Thrilled to share that our work has been selected for an Oral Scientific Presentation in the BEST of Physics session at the American Society for Radiation Oncology (ASTRO) 2026 Annual Meeting, September 26–30 in Boston, MA. Out of ~2,700 abstracts submitted to ASTRO this year, only 300 were chosen for oral presentation, and BEST of Physics gathers the highest-rated physics work of the meeting.
Presentation details
| Abstract # | 75557 |
| Title | Early Adaptive Interventions in Lung Cancer: Leveraging Fusion of Longitudinal CBCT Trajectories and Clinical Variables for Robust Survival Prediction |
| Session | SS 19 — BEST of Physics |
| Date / Time | September 28, 2026 · 10:45 AM – 12:00 PM ET |
| Venue | Thomas M. Menino Convention & Exhibition Center, Boston, MA |
| Format | 7-min oral + 3-min Q&A |
| Publication | Red Journal supplement |
Authors
Wookjin Choi, Pradeep Bhetwal, Michael Dichmann, Yingcui Jia, Wenchao Cao, Danfu Liang, Yingxuan Chen, Adam Dicker, Yevgeniy Vinogradskiy
Department of Radiation Oncology, Sidney Kimmel Medical College at Thomas Jefferson University, Philadelphia, PA
Acknowledgement. This work would not exist without Dr. Pradeep Bhetwal, who led the original data collection across the 189-patient cohort and built the first CBCT radiomics extraction pipeline and initial survival model during his time in the lab. The cumulative-longitudinal framework presented here was developed on the foundation of his earlier work — published as two first-author abstracts:
- Bhetwal P, Dichmann M, Ghimire R, Chen Y, Vinogradskiy Y, Werner-Wasik M, Dicker A, Choi W. Development and Validation of a Scalable Radiomics Pipeline for Lung Cancer Research Using Clinical and Public Datasets (SU-1015-202-4). Medical Physics 52(10):e700597, AAPM 2025.
- Bhetwal P, Dichmann M, Ghimire R, Chen Y, Vinogradskiy Y, Werner-Wasik M, Dicker AP, Choi W. Integrating Clinical and Radiomic Features for Enhanced Prognostic Modeling for Lung Cancer Survival. IJROBP 123(1):e719, ASTRO 2025.
Funding. This research was supported by a research grant from Varian Medical Systems, Inc. (related announcement).
What the study is about
Traditional prognostic models for lung cancer rely on static pre-treatment factors and miss the dynamic response of tumors during radiotherapy. Cone-beam CT (CBCT) provides serial imaging of this evolution, but snapshot or delta-radiomics approaches fail to capture the full response trajectory.
We propose a cumulative longitudinal radiomics framework that integrates clinical data with CBCT-derived trajectories. Across 189 patients · 225 treatment courses · 5,067 CBCT scans, we evaluated how early in the treatment course we can identify high-risk patients from imaging dynamics alone.
Key finding: the cumulative CBCT model reaches peak prognostic accuracy by Week 2 (C-index 0.72), with stability improving monotonically through Week 6 — outperforming clinical-only, planning-CT, and delta-radiomics baselines. The framework uses standard-of-care imaging with no additional acquisition burden, offering a practical pathway toward earlier adaptive radiotherapy interventions.
Looking forward to Boston
Excited to present this work to the radiation oncology physics community in late September. Drop by SS 19 if you’re attending!
The full abstract will be published in the Red Journal supplement closer to the meeting. Stay tuned for slides and follow-up materials.