Deforming a planning CT to match a daily CBCT provides the tools needed for the calculation of the "dose of the day" without the need to acquire a new CT. The initial clinical application of our method will be weekly offline calculations of the "dose of the day," and use this information to inform adaptive radiotherapy (ART). The work here presented is a first step into a full implementation of a "dose-driven" online ART.

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.

Advances in technical radiotherapy have resulted in significant sparing of organs at risk (OARs), reducing radiation-related toxicities for patients with cancer of the head and neck (HNC). Accurate delineation of target volumes (TVs) and OARs is critical for maximising tumour control and minimising radiation toxicities. When performed manually, variability in TV and OAR delineation has been shown to have significant dosimetric impacts for patients on treatment. Auto-segmentation (AS) techniques have shown promise in reducing both inter-practitioner variability and the time taken in TV and OAR delineation in HNC. Ultimately, this may reduce treatment planning and clinical waiting times for patients. Adaptation of radiation treatment for biological or anatomical changes during therapy will also require rapid re-planning; indeed, the time taken for manual delineation currently prevents adaptive radiotherapy from being implemented optimally. We are therefore standing on the doorstep of a transformation of routine radiotherapy planning via the use of artificial intelligence. In this article, we outline the current state-of-the-art for AS for HNC radiotherapy in order to predict how this will rapidly change with the introduction of artificial intelligence. We specifically focus on delineation accuracy and time saving. We argue that, if such technologies are implemented correctly, AS should result in better standardisation of treatment for patients and significantly reduce the time taken to plan radiotherapy.

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.

IntroductionFollowing growing evidence to support the safety, local control (LC) and potential improvement in overall survival (OS) in patients with oligometastatic non-small cell lung cancer (NSCLC) that have been treated with local ablative therapy such as stereotactic ablative radiotherapy (SABR) and stereotactic radiosurgery (SRS), we initiate the SARON trial to investigate the impact and feasibility of adding SABR/SRS and radical radiotherapy (RRT) following standard chemotherapy on OS.Methods and analysisSARON is a large, randomised controlled, multicentre, phase III trial for patients with oligometastatic EGFR, ALK and ROS1 mutation negative NSCLC (1–3 sites of synchronous metastatic disease, one of which must be extracranial). 340 patients will be recruited over 3 years from approximately 30 UK sites and randomised to receive either standard platinum-doublet chemotherapy only (control arm) or standard chemotherapy followed by RRT/SABR to their primary tumour and then SABR/SRS to all other metastatic sites (investigational arm). The primary endpoint is OS; the study is powered to detect an improvement in median survival from 9.9 months in the control arm to 14.3 months in the investigational arm with 85% power and two-sided 5% significance level. The secondary endpoints are LC, progression-free survival, new distant metastasis-free survival, toxicity and quality of life. An early feasibility review will take place after 50 randomised patients. Patients requiring both conventional thoracic RT to the primary and SABR to a thoracic metastasis will be included in a thoracic SABR safety substudy to assess toxicity and planning issues in this subgroup of patients more thoroughly.Ethics and disseminationAll participants are given a SARON patient information sheet and required to give written informed consent. Results will be submitted for presentation at local and international conferences and expected to be published in a peer-reviewed journal.Trial registration numberNCT02417662.Sponsor referenceUCL/13/0594.