发表于：Journal of Medical Internet Research · 年份：2021 · DOI：10.2196/26151 · 被引用次数：362 · 研究领域：Advanced Radiotherapy Techniques、Head and Neck Cancer Studies、Radiomics and Machine Learning in Medical Imaging

BACKGROUND: Over half a million individuals are diagnosed with head and neck cancer each year globally. Radiotherapy is an important curative treatment for this disease, but it requires manual time to delineate radiosensitive organs at risk. This planning process can delay treatment while also introducing interoperator variability, resulting in downstream radiation dose differences. Although auto-segmentation algorithms offer a potentially time-saving solution, the challenges in defining, quantifying, and achieving expert performance remain. OBJECTIVE: Adopting a deep learning approach, we aim to demonstrate a 3D U-Net architecture that achieves expert-level performance in delineating 21 distinct head and neck organs at risk commonly segmented in clinical practice. METHODS: The model was trained on a data set of 663 deidentified computed tomography scans acquired in routine clinical practice and with both segmentations taken from clinical practice and segmentations created by experienced radiographers as part of this research, all in accordance with consensus organ at risk definitions. RESULTS: We demonstrated the model's clinical applicability by assessing its performance on a test set of 21 computed tomography scans from clinical practice, each with 21 organs at risk segmented by 2 independent experts. We also introduced surface Dice similarity coefficient, a new metric for the comparison of organ delineation, to quantify the deviation between organ at risk surface contours...