Developers and users of artificial-intelligence-based tools for automatic contouring and treatment planning in radiotherapy are expected to assess clinical acceptability of these tools. However, what is ‘clinical acceptability’? Quantitative and qualitative approaches have been used to assess this ill-defined concept, all of which have advantages and disadvantages or limitations. The approach chosen may depend on the goal of the study as well as on available resources. In this paper, we discuss various aspects of ‘clinical acceptability’ and how they can move us toward a standard for defining clinical acceptability of new autocontouring and planning tools.

Application of different deformable dose accumulation (DDA) solutions makes institutional comparisons after online-adaptive magnetic resonance-guided radiotherapy (OA-MRgRT) challenging. The aim of this multi-institutional study was to analyze accuracy and agreement of DDA-implementations in OA-MRgRT. One gold standard (GS) case deformed with a biomechanical-model and five clinical cases consisting of prostate (2x), cervix, liver, and lymph node cancer, treated with OA-MRgRT, were analyzed. Six centers conducted DDA using institutional implementations. Deformable image registration (DIR) and DDA results were compared using the contour metrics Dice Similarity Coefficient (DSC), surface-DSC, Hausdorff-distance (HD95%), and accumulated dose-volume histograms (DVHs) analyzed via intraclass correlation coefficient (ICC) and clinical dosimetric criteria (CDC). For the GS, median DDA errors ranged from 0.0 to 2.8 Gy across contours and implementations. DIR of clinical cases resulted in DSC > 0.8 for up to 81.3% of contours and a variability of surface-DSC values depending on the implementation. Maximum HD95%=73.3 mm was found for duodenum in the liver case. Although DVH ICC > 0.90 was found after DDA for all but two contours, relevant absolute CDC differences were observed in clinical cases: Prostate I/II showed maximum differences in bladder V28Gy (10.2/7.6%), while for cervix, liver, and lymph node the highest differences were found for rectum D2cm³ (2.8 Gy), duodenum Dmax (7.1 Gy), and rectum D0.5cm³ (4.6 Gy). Overall, high agreement was found between the different DIR and DDA implementations. Case- and algorithm-dependent differences were observed, leading to potentially clinically relevant results. Larger studies are needed to define future DDA-guidelines.

Purpose: MR-guided radiotherapy (MRgRT) has the advantage of utilizing high soft tissue contrast imaging to track daily changes in target and critical organs throughout the entire radiation treatment course. Head and neck (HN) stereotactic body radiation therapy (SBRT) has been increasingly used to treat localized lesions within a shorter timeframe. The purpose of this study is to examine the dosimetric difference between the step-and-shot intensity modulated radiation therapy (IMRT) plans on Elekta Unity and our clinical volumetric modulated arc therapy (VMAT) plans on Varian TrueBeam for HN SBRT. Method: Fourteen patients treated on TrueBeam sTx with VMAT treatment plans were re-planned in the Monaco treatment planning system for Elekta Unity MR-Linac (MRL). The plan qualities, including target coverage, conformity, homogeneity, nearby critical organ doses, gradient index and low dose bath volume, were compared between VMAT and Monaco IMRT plans. Additionally, we evaluated the Unity adaptive plans of adapt-toposition (ATP) and adapt-to-shape (ATS) workflows using simulated setup errors for five patients and assessed the outcomes of our treated patients. Results: Monaco IMRT plans achieved comparable results to VMAT plans in terms of target coverage, uniformity and homogeneity, with slightly higher target maximum and mean doses. The critical organ doses in Monaco IMRT plans all met clinical goals; however, the mean doses and low dose bath volumes were higher than in VMAT plans. The adaptive plans demonstrated that the ATP workflow may result in degraded target coverage and OAR doses for HN SBRT, while the ATS workflow can maintain the plan quality. Conclusion: The use of Monaco treatment planning and online adaptation can achieve dosimetric results comparable to VMAT plans, with the additional benefits of real-time tracking of target volume and nearby critical structures. This offers the potential to treat aggressive and variable tumors in HN SBRT and improve local control and treatment toxicity.

Background: The treatment planning process from segmentation to producing a deliverable plan is time‐consuming and labor‐intensive. Existing solutions automate the segmentation and planning processes individually. The feasibility of combining auto‐segmentation and auto‐planning for volumetric modulated arc therapy (VMAT) for rectal cancers in an end‐to‐end process is not clear.Purpose: To create and clinically evaluate a complete end‐to‐end process for auto‐segmentation and auto‐planning of VMAT for rectal cancer requiring only the gross tumor volume contour and a CT scan as inputs.Methods: Patient scans and data were retrospectively selected from our institutional records for patients treated for malignant neoplasm of the rectum. We trained, validated, and tested deep learning auto‐segmentation models using nnU‐Net architecture for clinical target volume (CTV), bowel bag, large bowel, small bowel, total bowel, femurs, bladder, bone marrow, and female and male genitalia. For the CTV, we identified 174 patients with clinically drawn CTVs. We used data for 18 patients for all structures other than the CTV. The structures were contoured under the guidance of and reviewed by a gastrointestinal (GI) radiation oncologist. The predicted results for CTV in 35 patients and organs at risk (OAR) in six patients were scored by the GI radiation oncologist using a five‐point Likert scale. For auto‐planning, a RapidPlan knowledge‐based planning solution was modeled for VMAT delivery with a prescription of 25 Gy in five fractions. The model was trained and tested on 20 and 34 patients, respectively. The resulting plans were scored by two GI radiation oncologists using a five‐point Likert scale. Finally, the end‐to‐end pipeline was evaluated on 16 patients, and the resulting plans were scored by two GI radiation oncologists.Results: In 31 of 35 patients, CTV contours were clinically acceptable without necessary modifications. The CTV achieved a Dice similarity coefficient of 0.85 (±0.05) and 95% Hausdorff distance of 15.25 (±5.59) mm. All OAR contours were clinically acceptable without edits, except for large and small bowel which were challenging to differentiate. However, contours for total, large, and small bowel were clinically acceptable. The two physicians accepted 100% and 91% of the auto‐plans. For the end‐to‐end pipeline, the two physicians accepted 88% and 62% of the auto‐plans.Conclusions: This study demonstrated that the VMAT treatment planning technique for rectal cancer can be automated to generate clinically acceptable and safe plans with minimal human interventions.

Advanced imaging is the cornerstone of modern radiation oncology, contributing to each phase of patient care, from diagnosis and treatment planning to delivery and follow-up. It has evolved from providing purely geometric guidance to enabling biological and dynamic precision, capturing detailed spatial and functional information about tumors and surrounding tissues. This progress has also generated vast amounts of complex data that remain largely underexplored. AI-based methods have shown promises to unlock the potential of these data, ensuring quality and standardization while extracting previously inaccessible insights. AI-driven tools can enhance accuracy, efficiency, and personalization of radiation oncology through precision diagnosis, automated segmentation, adaptive treatment planning, real-time image guidance, and predictive response assessment. In this review, we conducted a systematic bibliometric analysis of relevant literature published in the last decade and explored current advancements in AI and radiomics applications across radiation oncology. We also addressed ongoing challenges, such as data heterogeneity, model interpretability, and clinical implementation, and discussed future directions for integrating AI-powered imaging solutions into routine practice to advance precision cancer care.