Udbhav S. Ram

Udbhav S. Ram

Auto-generated profile, based on publicly available information

Udbhav S. Ram

Department of Radiation Oncology, University of Alabama at Birmingham , Birmingham, AL

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2025 in Intelligent Oncology
Verified
Journal Article
Open access
URUdbhav S. Ram
Udbhav S. Ram
JPJoel A. Pogue
Joel A. Pogue
MSMichael Soike
Michael Soike
NPNeil T. Pfister
Neil T. Pfister
RJRojymon Jacob
Rojymon Jacob
CCCarlos E. Cardenas
Carlos E. Cardenas
Segmentation of abdominal organs in computed tomography (CT) images within clinical oncological workflows is crucial for ensuring effective treatment planning and follow-up. However, manually generated segmentations are time-consuming and labor-intensive in addition to being subject to inter-observer variability. Many deep learning (DL) and Automated Machine Learning (AutoML) frameworks have emerged as a solution to this challenge and show promise in clinical workflows. This study presents a comprehensive evaluation of existing AutoML frameworks (Auto3DSeg, nnU-Net) against a state-of-the-art non-AutoML framework, the Shifted Window U-Net Transformer (SwinUNETR). Each framework was trained on the same 122 training images, taken from the Abdominal Multi-Organ Segmentation (AMOS) grand challenge. Frameworks were compared using Dice Similarity Coefficient (DSC), Surface DSC (sDSC), and 95th Percentile Hausdorff Distances (HD95) on an additional 72 holdout-validation images. The perceived clinical viability of 30 auto-contoured test cases was assessed by three physicians in a blinded evaluation. Comparisons show significantly better performance by AutoML methods. nnU-Net (average DSC: 0.924, average sDSC: 0.938, average HD95: 4.26, median Likert: 4.57), Auto3DSeg (average DSC: 0.902, average sDSC: 0.919, average HD95: 8.76, median Likert: 4.49), and SwinUNETR (average DSC: 0.837, average sDSC: 0.844, average HD95: 13.93). AutoML frameworks were quantitatively preferred (13/13 OARs P >0.0.5 in DSC and sDSC, 12/13 OARs P>0.05 in HD95, comparing Auto3DSeg to SwinUNETR, and all OARs P>0.05 in all metrics comparing SwinUNETR to nnU-Net). Qualitatively, nnU-Net was preferred over Auto3DSeg (P=0.0027). The findings suggest that AutoML frameworks offer a significant advantage in the segmentation of abdominal organs, and underscores the potential of AutoML methods to enhance the efficiency of oncological workflows.

17 December 2025 in Neuro-Oncology Practice
Verified
Journal Article
Open access
YKYogesh Kumar
Yogesh Kumar
KLKayla Lewis
Kayla Lewis
HCHo-hsin Chang
Ho-hsin Chang
URUdbhav Ram
Udbhav Ram
GRGaurav N Rathi
Gaurav N Rathi
CCCarlos E. Cardenas
Carlos E. Cardenas
Background: Brain metastases (BMs) patients often receive multiple courses of radiotherapy (RT). Comparing follow-up imaging with RT plans is time-intensive and currently not possible in picture archiving and communication system (PACS). In this study, we aim to develop an automated tool to overlay pre-RT tumor contours onto follow-up MRI in the PACS to support response assessment and identification of untreated metastases, reducing review complexity and time. Methods: We built an AI-driven workflow that registers planning CT to follow-up MRI and propagates treated-lesion contours; outputs are exported as PACS-compliant DICOM. Performance was evaluated in 40 patients: 20 underwent quantitative comparison between manual and automated registrations using Dice similarity coefficient (DSC) and mean surface distance (MSD), following AAPM TG-132 guidelines; 20 additional patients (5-35 lesions per patient) underwent clinical evaluation of follow-up and pre-RT lesions contours visualization in PACS. Three physicians assessed these cases to measure review time and inter-observer agreement in treatment response classification (improved/stable vs indeterminate). Results: The workflow successfully registered all CT-MRI pairs. Mean DSC/MSD was: brain 0.97 ± 0.01/0.0 ± 0.0 mm, brainstem 0.89 ± 0.03/0.1 ± 0.1 mm, and gross tumor volumes 0.65 ± 0.18/0.6 ± 0.4 mm. Average physician review time per case decreased from 7.97 to 3.95 min with the automated workflow, and full inter-physician agreement increased from 72.4% to 93.5%. Conclusion: We developed and validated an AI-based tool that accurately fuses pre-RT contours with follow-up MRI for BMs, addressing a key gap in current PACS systems. The workflow significantly reduced review time per lesion and enhanced inter-physician agreement, and has the potential to enable faster, more consistent multidisciplinary follow-up assessment.

2 October 2024 in medRxiv
Verified
Preprint
Open access
PDF file
URUdbhav S. Ram
Udbhav S. Ram
JPJoel A. Pogue
Joel A. Pogue
MSMichael Soike
Michael Soike
NPNeil T. Pfister
Neil T. Pfister
RJRojymon Jacob
Rojymon Jacob
CCCarlos E. Cardenas
Carlos E. Cardenas
Segmentation of abdominal organs in clinical oncological workflows is crucial for ensuring effective treatment planning and follow-up. However, manually generated segmentations are time-consuming and labor-intensive in addition to experiencing inter-observer variability. Many deep learning (DL) and Automated Machine Learning (AutoML) frameworks have emerged as a solution to this challenge and show promise in clinical workflows. This study presents a comprehensive evaluation of existing AutoML frameworks (Auto3DSeg, nnU-Net) against a state-of-the-art non-AutoML framework, the Shifted Window U-Net Transformer (SwinUNETR), each trained on the same 122 training images, taken from the Abdominal Multi-Organ Segmentation (AMOS) grand challenge. Frameworks were compared using Dice Similarity Coefficient (DSC), Surface DSC (sDSC) and 95th Percentile Hausdorff Distances (HD95) on an additional 72 holdout-validation images. The perceived clinical viability of 30 auto-contoured test cases were assessed by three physicians in a blinded evaluation. Comparisons show significantly better performance by AutoML methods. nnU-Net (average DSC: 0.924, average sDSC: 0.938, average HD95: 4.26, median Likert: 4.57), Auto3DSeg (average DSC: 0.902, average sDSC: 0.919, average HD95: 8.76, median Likert: 4.49), and SwinUNETR (average DSC: 0.837, average sDSC: 0.844, average HD95: 13.93). AutoML frameworks were quantitatively preferred (13/13 OARs p>0.0.5 in DSC and sDSC, 12/13 OARs p>0.05 in HD95, comparing Auto3DSeg to SwinUNETR, and all OARs p>0.05 in all metrics comparing SwinUNETR to nnU-Net). Qualitatively, nnU-Net was preferred over Auto3DSeg (p=0.0027). The findings suggest that AutoML frameworks offer a significant advantage in the segmentation of abdominal organs, and underscores the potential of AutoML methods to enhance the efficiency of oncological workflows.

21 November 2025 in Journal of Applied Clinical Medical Physics
Verified
Journal Article
Open access
URUdbhav S. Ram
Udbhav S. Ram
RPRichard A. Popple
Richard A. Popple
JFJohn B. Fiveash
John B. Fiveash
KHKatherine A. Heinzman
Katherine A. Heinzman
YKYogesh Kumar
Yogesh Kumar
JPJoel A. Pogue
Joel A. Pogue
Purpose: This study evaluates the impact of the Ethos 2.0 high‐fidelity (HF) mode on single‐isocenter, stereotactic radiosurgery (SRS) planning workflows. By comparing different planning templates, we assess the effects of HF mode and control rings (R) on plan quality, aiming to optimize treatment for patients with brain metastases. Methods: A cohort of 45 patients with brain metastases was divided into a tuning ( n = 15) and a validation set ( n = 30). Four planning templates were evaluated: HFonRon, HFonRoff, HFoffRon, and HFoffRoff. Plans were generated using the Ethos Intelligent Optimization Engine (IOE v02.00.10), and all patients were prescribed 30 Gy in 5 fractions using 2 mm PTV margins. Plan quality was evaluated using target coverage (PTV V100%), normal brain dose (Brain‐PTV V30Gy), Paddick conformity index (CI), and Falloff index. Plan complexity was evaluated using total MU's on a per‐plan basis across the four templates. Results: The HFonRon template produced better quality plans, achieving significant improvements in normal tissue sparing ( p < 0.0001), CI ( p < 0.0001), and Falloff index ( p < 0.0001) compared to other templates. All templates provided clinically acceptable target coverage. In the HFoffRoff configuration, 97.5 % of targets met the coverage criterion (V100% > 95%). The other setups achieved coverage in 99.2% (HFoffRon), 96.6% (HFonRoff), and 98.3% (HFonRon) of targets, respectively. Plan complexity decreased significantly ( p < 0.0001) when enabling HF mode compared to both HF disabled templates Conclusions: His study shows that combining Ethos 2.0's high‐fidelity mode with user‐defined control rings yields superior single‐isocenter SRS plans compared with planning strategies that omit one or both features. This approach improves dose conformity, reduces normal tissue exposure, and decreases plan complexity through semi‐automated, template‐based planning. These findings suggest that HF mode can be a valuable tool in clinical practice for optimizing SRS treatments for patients with brain metastases.

13 October 2026 in medRxiv
Verified
Preprint
Open access
PDF file
URUdbhav Ram
Udbhav Ram
RZRan Zhang
Ran Zhang
Background: Many radiology decisions, such as whether a report describes a finding or how urgently a study should be read, are choices among a fixed set of answers. Decision models return a probability for each permitted answer in one step, without generating text, and an open-weight model can run within a hospital so that patient data stay local. No decision model has yet been specialized for radiology and compared with large language models (LLMs). Methods: We fine-tuned the general-purpose decision models Kev-27B (Qwen3.8-27B backbone) and Kev-9B on 36,109 records from public radiology datasets to obtain RadKev-27B and RadKev-9B, and compared them with the Kev models, the hosted decision models Jev and OpenAI Decisions, and the LLM Qwen3.8-27B, on 14,142 held-out questions in fifteen tasks (report reading, case diagnosis and classification, radiological knowledge). The prespecified primary outcome was task-averaged accuracy relative to Kev-27B. Results: RadKev-27B exceeded Kev-27B by 4.9 percentage points (95% CI 3.8 to 6.2), with the largest gain in report error detection (22.6 points); RadKev-9B exceeded Kev-9B by 6.9 points (5.5 to 8.4) and did not differ detectably from Kev-27B, a model three times its size. RadKev-27B was more accurate than the hosted decision models Jev (3.0 points, 1.7 to 4.4) and OpenAI Decisions (4.8, 3.2 to 6.4), than Qwen3.8-27B without reasoning (4.7, 3.4 to 6.0) and with reasoning (2.8 points, 1.0 to 4.6) on 1,675 questions, at 132-fold lower latency (128 ms vs 16.9 s per question). At an error rate of 5%, RadKev-27B could answer 90.5% of questions and Kev-27B 76.4%. Conclusions: RadKev-27B was more accurate than two hosted decision models and an LLM of the same size, with or without reasoning, at a fraction of the latency of reasoning, and can be deployed within an institution for categorical radiology decisions after validation on local data.