TY  - JOUR
AU  - Nikolov, Stanislav
AU  - Blackwell, Sam
AU  - Zverovitch, Alexei
AU  - Mendes, Ruheena
AU  - Livne, Michelle
AU  - De Fauw, Jeffrey
AU  - Patel, Yojan
AU  - Meyer, Clemens
AU  - Askham, Harry
AU  - Romera-Paredes, Bernadino
AU  - Kelly, Christopher
AU  - Karthikesalingam, Alan
AU  - Chu, Carlton
AU  - Carnell, Dawn
AU  - Boon, Cheng
AU  - D'Souza, Derek
AU  - Moinuddin, Syed Ali
AU  - Garie, Bethany
AU  - McQuinlan, Yasmin
AU  - Ireland, Sarah
AU  - Hampton, Kiarna
AU  - Fuller, Krystle
AU  - Montgomery, Hugh
AU  - Rees, Geraint
AU  - Suleyman, Mustafa
AU  - Back, Trevor
AU  - Hughes, Cían Owen
AU  - Ledsam, Joseph R
AU  - Ronneberger, Olaf
PY  - 2021
DA  - 2021/7/12
TI  - Clinically Applicable Segmentation of Head and Neck Anatomy for Radiotherapy: Deep Learning Algorithm Development and Validation Study
JO  - J Med Internet Res
SP  - e26151
VL  - 23
IS  - 7
KW  - radiotherapy
KW  - segmentation
KW  - contouring
KW  - machine learning
KW  - artificial intelligence
KW  - UNet
KW  - convolutional neural networks
KW  - surface DSC
AB  - 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 rather than volumes, better reflecting the clinical task of correcting errors in automated organ segmentations. The model’s generalizability was then demonstrated on 2 distinct open-source data sets, reflecting different centers and countries to model training. Conclusions: Deep learning is an effective and clinically applicable technique for the segmentation of the head and neck anatomy for radiotherapy. With appropriate validation studies and regulatory approvals, this system could improve the efficiency, consistency, and safety of radiotherapy pathways. 
SN  - 1438-8871
UR  - https://www.jmir.org/2021/7/e26151
UR  - https://doi.org/10.2196/26151
UR  - http://www.ncbi.nlm.nih.gov/pubmed/34255661
DO  - 10.2196/26151
ID  - info:doi/10.2196/26151
ER  -