EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Personalized eye protection for head CT organ‐based tube current modulation: A deep learning approach to derive 3D eyeball models from a single‐view topogram

Xiaolin Meng, Lei Zhu, Shenghao Chen, Manhua Liu, Yang Wang

Journal of Applied Clinical Medical Physics · 2026-07 · 27 (7)

DOI: 10.1002/acm2.70665 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, online erschienen am 23.06.2026. Verfasst von Xiaolin Meng und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China. Hauptthemen laut MEDLINE: Deep Learning, Tomography, X-Ray Computed, Radiation Protection, Phantoms, Imaging. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Natural Science Foundation, Science and Technology Program of Guangzhou, Scientific Research Fund of the Medical Equipment Society of Guangdong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The lens of the eye is highly radiosensitive, yet personalized shielding during head CT remains challenging due to the lack of a rapid, pre‐scan localization method.

Purpose

To develop and validate a deep learning solution that enables automated, patient‐specific eye protection by generating a precise 3D eyeball model directly from a single‐view topogram.

Methods

Our two‐stage approach combines an advanced data simulation pipeline—which generates realistic training topograms from digitally reconstructed radiographs (DRRs) using a table‐movement‐aware model and CycleGAN‐based stylization—with a dedicated generative network (EyeGen‐Net). The model was trained on 400 synthetic and validated on 100 real clinical samples.

Results

EyeGen‐Net achieved a Dice Similarity Coefficient of 0.79 ± 0.08, a Hausdorff Distance of 5.40 ± 1.57 mm, and an Average Surface Distance of 1.84 ± 0.65 mm against expert segmentations. Crucially, phantom validation demonstrated that the derived 3D model facilitates organ‐based tube current modulation (OBTCM), yielding an approximate 30% reduction in lens dose across different scanning modes without compromising diagnostic image quality.

Conclusions

This work provides a practical, automated pathway for implementing personalized radioprotection in routine head CT, aligning with the ALARA (As Low As Reasonably Achievable) principle.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningTomography, X-Ray ComputedRadiation ProtectionPhantoms, ImagingImaging, Three-DimensionalRadiotherapy Planning, Computer-AssistedEyeImage Processing, Computer-AssistedHeadEye Protective DevicesHumansRadiotherapy DosageOrgans at RiskGenerative Adversarial Networks

Stichwörter der Autor:innen

deep learningeyeball model generationorgan‐based tube current modulation (OBTCM)radiation protectiontopogram

Autor:innen und Institutionen

  • School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
  • Healthcare Advanced Algorithm Department of HSW BU, Shanghai United Imaging Healthcare Co., Ltd, Shanghai, P.R. China.
  • Correction Algorithm Department of CT BU, Shanghai United Imaging Healthcare Co., Ltd, Shanghai, P.R. China.
  • MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China.
  • Department of Radiology, Zhujiang Hospital of Southern Medical University, Guangzhou, China.
  • Department of Radiology, Shanghai Tenth People's Hospital, Tongji University School of Medicine, Shanghai, China.

Förderung

  • Guangdong Natural Science Foundation
  • Science and Technology Program of Guangzhou
  • Scientific Research Fund of the Medical Equipment Society of Guangdong Province
  • Guangdong Basic and Applied Basic Research Foundation
  • Natural Science Foundation of Guangdong Province

Zitieren

APA

Meng, X., Zhu, L., Chen, S., Liu, M., & Wang, Y. (2026). Personalized eye protection for head CT organ‐based tube current modulation: A deep learning approach to derive 3D eyeball models from a single‐view topogram. Journal of Applied Clinical Medical Physics, 27(7). https://doi.org/10.1002/acm2.70665

Vancouver

Meng X, Zhu L, Chen S, Liu M, Wang Y. Personalized eye protection for head CT organ‐based tube current modulation: A deep learning approach to derive 3D eyeball models from a single‐view topogram. Journal of Applied Clinical Medical Physics. 2026;27(7). doi:10.1002/acm2.70665

BibTeX
@article{Meng2026,
  author = {Meng, Xiaolin and Zhu, Lei and Chen, Shenghao and Liu, Manhua and Wang, Yang},
  title = {Personalized eye protection for head CT organ‐based tube current modulation: A deep learning approach to derive 3D eyeball models from a single‐view topogram},
  journal = {Journal of Applied Clinical Medical Physics},
  year = {2026},
  volume = {27},
  number = {7},
  doi = {10.1002/acm2.70665}
}
Kostenlos starten →