To establish an artificial intelligence (AI)-empowered multistep integrated (MSI) radiation therapy (RT) workflow for patients with nasopharyngeal carcinoma (NPC) and evaluate its feasibility and clinical performance. Patients with NPC scheduled for MSI RT workflow were prospectively enrolled. This workflow integrates RT procedures from computed tomography (CT) scan to beam delivery, all performed with the patient on the treatment couch. Workflow performance, tumor response, patient-reported acute toxicities, and quality of life were evaluated. From March 2022 to October 2023, 120 newly diagnosed, nonmetastatic patients with NPC were enrolled. Of these, 117 completed the workflow with a median duration of 23.2 minutes (range, 16.3-45.8). Median translation errors were 0.2 mm (from CT scan to planning approval) and 0.1 mm (during beam delivery). AI-generated contours required minimal revision for the high-risk clinical target volume and organs at risk, minor revision for the involved cervical lymph nodes and low-risk clinical target volume (median Dice similarity coefficients (DSC), 0.98 and 0.94), and more revision for the gross tumor at the primary site and the involved retropharyngeal lymph nodes (median DSC, 0.84). Of 117 AI-generated plans, 108 (92.3%) passed after the first optimization, with ≥97.8% of target volumes receiving ≥100% of the prescribed dose. Dosimetric constraints were met for most organs at risk, except the thyroid and submandibular glands. One hundred and fifteen patients achieved a complete response at week 12 post-RT, while 14 patients reported any acute toxicity as "very severe" from the start of RT to week 12 post-RT. AI-empowered MSI RT workflow for patients with NPC is clinically feasible in a single institutional setting compared with standard, human-based RT workflow.

To evaluate the difference of absorbed doses calculated to medium and to water by a Monte Carlo (MC) algorithm based treatment planning system (TPS), and to assess the potential clinical impact to dose prescription. Thirty patients, 10 nasopharyngeal cancer (NPC), 10 lung cancer and 10 bone metastases cases, were selected for this study. For each case, the treatment plan was generated using a commercial MC based TPS and dose was calculated to medium (D_m). The plan was recalculated for dose to water (D_w) using the same Monitor Units (MU) and control points. The differences between D_m and D_w were qualitatively evaluated by dose-volume parameters and by the plan subtraction method. All plans were measured using the MapCheck2, and gamma passing rates were calculated. For NPC and Lung cases, the mean differences between D_w and D_m for the targets were less than 2% and the maximum difference was 3.9%. The maximum difference of D_2% for the organs at risk (OARs) was 6.7%. The maximum differences between D_w and D_m were as high as 10% in certain high density regions. For bone metastases cases, the mean differences between D_w and D_m for the targets were more than 2.2% and the maximum difference was 7.1%. The differences between D_w and D_m for the OARs were basically negligible. At 3%&3 mm criterion, the gamma passing rate of D_w plan and D_m plan were close (> 94%). The differences between D_w and D_m has little clinical impact for most clinical cases. In bony structures the differences may become clinically significant if the target/OAR is receiving doses close to its tolerance limit which can potentially influence the selection or rejection of a particular plan.

The aim of this study was to evaluate the inter- and intrafractional organs motions and dosimetric advantages of MRI guided online adaptive radiotherapy for cervical cancer. A total of 150 fractions treated on the 1.5 T Unity MR-Linac were included in this study. Each fraction, pre-treatment, position validation and post-treatment MRI scans were obtained. Structures including CTV, rectum and bladder were delineated by the same radiation oncologists on each MRI. The inter- and intrafractional changes of contours were assessed by Hausdorff distance (HD), dice similarity coefficient (DSC), relative volume difference (ΔV) and the relative positions of the geometric center. The non-ART plans and online adaptive plans were obtained by recalculating or re-optimizing from reference plans on daily MRI, respectively. CTV coverage and OARs constraints were evaluated between ART and non-ART plans. For each fraction, the interfractional changes of HD, ΔV and DSC for CTV, bladder and rectum were significant. Our study also examined the relationship of bladder and rectum filling on CTV position. For 150 non-ART plans, CTV coverage constraints (D_98% ≥ 45 Gy) were not met by 45 %, while 15 % were not covered by more than 5 % of the prescribed dose. Compared to the non-ART plans, the ART plans had higher CTV coverage and lower dose to the bladder and rectum (P < 0.05). During the treatment, the intrafractional changes of bladder, rectum and CTV may affect actual dose delivery. And we observed an intrafractional time trend in the motion of the CTV. There were 15 % fractions failing the CTV coverage constraints in post-MRI due to intrafractional motion. The adaptive plans optimized with 3 mm margin could cover CTV of post-MRI in 98 % fractions. Considerable inter- and intrafractional CTV and OARs changes were observed in cervical cancer patients treated on MR-Linac. MRI guided online ART has significant dosimetric advantages in cervical cancer and is an ideal approach for achieving individualized and precise radiotherapy.

In this study, we assess the dosimetric qualities and usability of planning for 1.5 T MR-Linac based intensity modulated radiotherapy (MRL-IMRT) for various clinical sites in comparison with IMRT plans using a conventional linac. In total of 30 patients with disease sites in the brain, esophagus, lung, rectum and vertebra were re-planned retrospectively for simulated MRL-IMRT using the Elekta Unity dedicated treatment planning system (TPS) Monaco (v5.40.01). Currently, the step-and-shoot (ss) is the only delivery technique for IMRT available on Unity. All patients were treated on an Elekta Versa HD^TM with IMRT using the dynamic multileaf collimator (dMLC) technique, and the plans were designed using Monaco v5.11. For comparison, the same dMLC-IMRT plan was recalculated with the same machine and TPS but only changing the technique to step-and-shoot. The dosimetric qualities of the MRL-IMRT plans, to be evaluated by the Dose Volume Histograms (DVH) metrics, Homogeneity Index and Conformality Index, were compared with the clinical plans. The planning usability was measured by the optimization time and the number of Monitor Units (MUs). Comparing MRL-IMRT with conventional linac based plans, all created plans were clinically equivalent to current clinical practice. However, MRL-IMRT plans had higher dose to skin and larger low dose region of normal tissues. Furthermore, MRL-IMRT plans had significantly reduced optimization time by comparing conventional linac based plans. The number of MUs of MRL-IMRT was increased by 23% compared with ss-IMRT, and no difference from dMLC-IMRT. In conclusion, clinically acceptable plans can be achieved with 1.5 T MR-Linac system for multiple tumor sites. Given the differences in machine characteristics, some minor differences in plan quality were found between MR-Linac plans and current clinical practice and this should be considered in clinical practice.