Clinical Evaluation of Deep Learning and Atlas-Based Auto-Contouring for Head and Neck Radiation Therapy

Various commercial auto-contouring solutions have emerged over past few years to address labor-intensiveness, and inter- and intra-operator variabilities issues of traditional manual anatomy contouring for head and neck (H&N) radiation therapy (RT). The purpose of this study is to compare the clinical performances between RaySearch Laboratories deep learning (DL) and atlas-based auto-contouring tools for organs at risk (OARs) segmentation in the H&N RT with the manual contouring as reference. Forty-five H&N computed tomography datasets were used for the DL and atlas-based auto-contouring tools to contour 16 OARs and time required for the segmentation was measured. Dice similarity coefficient (DSC), Hausdorff distance (HD) and HD 95th-percentile (HD95) were used to evaluate geometric accuracy of OARs contoured by the DL and atlas-based auto-contouring tools. Paired sample t-test was employed to compare the mean DSC, HD, HD95, and contouring time values of the two groups. The DL auto-contouring approach achieved more consistent performance in OARs segmentation than its atlas-based approach, resulting in statistically significant time reduction of the whole segmentation process by 40% (p < 0.001). The DL auto-contouring had statistically significantly higher mean DSC and lower HD and HD95 values (p < 0.001–0.009) for 10 out of 16 OARs. This study proves that the RaySearch Laboratories DL auto-contouring tool has significantly better clinical performances than its atlas-based approach.

[1]  R. Bilimagga,et al.  Autodelineation of organ at risk in head and neck cancer radiotherapy using artificial intelligence , 2022, Journal of cancer research and therapeutics.

[2]  Zhonghua Sun,et al.  Finetuned Super-Resolution Generative Adversarial Network (Artificial Intelligence) Model for Calcium Deblooming in Coronary Computed Tomography Angiography , 2022, Journal of personalized medicine.

[3]  C. Ng.  Artificial Intelligence for Radiation Dose Optimization in Pediatric Radiology: A Systematic Review , 2022, Children.

[4]  Zhonghua Sun,et al.  Artificial Intelligence (Enhanced Super-Resolution Generative Adversarial Network) for Calcium Deblooming in Coronary Computed Tomography Angiography: A Feasibility Study , 2022, Diagnostics.

[5]  Shouping Xu,et al.  Evaluation Exploration of Atlas-Based and Deep Learning-Based Automatic Contouring for Nasopharyngeal Carcinoma , 2022, Frontiers in Oncology.

[6]  Y. Rong,et al.  Evaluating Automatic Segmentation for Swallowing-Related Organs for Head and Neck Cancer , 2022, Technology in cancer research & treatment.

[7]  J. Deasy,et al.  Prospectively-validated deep learning model for segmenting swallowing and chewing structures in CT , 2021, Physics in medicine and biology.

[8]  N. Zamboglou,et al.  Evaluation of an Atlas-Based Auto-Segmentation Tool of Target Volumes and Organs at Risk in Head and Neck Radiation Therapy , 2021, Journal of Oncology Research and Therapy.

[9]  Xixu Zhu,et al.  A deep learning based automatic segmentation approach for anatomical structures in intensity modulation radiotherapy. , 2021, Mathematical biosciences and engineering : MBE.

[10]  V. Grégoire,et al.  Clinical implementation of deep-learning based auto-contouring tools-Experience of three French radiotherapy centers. , 2021, Cancer radiotherapie : journal de la Societe francaise de radiotherapie oncologique.

[11]  Zhonghua Sun,et al.  Use of Three-Dimensional Printing in Modelling an Anatomical Structure with a High Computed Tomography Attenuation Value: A Feasibility Study , 2021, J. Medical Imaging Health Informatics.

[12]  Jiazhou Wang,et al.  A Preliminary Experience of Implementing Deep-Learning Based Auto-Segmentation in Head and Neck Cancer: A Study on Real-World Clinical Cases , 2021, Frontiers in Oncology.

[13]  K. Keum,et al.  Feasibility of Continual Deep Learning-Based Segmentation for Personalized Adaptive Radiation Therapy in Head and Neck Area , 2021, Cancers.

[14]  Sam Blackwell,et al.  Clinically Applicable Segmentation of Head and Neck Anatomy for Radiotherapy: Deep Learning Algorithm Development and Validation Study , 2020, Journal of medical Internet research.

[15]  Anton Schwaighofer,et al.  Evaluation of Deep Learning to Augment Image-Guided Radiotherapy for Head and Neck and Prostate Cancers , 2020, JAMA network open.

[16]  Skylar S. Gay,et al.  Generating High-Quality Lymph Node Clinical Target Volumes for Head and Neck Cancer Radiation Therapy Using a Fully Automated Deep Learning-Based Approach , 2020, International journal of radiation oncology, biology, physics.

[17]  Charlotte L. Brouwer,et al.  External validation of deep learning-based contouring of head and neck organs at risk , 2020, Physics and imaging in radiation oncology.

[18]  J. Siebers,et al.  An Automated Workflow to Improve Efficiency in Radiation Therapy Treatment Planning by Prioritizing Organs at Risk , 2020, Advances in radiation oncology.

[19]  Wen Chen,et al.  Deep learning vs. atlas-based models for fast auto-segmentation of the masticatory muscles on head and neck CT images , 2020, Radiation oncology.

[20]  Eleanor Stride,et al.  Applications and limitations of machine learning in radiation oncology , 2019, The British journal of radiology.

[21]  S. Subramanian,et al.  Auto-segmentation of head and neck organs at risk in radiotherapy and its dependence on anatomic similarity , 2019, Radiation oncology journal.

[22]  Jin Sung Kim,et al.  Clinical Evaluation of Commercial Atlas-Based Auto-Segmentation in the Head and Neck Region , 2019, Front. Oncol..

[23]  R. Mendes,et al.  Rapid advances in auto-segmentation of organs at risk and target volumes in head and neck cancer. , 2019, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[24]  S Nill,et al.  Geometric and dosimetric evaluations of atlas-based segmentation methods of MR images in the head and neck region , 2018, Physics in medicine and biology.

[25]  Stéphane Supiot,et al.  Comparison of Automated Atlas-Based Segmentation Software for Postoperative Prostate Cancer Radiotherapy , 2016, Front. Oncol..

[26]  Primoz Petric,et al.  Uncertainties in target volume delineation in radiotherapy – are they relevant and what can we do about them? , 2016, Radiology and oncology.

[27]  R. Steenbakkers,et al.  CT-based delineation of organs at risk in the head and neck region: DAHANCA, EORTC, GORTEC, HKNPCSG, NCIC CTG, NCRI, NRG Oncology and TROG consensus guidelines. , 2015, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[28]  Wolfgang A Tomé,et al.  Heterogeneity in head and neck IMRT target design and clinical practice. , 2012, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[29]  Ying Li,et al.  Human–Computer Interaction in Radiotherapy Target Volume Delineation: A Prospective, Multi-institutional Comparison of User Input Devices , 2011, Journal of Digital Imaging.

[30]  Paul Aljabar,et al.  Improving automatic delineation for head and neck organs at risk by Deep Learning Contouring. , 2019, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.