Purpose: To investigate whether an AI-based method can detect subtle inter-fraction changes in MR-Linac images acquired during radiotherapy and explore the broader potential of MRLinac imaging. Methods: This retrospective study included longitudinal 0.35T MR-Linac images from 761 patients. To identify temporal changes, we employed a deep learning model using temporal ordering via pairwise comparison, previously shown effective for longitudinal imaging studies. The model was trained using first-to-last fraction pairs (F1-FL) and all pairs (All-pairs). Performance was assessed using quantitative metrics (accuracy and AUC) and compared against a radiologist's performance. Qualitative evaluation was performed using saliency maps, which identify anatomical regions associated with temporal imaging changes. Results: The F1-FL model demonstrated high performance (AUC=0.99, accuracy=0.95) and outperformed the radiologist in temporal ordering task. The All-pairs model also showed high performance (AUC=0.97, accuracy=0.91). Regions contributing to predictions included the prostate, bladder, and pubic symphysis. The performance was correlated to fractional intervals and was reduced for non-radiation-exposed timepoints (Sim and F1), suggesting that observed changes may reflect both temporal variation and radiation exposure. Conclusion: MR-Linac imaging appears capable of capturing subtle changes during prostate radiotherapy that can be detected by AI models, even over approximately two-day intervals. The model's high performance, together with quantitative and qualitative analyses, supports a potential role for MR-Linac in clinical applications beyond image guidance.

BACKGROUND AND OBJECTIVE:Some patients undergoing prostatectomy develop biochemical recurrence or have persistently detectable prostate-specific antigen level. Salvage radiotherapy (RT), delivered over ≥4 wk, is a current standard of care. Our objective was to demonstrate that salvage RT delivered in a five-fraction stereotactic body radiotherapy (SBRT) regimen does not significantly increase patient-reported genitourinary (GU) and gastrointestinal (GI) symptoms compared with a 20-fraction regimen (HYPO). METHODS:In this randomized noninferiority study, 137 patients were randomized 1:1 to salvage RT with 32.5 Gy in five fractions or 55 Gy in 20 fractions. We report acute changes in Expanded Prostate Cancer Index Composite (EPIC) scores and Common Terminology Criteria for Adverse Events at 3 and 6 mo. KEY FINDINGS AND LIMITATIONS:The difference in the changes in EPIC GU scores between SBRT and HYPO was 3.3 (95% confidence interval [CI], -8.53, 1.93), indicating a lack of a clinically meaningful difference. The difference in the changes in EPIC GI scores between SBRT and HYPO was 1.16 (95% CI, -5.15, 7.46), indicating a lack of a clinically meaningful difference. CONCLUSIONS AND CLINICAL IMPLICATIONS:Salvage RT delivered in five fractions was not associated with a significantly worse decline in patient-reported GU or GI toxicities at 3 or 6 mo. Further follow-up is necessary to monitor for potential differences in late toxicity and patient-reported outcomes.

Background: Prone breast radiotherapy has been shown to optimally spare the dose to the heart and lungs; we report on the heart and left anterior descending coronary artery (LAD) dosimetry and their implications for current care. Aims: (I) To measure the mean heart dose (MHD) and LAD mean and maximum doses (Dmean and Dmax) in patients with left-side breast cancer who have undergone hypo-fractionated whole breast radiotherapy (WBRT) with a concomitant boost to the post-operative cavity (40.50 Gy to the breast and 48 Gy to the cavity in 15 fractions) in the prone position; (II) to compare the dosimetry results to those reported in the literature for other techniques. Materials and Methods: In a consecutive series of 524 irradiated left-side breast cancer patients, heart and LAD dosimetry data were collected and correlated to breast volume and the volume of the radiation boost to the tumor cavity. A descriptive statistical analysis was performed to compare the same dosimetry data with those reported in the literature from supine techniques. To account for dosimetry differences in hypo-fractionation and conventional fractionated regimens (50–60 Gy in 25–30 fractions) reported in the literature, the cardiac doses were converted to the equivalent dose in 2 Gy fractions (EQD2). As previously reported, the prone setup protocol placed the medial edges of the tangential radiation fields at least 2.5 mm from the contoured LAD. Results: In all patients’ plans, the target coverage was successfully achieved. The mean values (±SD) were as follows: MHD = 0.69 Gy (±0.19) (EQD2 0.35 Gy ± 0.1); LAD Dmean = 2.20 Gy (±0.68) (EQD2 1.18 Gy ± 0.35); LAD Dmax = 4.44 Gy (±1.82) (EQD2 2.55 Gy ± 0.97). The values were consistently lower compared with those achieved by the multiple supine techniques reported in the literature. Spearman’s correlation analysis revealed a strong positive correlation between LAD and heart dosimetry variables. In contrast, no strong correlation was observed between the cardiac dose metrics and breast volume, boost volume, or their ratio index. A linear correlation was detected between LAD Dmean and LAD D2% (R2 0.64); LAD D2% and heart D2% (R2 0.60); LAD Dmax and heart D2% (R2 0.41). Conclusions: The prone position protocol minimizes heart and LAD exposure. This approach results in a dosimetry advantage when compared with more complex and expensive WBRT techniques in the supine position.

Purpose/Objective(s) Ventricular tachycardia (VT) in patients with structural heart disease is associated with reduced quality of life and poor prognosis. Therapeutic options include medication, anti-tachycardia pacing or shock by implantable cardiac devices and catheter-based ablation of heart arrhythmogenic substrates. STereotactic Arrhythmia Radioablation (STAR) tested in a phase I/II trial by Robinson and colleagues offers a novel approach. Materials/Methods Data from a retrospective series of 5 high-risk patients with VT refractory to catheter ablation and medication, treated with STAR are reported from a single referral center. CTV was defined to encompass the arrhythmogenic substrate by a team of a radiation oncologists and treating electrophysiologists, based on clinical and electro-anatomical information derived from CT scan and catheter ablation maps. ITV was added to CTV to compensate for heart and respiratory movement. PTV was then defined by adding an isotropic margin of 2-3 mm to the ITV. Volumetric Modulated Arc Therapy (VMAT) plans were generated, optimized, and delivered using medical linear accelerator. The prescription dose to the PTV was 25 Gy in 1 fraction. Results Mean CTV, ITV and PTV volumes, were 141.1cc, 187.7cc, 298.1cc, respectively. Mean heart volume was 1740.6 cc. All 5 patients completed STAR procedure and treatment. There were no acute treatment-related adverse events. Clinical and treatment-efficacy data are summarized in Table. STAR significantly reduced or abrogated arrythmia at a median time of 24 weeks (range = 4-48) post-treatment. Patient n.1 and n.3 showed a remarkable reduction of VT episodes at 4- and 8-weeks post-treatment, respectively. Patients n.2, n.4 and n.5 were free of VT episodes at 6-months post-treatment. At a median follow-up time of 11 months (range = 1-19), 2/5 patients are alive (patient n.2 and n.4), both free of VT events at 1-year post-treatment. Patient n.1 died due to complication after cardiac transplantation, patients n.3 due to sepsis and multiorgan failure and patient n.5 due to COVID pneumonia, at 11-, 1- and 5-months post-STAR, respectively. Conclusion These data suggest that LINAC-based STAR is a safe and effective treatment option in high-risk patients with VT refractory to catheter ablation and medication. Results from large perspective studies will define optimal patient selection and inform about long-term outcomes.

Purpose: Magnetic resonance (MR) image guidance may facilitate safe ultrahypofractionated radiation dose escalation for inoperable pancreatic ductal adenocarcinoma. We conducted a prospective study evaluating the safety of 5-fraction Stereotactic MR-guided on-table Adaptive Radiation Therapy (SMART) for locally advanced (LAPC) and borderline resectable pancreatic cancer (BRPC). Methods and Materials: Patients with LAPC or BRPC were eligible for this multi-institutional, single-arm, phase 2 trial after >= 3 months of systemic therapy without evidence of distant progression. Fifty gray in 5 fractions was prescribed on a 0.35T MR-guided radiation delivery system. The primary endpoint was acute grade >= 3 gastrointestinal (GI) toxicity definitely attrib-uted to SMART.Results: One hundred thirty-six patients (LAPC 56.6%, BRPC 43.4%) were enrolled between January 2019 and January 2022. Mean age was 65.7 (36-85) years. Head of pancreas lesions were most common (66.9%). Induction chemotherapy mostly con-sisted of (modified)FOLFIRINOX (65.4%) or gemcitabine/nab-paclitaxel (16.9%). Mean CA19-9 after induction chemotherapy and before SMART was 71.7 U/mL (0-468). On-table adaptive replanning was performed for 93.1% of all delivered fractions. Median follow-up from diagnosis and SMART was 16.4 and 8.8 months, respectively. The incidence of acute grade >= 3 GI tox-icity possibly or probably attributed to SMART was 8.8%, including 2 postoperative deaths that were possibly related to SMART in patients who had surgery. There was no acute grade >= 3 GI toxicity definitely related to SMART. One-year overall survival from SMART was 65.0%.Conclusions: The primary endpoint of this study was met with no acute grade >= 3 GI toxicity definitely attributed to ablative 5-fraction SMART. Although it is unclear whether SMART contributed to postoperative toxicity, we recommend caution when pursuing surgery, especially with vascular resection after SMART. Additional follow-up is ongoing to evaluate late toxic-ity, quality of life, and long-term efficacy. (c) 2023 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Purpose/objectivesAn artificial intelligence-based pseudo-CT from low-field MR images is proposed and clinically evaluated to unlock the full potential of MRI-guided adaptive radiotherapy for pelvic cancer care.Materials and methodIn collaboration with TheraPanacea (TheraPanacea, Paris, France) a pseudo-CT AI-model was generated using end-to-end ensembled self-supervised GANs endowed with cycle consistency using data from 350 pairs of weakly aligned data of pelvis planning CTs and TrueFisp-(0.35T)MRIs. The image accuracy of the generated pCT were evaluated using a retrospective cohort involving 20 test cases coming from eight different institutions (US: 2, EU: 5, AS: 1) and different CT vendors. Reconstruction performance was assessed using the organs at risk used for treatment. Concerning the dosimetric evaluation, twenty-nine prostate cancer patients treated on the low field MR-Linac (ViewRay) at Montpellier Cancer Institute were selected. Planning CTs were non-rigidly registered to the MRIs for each patient. Treatment plans were optimized on the planning CT with a clinical TPS fulfilling all clinical criteria and recalculated on the warped CT (wCT) and the pCT. Three different algorithms were used: AAA, AcurosXB and MonteCarlo. Dose distributions were compared using the global gamma passing rates and dose metrics.ResultsThe observed average scaled (between maximum and minimum HU values of the CT) difference between the pCT and the planning CT was 33.20 with significant discrepancies across organs. Femoral heads were the most reliably reconstructed (4.51 and 4.77) while anal canal and rectum were the less precise ones (63.08 and 53.13). Mean gamma passing rates for 1%1mm, 2%/2mm, and 3%/3mm tolerance criteria and 10% threshold were greater than 96%, 99% and 99%, respectively, regardless the algorithm used. Dose metrics analysis showed a good agreement between the pCT and the wCT. The mean relative difference were within 1% for the target volumes (CTV and PTV) and 2% for the OARs.ConclusionThis study demonstrated the feasibility of generating clinically acceptable an artificial intelligence-based pseudo CT for low field MR in pelvis with consistent image accuracy and dosimetric results.

Prostate cancer is a common malignancy for which radiation therapy provides an excellent management option with high rates of control and low toxicity. Historically radiation therapy has been delivered with CT-based image guidance. Recently, magnetic resonance (MR) imaging capabilities have been successfully integrated with radiation therapy delivery platforms, presenting an appealing, yet complex, method of guiding, adapting, and delivering radiation therapy. We sought to summarize the current landscape of optimal strategies of testing and benefits of MR guidance and radiation treatment delivery in prostate cancer.

BACKGROUND AND PURPOSE:Radiation dose escalation may improve local control (LC) and overall survival (OS) in select pancreatic ductal adenocarcinoma (PDAC) patients. We prospectively evaluated the safety and efficacy of ablative stereotactic magnetic resonance (MR)-guided adaptive radiation therapy (SMART) for borderline resectable (BRPC) and locally advanced pancreas cancer (LAPC). The primary endpoint of acute grade ≥ 3 gastrointestinal (GI) toxicity definitely related to SMART was previously published with median follow-up (FU) 8.8 months from SMART. We now present more mature outcomes including OS and late toxicity. MATERIALS AND METHODS:This prospective, multi-center, single-arm open-label phase 2 trial (NCT03621644) enrolled 136 patients (LAPC 56.6 %; BRPC 43.4 %) after ≥ 3 months of any chemotherapy without distant progression and CA19-9 ≤ 500 U/mL. SMART was delivered on a 0.35 T MR-guided system prescribed to 50 Gy in 5 fractions (biologically effective dose10 [BED10] = 100 Gy). Elective coverage was optional. Surgery and chemotherapy were permitted after SMART. RESULTS:Mean age was 65.7 years (range, 36-85), induction FOLFIRINOX was common (81.7 %), most received elective coverage (57.4 %), and 34.6 % had surgery after SMART. Median FU was 22.9 months from diagnosis and 14.2 months from SMART, respectively. 2-year OS from diagnosis and SMART were 53.6 % and 40.5 %, respectively. Late grade ≥ 3 toxicity definitely, probably, or possibly attributed to SMART were observed in 0 %, 4.6 %, and 11.5 % patients, respectively. CONCLUSIONS:Long-term outcomes from the phase 2 SMART trial demonstrate encouraging OS and limited severe toxicity. Additional prospective evaluation of this novel strategy is warranted.

Advances in radiotherapy technologies have enabled more precise target guidance, improved treatment verification, and greater control and versatility in radiation delivery. Amongst the recent novel technologies, Magnetic Resonance Imaging (MRI) guided radiotherapy (MRgRT) may hold the greatest potential to improve the therapeutic gains of image-guided delivery of radiation dose. The ability of the MRI linear accelerator (LINAC) to image tumors and organs with on-table MRI, to manage organ motion and dose delivery in real-time, and to adapt the radiotherapy plan on the day of treatment while the patient is on the table are major advances relative to current conventional radiation treatments. These advanced techniques demand efficient coordination and communication between members of the treatment team. MRgRT could fundamentally transform the radiotherapy delivery process within radiation oncology centers through the reorganization of the patient and treatment team workflow process. However, the MRgRT technology currently is limited by accessibility due to the cost of capital investment and the time and personnel allocation needed for each fractional treatment and the unclear clinical benefit compared to conventional radiotherapy platforms. As the technology evolves and becomes more widely available, we present the case that MRgRT has the potential to become a widely utilized treatment platform and transform the radiation oncology treatment process just as earlier disruptive radiation therapy technologies have done.

Purpose/Objective(s) Organs at risk annotation is a strong bottleneck of Magnetic resonance imaging guided radiotherapy (MRgRT) in the context of adaptive treatment. It is a time-consuming task that reduces patient throughput (20% of the fraction duration dedicated to contouring) while suffering standardization and reproducibility across physicians, hampering the accuracy of high precision MRgRT and diminishing its adoption potential. AI-contouring becomes a game changer in radiation oncology since it is able within seconds to provide a full OAR delineation that could be close to clinical acceptance with little modifications. The aim of this study is to evaluate the performance of AI-contouring within a multi-centric cohort for patients with pelvic / abdominal tumors treated with low field (0.35T) MRgRT. Materials/Methods In the context of this study, a CE/FDA cleared anatomically preserving ensemble deep-learning architecture contouring solution was considered. The adopted solution was trained using more than 350 0.35T MR fully annotated pelvic cases according to the ESTRO guidelines and 270 annotated abdomen fractions samples. A retrospective cohort involving 42 test cases coming from seven different institutions (US: 1, EU: 5, AS: 1) was considered. The clinical delineations used for treatment planning from expert physicians/medical physicists were associated with these cases. Results It appears that treatment practices can be very different between institutions since the use of OAR constraints were far from being uniformly adopted. Bladder & liver dosimetry constraints were the most frequently used (100% & 90%) while abdominal aorta and seminal vesicle were the least adopted (24% & 15%). The average DSC between Clinical experts and AI annotations was 78% across all structures. Bladder and left/right kidney were the structures for which the highest DSC were observed (93%, 91% & 90%), while penile bulb and duodenum were the ones with the lowest agreement (54% & 59%). AI solutions seem to have important discrepancies with clinical contours in organs on which either the volume is small or there are practice-related uncertainties with respect to the definition of beginning and the end of the structure. For quantitative evaluation, dice similarity coefficients (DSC) and 95% Hausdorff distances (HD95) were calculated. Conclusion This retrospective multi-centric study demonstrates that AI-driven contours could be a reliable alternative to clinical contours offering performance that appears to be close to the human expert for many of the structures while increasing throughput and offering automatization & standardization.

Purpose/Objective(s) Magnetic Resonance is an essential modality in the context of radiotherapy primarily for providing additional information with respect to tumor functional information leading to better target delineation (brain, prostate, etc.) and secondary in the context of emergence of magnetic resonance guided radiotherapy. However, in both cases computed tomography acquisition remains necessary for dosimetric purposes hampering the workflow, introducing additional cost and dose simulation/optimization discrepancies (due to the registration issues between MR & CT) while being associated with additional patient toxicity. This study aims to investigate in a retrospective manner the relevance deep learning synthetic CT generation as an alternative for simulation and planning for pelvic tumors treated with low field (0.35T) MRgRT. Materials/Methods In the context of this study, a cycle generative adversarial neural network (GAN) deep learning architecture was trained to determine a bijective transformation between a low field (0.35T) MR and the associated computed tomography scan acquisition. The training set involved 350 pairs of weakly aligned data of pelvis cases. A retrospective cohort involving 20 test cases coming from eight different institutions (US: 2, EU: 5, AS: 1) involving different CT vendors was considered for testing. Results Reconstruction performance was assessed using the OARs used for treatment. The observed average scaled (between maximum and minimum HU values of the CT) difference between the reconstructed and the CT used for planning was 35.08 with significant discrepancies across organs. Femoral heads were the most reliably reconstructed (4.51 & 4.77) while rectum and sigmoid were the less precise ones (53.13 & 51.48). In terms of qualitative evaluation, the presence of fiducial markers heavily penalizes the reconstruction due to the implicit propagation of errors associated with the "convolution" nature of deep learning. The presence of air bubbles visible on the CT (sigmoid and rectum) is also an issue since these elements are marginally perceptible in the MR and therefore can hardly be predicted from generator. Detailed reconstruction results per organ are appended. Conclusion This retrospective multi-centric study is a first step toward assessing the potential of a fully low field MR-based treatment planning workflow that eliminates the need of CT acquisition. Integration of the synthetic CT in the simulation/optimization and assessment of the induced dosimetric errors are necessary steps to determine the clinical relevance of our preliminary findings.

Background:A major challenge in breast radiotherapy is accurately targeting the surgical cavity volume. Application of the emerging MRI-guided radiotherapy (MRgRT) technique in breast radiotherapy may enable more accurate targeting and potentially reduce side effects associated with treatment.Purpose:To study the feasibility of delivering MRI-guided partial breast radiotherapy or Precision Prone Irradiation (PPI) to treat DCIS and early stage breast cancer patients.Materials and methods:Eleven patients with diagnosed DCIS or early stage breast cancer treated with lumpectomy underwent CT-based and MRI-based simulations and treatment planning in the prone position. MRI-guided radiotherapy was utilized to deliver partial breast irradiation. A customized adaptive plan was created for each delivered radiotherapy fraction and the cumulative doses to the target volumes and nearby organs at risk were determined. The CT-based and the MRI-guided radiotherapy plans were compared with respect to target volumes, target volume coverage, and dose to nearby organs.Results:All patients receiving PPI successfully completed their treatments as planned. Clinical target volume (CTV) and planning target volume (PTV) dose coverage and organs-at-risk (OAR) dose constraints were met in all fractions planned and delivered and the MRI-guided clinical target volumes were smaller when compared to those of the CT-based partial breast radiotherapy plans for these eleven patients.Conclusions:MRI-guided partial breast radiotherapy as a breast radiotherapy technology is feasible and is a potential high clinical impact application of MRgRT. PPI has the potential to improve the therapeutic index of breast radiotherapy by more accurately delivering radiation dose to the cavity target and decreasing toxicities associated with radiation to the surrounding normal tissues. Prospective clinical data and further technical refinements of this novel technology may broaden its clinical implementation.

Abstract PURPOSE/OBJECTIVE(S) Post-operative spine SBRT presents unique clinical challenges. Spinal hardware produces CT and high-field strength MRI artifacts that obscure visualization of the spinal cord and unresected disease. Existing workflows incorporate additional invasive procedures with CT myelogram and quality control for these procedures can introduce uncertainty into SBRT planning. Reducing metallic imaging artifact with a low-field strength (0.35 T) MRI integrated into a MR-Linac (MRL) may facilitate superior visualization of the spinal cord, improved target delineation and treatment localization. The primary objective is to determine the feasibility of MRL-based simulation workflow to facilitate MR-guided post-operative spine SBRT without the need for CT myelogram or CT-based target delineation. MATERIALS/METHODS A single-institution, single-arm interventional feasibility study is planned. A total of 10 patients who underwent surgical resection of solid tumor spinal metastases with an indication for post-operative SBRT will be enrolled and undergo radiation planning and treatment on a MRL platform that combines a 6MV Linac and 0.35 T on-board MRI system. Enrolled subjects will undergo CT and MR simulation followed by standard-of-care post-operative spine SBRT and follow-up spine imaging every 3 months. RESULTS The primary endpoint is feasibility of MR-guided post-operative spine SBRT without CT myelogram. Feasibility is defined as > 70% of participants with clinically acceptable visualization/delineation as determined by blinded dual neuroradiologist review for clinically acceptable visualization/delineation of organs-at-risk (OARs) and target volume(s). Exploratory endpoints involve radiation dosimetry analysis of OARs and target volumes as well as documenting the use of adaptive planning. Radiation site progression-free survival will be recorded at 6-months after SBRT. CONCLUSION If feasible, an MRL-based workflow for post-operative spine SBRT represents a patient-centric approach to improve efficiency, minimize treatment delays, and avoid invasive procedures that may improve clinical management of solid tumor spinal metastases.

AbstractPurposeTo investigate the impact of rectal spacing on inter‐fractional rectal and bladder dose and the need for adaptive planning in prostate cancer patients undergoing SBRT with a 0.35 T MRI‐Linac.Materials and MethodsWe evaluated and compared SBRT plans from prostate cancer patients with and without rectal spacer who underwent treatment on a 0.35 T MRI‐Linac. Each group consisted of 10 randomly selected patients that received prostate SBRT to a total dose of 36.25 Gy in five fractions. Dosimetric differences in planned and delivered rectal and bladder dose and the number of fractions violating OAR constraints were quantified. We also assessed whether adaptive planning was needed to meet constraints for each fraction.ResultsOn average, rectal spacing reduced the maximum dose delivered to the rectum by more than 8 Gy (p < 0.001). We also found that D3cc received by the rectum could be 12 Gy higher in patients who did not have rectal spacer (p < 9E‐7). In addition, the results show that a rectal spacer can reduce the maximum dose and D15cc to the bladder wall by more than 1 (p < 0.004) and 8 (p < 0.009) Gy, respectively. Our study also shows that using a rectal spacer could reduce the necessity for adaptive planning. The incidence of dose constraint violation was observed in almost 91% of the fractions in patients without the rectal spacer and 52% in patients with implanted spacer.ConclusionInter‐fractional changes in rectal and bladder dose were quantified in patients who underwent SBRT with/without rectal SpaceOAR hydrogel. Rectal spacer does not eliminate the need for adaptive planning but reduces its necessity.

High dose stereotactic body radiotherapy (SBRT) may offer improved outcomes for pancreatic cancer patients, but treatment delivery remains a challenge due to tumor proximity to organs-at-risk (OAR) and daily anatomic variability. Stereotactic MRI-guided adaptive radiation therapy (SMART) with real-time tumor tracking allows for improved dose delivery and OAR sparing by accounting for anatomic changes with each treatment. This study reports initial outcomes, treatment-associated toxicities, and dosimetric outcomes in locally advanced, metastatic, and/or recurrent pancreatic cancer patients treated using SMART. We performed a retrospective analysis of locally advanced, metastatic, and/or recurrent pancreatic cancer patients who underwent adaptive planning with MRI-guided radiation treatments. Charts were reviewed for follow-up, imaging, and laboratory values, including CA19-9 and absolute lymphocyte count. A plan was generated for each patient after initial CT and MR-simulation. At each treatment, MR imaging was obtained for the daily anatomy and the initial (unadapted) plan was compared to obtain a predicted dose to target volumes and OARs using a prescribed dose ranging from 30-50 Gy in 3-5 fractions. If constraints were not met or coverage was inadequate, an adaptive plan was generated based on the anatomy imaged on the day of treatment. From June 2018 to February 2020, a total of 23 patients were analyzed. With a median follow up of 5 months, we observed 15/19 (79%) with local control, 12/19 (63%) distal metastatic control, and a median overall survival of 19 months from cancer diagnosis. We observed no grade 3 or higher treatment related toxicities. Two patients were found to have an absolute lymphocyte count less than 0.5 x 103 cells/μl within six months of radiation, and 11/17 (65%) had lower CA19-9 six months after radiation treatment compared to before treatment. Of the 23 patients treated, there were 71 adaptive plans available for analysis. Compared to unadapted plans, adaptive fractions had improved coverage of PTV (84.94% vs. 73.36% at 100% of prescribed dose) and CTV (94.62% vs 88.08% at 95% of prescribed dose). Unadapted plans were more likely to exceed OAR constraints with 63 of 71 (89%) unadapted fractions predicted to violate prescribed duodenal, stomach, or small bowel constraints. Moreover, 34/71 (48%) of unadapted fractions violated constraints for 2 of 3 abdominal OARs and 10/71 (14%) violated constraints for all 3 compared to none for adapted fractions. Stereotactic adaptive MRI-guided radiotherapy demonstrated minimal treatment-related toxicities, enhanced tumor volume coverage, and improved adherence to OAR constraints in pancreatic cancer patients. Additional follow up is needed to further assess outcomes of these patients.