Justin Rineer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Justin Rineer has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Patrick Kelly
Department of Radiation Oncology, Orlando Health Cancer Institute, 9900 W Colonial Drive, Ocoee, FL 34761, USA
4 shared publications - Amish P. Shah
Orlando Hlth Canc Inst, Dept Radiat Oncol, Orlando, FL 32806 USA
3 shared publications - Sanford L. Meeks
Department of Radiation Oncology, Orlando Health Cancer Institute, Orlando, Florida
3 shared publications - Jerrold E. Kielbasa
Department of Radiation Oncology Orlando Health – UF Health Cancer Center Orlando FL USA
2 shared publications Alex Kubli
Center for Advanced Radiation Therapy, Orlando Health-UF Health Cancer Center, Orlando, Florida
1 shared publicationAmish P. Shah
Center for Advanced Radiation Therapy, Orlando Health-UF Health Cancer Center, Orlando, Florida
1 shared publication
Latest Publications
- Open Access
- 11 June 2025
- Published by Elsevier in Physics and Imaging in Radiation Oncology
- Vol. 35
Magnetic resonance-only rapid on-table planning and immediate treatment for spine metastases
- 11 June 2025
- Published by Elsevier in Physics and Imaging in Radiation Oncology
- Vol. 35
Open AccessMagnetic resonance-only rapid on-table planning and immediate treatment for spine metastases
- Open Access
Self-Supervised Learning for Organs At Risk and Tumor Segmentation with Uncertainty Quantification
In this study, our goal is to show the impact of self-supervised pre-training of transformers for organ at risk (OAR) and tumor segmentation as compared to costly fully-supervised learning. The proposed algorithm is called Monte Carlo Transformer based U-Net (MC-Swin-U). Unlike many other available models, our approach presents uncertainty quantification with Monte Carlo dropout strategy while generating its voxel-wise prediction. We test and validate the proposed model on both public and one private datasets and evaluate the gross tumor volume (GTV) as well as nearby risky organs' boundaries. We show that self-supervised pre-training approach improves the segmentation scores significantly while providing additional benefits for avoiding large-scale annotation costs.
Open AccessSelf-Supervised Learning for Organs At Risk and Tumor Segmentation with Uncertainty Quantification
In this study, our goal is to show the impact of self-supervised pre-training of transformers for organ at risk (OAR) and tumor segmentation as compared to costly fully-supervised learning. The proposed algorithm is called Monte Carlo Transformer based U-Net (MC-Swin-U). Unlike many other available models, our approach presents uncertainty quantification with Monte Carlo dropout strategy while generating its voxel-wise prediction. We test and validate the proposed model on both public and one private datasets and evaluate the gross tumor volume (GTV) as well as nearby risky organs' boundaries. We show that self-supervised pre-training approach improves the segmentation scores significantly while providing additional benefits for avoiding large-scale annotation costs.
- Open Access
- 23 February 2022
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 11 (5) , 1189
Proposal and Evaluation of a Physician-Free, Real-Time On-Table Adaptive Radiotherapy (PF-ROAR) Workflow for the MRIdian MR-Guided LINAC
With the implementation of MR-LINACs, real-time adaptive radiotherapy has become a possibility within the clinic. However, the process of adapting a patient’s plan is time consuming and often requires input from the entire clinical team, which translates to decreased throughput and limited patient access. In this study, the authors propose and simulate a workflow to address these inefficiencies in staffing and patient throughput. Two physicians, three radiation therapists (RTT), and a research fellow each adapted bladder and bowel contours for 20 fractions from 10 representative patient plans. Contouring ability was compared via calculation of a Dice Similarity Index (DSI). The DSI for bladder and bowel based on each potential physician–therapist pair, as well as an inter-physician comparison, exhibited good overlap amongst all comparisons (p = 0.868). Plan quality was compared through calculation of the conformity index (CI), as well as an evaluation of the plan’s dose to a ‘gold standard’ set of structures. Overall, non-physician plans passed 91.2% of the time. Of the eight non-physician plans that failed their clinical evaluation, six also failed their evaluation against the ‘gold standard’. Another two plans that passed their clinical evaluation subsequently failed in their evaluation against the ‘gold standard’. Thus, the PF-ROAR process has a success rate of 97.5%, with 78/80 plans correctly adapted to the gold standard or halted at treatment. These findings suggest that a physician-free workflow can be well tolerated provided RTTs continue to develop knowledge of MR anatomy and careful attention is given to understanding the complexity of the plan prior to treatment.
- 23 February 2022
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 11 (5) , 1189
Open AccessProposal and Evaluation of a Physician-Free, Real-Time On-Table Adaptive Radiotherapy (PF-ROAR) Workflow for the MRIdian MR-Guided LINAC
With the implementation of MR-LINACs, real-time adaptive radiotherapy has become a possibility within the clinic. However, the process of adapting a patient’s plan is time consuming and often requires input from the entire clinical team, which translates to decreased throughput and limited patient access. In this study, the authors propose and simulate a workflow to address these inefficiencies in staffing and patient throughput. Two physicians, three radiation therapists (RTT), and a research fellow each adapted bladder and bowel contours for 20 fractions from 10 representative patient plans. Contouring ability was compared via calculation of a Dice Similarity Index (DSI). The DSI for bladder and bowel based on each potential physician–therapist pair, as well as an inter-physician comparison, exhibited good overlap amongst all comparisons (p = 0.868). Plan quality was compared through calculation of the conformity index (CI), as well as an evaluation of the plan’s dose to a ‘gold standard’ set of structures. Overall, non-physician plans passed 91.2% of the time. Of the eight non-physician plans that failed their clinical evaluation, six also failed their evaluation against the ‘gold standard’. Another two plans that passed their clinical evaluation subsequently failed in their evaluation against the ‘gold standard’. Thus, the PF-ROAR process has a success rate of 97.5%, with 78/80 plans correctly adapted to the gold standard or halted at treatment. These findings suggest that a physician-free workflow can be well tolerated provided RTTs continue to develop knowledge of MR anatomy and careful attention is given to understanding the complexity of the plan prior to treatment.
- 1 September 2020
- Published by Elsevier in Practical Radiation Oncology
- Vol. 10 (5) , e425-e431
Technical Report: Diagnostic Scan-Based Planning (DSBP), A Method to Improve the Speed and Safety of Radiation Therapy for the Treatment of Critically Ill Patients
- 1 September 2020
- Published by Elsevier in Practical Radiation Oncology
- Vol. 10 (5) , e425-e431
Technical Report: Diagnostic Scan-Based Planning (DSBP), A Method to Improve the Speed and Safety of Radiation Therapy for the Treatment of Critically Ill Patients
- Open Access
- 5 February 2014
- Published by Springer Nature in Radiation Oncology
- Vol. 9 (1) , 46
A margin-based analysis of the dosimetric impact of motion on step-and-shoot IMRT lung plans
Purpose: Intrafraction motion during step-and-shoot (SNS) IMRT is known to affect the target dosimetry by a combination of dose blurring and interplay effects. These effects are typically managed by adding a margin around the target. A quantitative analysis was performed, assessing the relationship between target motion, margin size, and target dosimetry with the goal of introducing new margin recipes. Methods: A computational algorithm was used to calculate 1,174 motion-encoded dose distributions and DVHs within the patient’s CT dataset. Sinusoidal motion tracks were used simulating intrafraction motion for nine lung tumor patients, each with multiple margin sizes. Results: D95% decreased by less than 3% when the maximum target displacement beyond the margin experienced motion less than 5 mm in the superior-inferior direction and 15 mm in the anterior-posterior direction. For target displacements greater than this, D95% decreased rapidly. Conclusions: Targets moving in excess of 5 mm outside the margin can cause significant changes to the target. D95% decreased by up to 20% with target motion 10 mm outside the margin, with underdosing primarily limited to the target periphery. Multi-fractionated treatments were found to exacerbate target under-coverage. Margins several millimeters smaller than the maximum target displacement provided acceptable motion protection, while also allowing for reduced normal tissue morbidity. PACS: 87.55.dk
- 5 February 2014
- Published by Springer Nature in Radiation Oncology
- Vol. 9 (1) , 46
Open AccessA margin-based analysis of the dosimetric impact of motion on step-and-shoot IMRT lung plans
Purpose: Intrafraction motion during step-and-shoot (SNS) IMRT is known to affect the target dosimetry by a combination of dose blurring and interplay effects. These effects are typically managed by adding a margin around the target. A quantitative analysis was performed, assessing the relationship between target motion, margin size, and target dosimetry with the goal of introducing new margin recipes. Methods: A computational algorithm was used to calculate 1,174 motion-encoded dose distributions and DVHs within the patient’s CT dataset. Sinusoidal motion tracks were used simulating intrafraction motion for nine lung tumor patients, each with multiple margin sizes. Results: D95% decreased by less than 3% when the maximum target displacement beyond the margin experienced motion less than 5 mm in the superior-inferior direction and 15 mm in the anterior-posterior direction. For target displacements greater than this, D95% decreased rapidly. Conclusions: Targets moving in excess of 5 mm outside the margin can cause significant changes to the target. D95% decreased by up to 20% with target motion 10 mm outside the margin, with underdosing primarily limited to the target periphery. Multi-fractionated treatments were found to exacerbate target under-coverage. Margins several millimeters smaller than the maximum target displacement provided acceptable motion protection, while also allowing for reduced normal tissue morbidity. PACS: 87.55.dk
- Open Access
- 1 March 2013
- Published by Elsevier in Radiotherapy and Oncology
- Vol. 106 (3) , 327-332
Aortic dose constraints when reirradiating thoracic tumors
- 1 March 2013
- Published by Elsevier in Radiotherapy and Oncology
- Vol. 106 (3) , 327-332
Open AccessAortic dose constraints when reirradiating thoracic tumors