EUVIMEDEUVIMED entdecken
Crossref

Reliability‐weighted patch learning for synthetic CT reconstruction in head and neck adaptive radiotherapy: A proof‐of‐concept study

Jeong Heon Kim, Sven Olberg, Byong Su Choi, Sridhar Yaddanapudi, Xiaoying Liang, Bo Lu, Jun Tan, Jin Sung Kim, So Hyun Ahn, Keith M Furutani, Chris J Beltran, Justin C Park

Medical Physics · 2026-11 · 53 (11)

DOI: 10.1002/mp.70684 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 02.11.2026. Verfasst von Jeong Heon Kim und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Mayo Clinic, Jacksonville, Florida, USA. Hauptthemen laut MEDLINE: Head and Neck Neoplasms, Cone-Beam Computed Tomography, Image Processing, Computer-Assisted, Radiotherapy, Image-Guided. Die Arbeit nennt 50 Literaturangaben. Gefördert von: Office of Governor Ron DeSantis, State of Florida (Governor DeSantis), Korea Institute for Advancement of Technology, National Research Foundation of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Cone‐beam computed tomography (CBCT) is essential for adaptive radiotherapy (ART) but is limited by poor image quality. Existing deep learning methods for synthetic CT (sCT) generation face a critical trade‐off: diffusion models offer high fidelity but are impractically slow, while fast‐inference networks often lack structural accuracy and optimization stability.

Purpose

To develop HQ‐PatchNet, a reliability‐driven deep learning framework designed to improve CBCT‐to‐sCT image quality while maintaining rapid inference speed for online ART workflows.

Methods

HQ‐PatchNet utilizes a vision transformer (ViT)‐integrated CycleGAN architecture. It introduces a reliability‐driven, SSIM‐based selective patch weighting mechanism controlled by a temperature decay schedule. This dynamically suppresses artifact‐dominated regions and focuses optimization on anatomically reliable structures. The model was evaluated on 304 paired head‐and‐neck (HN) scans against conventional networks and recent diffusion models using quantitative metrics (MAE, SSIM, NCC, PSNR), computational speed, and clinical dosimetric accuracy (3D gamma index, 2%/2 mm).

Results

HQ‐PatchNet improved image quality, reducing Mean Absolute Error (MAE) from 44.81 ± 11.24 HU to 11.85 ± 4.31 HU and achieving an SSIM of 0.960 ± 0.055, comparable to state‐of‐the‐art diffusion models. Inference required only 6.42 ± 1.71 s per volume, compared to > 15 min for diffusion approaches. The model reduced severe metal and truncation artifacts, and representative qualitative assessment suggested visually consistent sCT generation under interfractional anatomical variation. Dosimetric assessment of complex HN IMRT plans yielded a high average gamma passing rate of 99.32 ± 0.56%.

Conclusions

HQ‐PatchNet provides a computationally efficient and clinically promising approach for daily CBCT‐guided online ART by improving CBCT‐to‐sCT image quality while maintaining rapid inference speed. Further contour‐based, multi‐institutional, and multi‐site validation remains necessary to confirm its broader clinical utility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Head and Neck NeoplasmsCone-Beam Computed TomographyImage Processing, Computer-AssistedRadiotherapy, Image-GuidedDeep LearningHumansReproducibility of ResultsProof of Concept Study

Stichwörter der Autor:innen

adaptive radiotherapycone‐beam computed tomography (CBCT)deep learningpatch‐based learningsynthetic CT

Autor:innen und Institutionen

  • Department of Radiation Oncology, Mayo Clinic, Jacksonville, Florida, USA.
  • Medical Physics and Biomedical Engineering Lab (MPBEL), Yonsei University College of Medicine, Seoul, South Korea.
  • Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, South Korea.
  • Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, New York, USA.
  • Ewha Medical Research Institute, School of Medicine, Ewha Womans University, Seoul, South Korea.
  • Ewha Medical Artificial Intelligence Research Institute, Ewha Womans University College of Medicine, Seoul, South Korea.

Förderung

  • Office of Governor Ron DeSantis, State of Florida (Governor DeSantis)
  • Korea Institute for Advancement of Technology
  • National Research Foundation of Korea

Zitieren

APA

Kim, J. H., Olberg, S., Choi, B. S., Yaddanapudi, S., Liang, X., Lu, B., Tan, J., Kim, J. S., Ahn, S. H., Furutani, K. M., Beltran, C. J., & Park, J. C. (2026). Reliability‐weighted patch learning for synthetic CT reconstruction in head and neck adaptive radiotherapy: A proof‐of‐concept study. Medical Physics, 53(11). https://doi.org/10.1002/mp.70684

Vancouver

Kim JH, Olberg S, Choi BS, Yaddanapudi S, Liang X, Lu B, et al. Reliability‐weighted patch learning for synthetic CT reconstruction in head and neck adaptive radiotherapy: A proof‐of‐concept study. Medical Physics. 2026;53(11). doi:10.1002/mp.70684

BibTeX
@article{Kim2026,
  author = {Kim, Jeong Heon and Olberg, Sven and Choi, Byong Su and Yaddanapudi, Sridhar and Liang, Xiaoying and Lu, Bo and Tan, Jun and Kim, Jin Sung and Ahn, So Hyun and Furutani, Keith M and Beltran, Chris J and Park, Justin C},
  title = {Reliability‐weighted patch learning for synthetic CT reconstruction in head and neck adaptive radiotherapy: A proof‐of‐concept study},
  journal = {Medical Physics},
  year = {2026},
  volume = {53},
  number = {11},
  doi = {10.1002/mp.70684}
}
Kostenlos starten →