Geometry-encoded deep learning (GeoDL) framework for real-time 3D dose verification for online adaptive radiotherapy.
1/5 보강
[BACKGROUND] Accurate and efficient dose verification is vital for online adaptive radiotherapy (ART) while the patient is waiting on the treatment couch.
APA
Yan S, Maniscalco A, et al. (2025). Geometry-encoded deep learning (GeoDL) framework for real-time 3D dose verification for online adaptive radiotherapy.. Machine learning. Health, 1(1). https://doi.org/10.1088/3049-477x/adcb4b
MLA
Yan S, et al.. "Geometry-encoded deep learning (GeoDL) framework for real-time 3D dose verification for online adaptive radiotherapy.." Machine learning. Health, vol. 1, no. 1, 2025.
PMID
41477362 ↗
Abstract 한글 요약
[BACKGROUND] Accurate and efficient dose verification is vital for online adaptive radiotherapy (ART) while the patient is waiting on the treatment couch. Conventional methods are computationally intensive, limiting ART workflow efficiency and quality. A pilot study successfully illustrated the potential of geometry-encoded deep learning (GeoDL) algorithm for two-dimensional (2D) dose estimation on the central axial plane. This study investigates the feasibility of extending GeoDL for real-time dose verification for the entire three-dimensional (3D) volume of interest, fulfilling the unmet need in real clinical practice.
[METHODS] The proposed GeoDL unifies the representation of fluence maps (FMs) and CT images by resolving the treatment delivery geometry of a linear accelerator (LINAC) to ease the burden of learning the complex domain transformation between FMs and CT image. A carefully designed 3D U-Net was trained on the integrated CT-FM volume to estimate the 3D dose distribution for the entire volume of interest, utilizing a combined loss function focusing on prediction errors in both high and low dose regions. The model was trained and validated on 281 prostate cancer cases, with 24 additional cases employed for independent testing.
[RESULTS] The proposed GeoDL algorithm achieved highly accurate 3D dose estimation in almost real-time. The average γ passing rate ( , 10% threshold) for the estimated dose was 99.94% ± 0.15% on testing patients. The mean dose differences for the planning target volume (PTV) and organs at risk (OARs) were 0.93% ± 0.59% and 0.28% ± 0.32%, respectively. The average overall computational time for each testing case is ~35ms.
[CONCLUSION] This study demonstrates the feasibility of GeoDL in ultra-fast dose verification for ART, with strong performance in relevant dosimetric metrics across the entire volume of interest, positioning it as a valuable tool for real clinical use.
[METHODS] The proposed GeoDL unifies the representation of fluence maps (FMs) and CT images by resolving the treatment delivery geometry of a linear accelerator (LINAC) to ease the burden of learning the complex domain transformation between FMs and CT image. A carefully designed 3D U-Net was trained on the integrated CT-FM volume to estimate the 3D dose distribution for the entire volume of interest, utilizing a combined loss function focusing on prediction errors in both high and low dose regions. The model was trained and validated on 281 prostate cancer cases, with 24 additional cases employed for independent testing.
[RESULTS] The proposed GeoDL algorithm achieved highly accurate 3D dose estimation in almost real-time. The average γ passing rate ( , 10% threshold) for the estimated dose was 99.94% ± 0.15% on testing patients. The mean dose differences for the planning target volume (PTV) and organs at risk (OARs) were 0.93% ± 0.59% and 0.28% ± 0.32%, respectively. The average overall computational time for each testing case is ~35ms.
[CONCLUSION] This study demonstrates the feasibility of GeoDL in ultra-fast dose verification for ART, with strong performance in relevant dosimetric metrics across the entire volume of interest, positioning it as a valuable tool for real clinical use.
🏷️ 키워드 / MeSH 📖 같은 키워드 OA만
같은 제1저자의 인용 많은 논문 (5)
- The Prognostic Value of SERPINE1 in Clinical Outcomes in Head and Neck Squamous Cell Carcinoma: A Systematic Review and Meta-Analysis.
- Artificial intelligence (AI)-based multi-organ contour quality assurance with uncertainty estimation for online adaptive radiotherapy (oART).
- Postoperative infectious complications in gastric and colorectal cancer patients: A multicenter prospective cohort study from China.
- A theranostic endoperoxide agent with targeted singlet oxygen release and concomitant fluorescence signals.
- ITGA4 Contributes to 5-Fluorouracil Resistance by Up-Regulating PI3K/AKT Signaling: Evidence from Network Pharmacology, Molecular Docking and Experimental Verification.
🏷️ 같은 키워드 · 무료전문 — 이 논문 MeSH/keyword 기반
- Nanotechnology-Assisted Molecular Profiling: Emerging Advances in Circulating Tumor DNA Detection.
- Artificial intelligence and breast cancer screening in Serbia: a dual-perspective qualitative study among radiologists and screening-aged women.
- LCMS-Net: Deep Learning for Raw High Resolution Mass Spectrometry Data Applied to Forensic Cause-of-Death Screening.
- PIBAdb: a public cohort of multimodal colonoscopy videos and images including polyps with histological information.
- Aesthetically ideal noses created using a single artificial intelligence model: Validating literature and exploring ethnic differences.
- Integrative Computational Approaches to Prostate Cancer with Conditional Reprogramming and AI-Driven Precision Medicine.