글로벌 연구동향
의학물리학
- 2024년 12월호
[Med Phys .] Generating 3D images of VMAT plans for predictive models and activation maps associated with plan deliverability방사선치료계획에서 예측 모델 및 활성화 맵을 위한 체적변조방사선치료(VMAT) 계획 3D 이미지 생성에 관한 연구연세의대, 서울의대/ 조현정, 김호진*, 이재성*
- 출처
- Med Phys .
- 등재일
- 2024 Oct
- 저널이슈번호
- 51(10):7415-7424.
- 내용
Abstract
Background: Intensity modulation with dynamic multi-leaf collimator (MLC) and monitor unit (MU) changes across control points (CPs) characterizes volumetric modulated arc therapy (VMAT). The increased uncertainty in plan deliverability required patient-specific quality assurance (PSQA), which remained inefficient upon Quality Assurance (QA) failure. To prevent waste before QA, plan complexity metrics (PCMs) and machine learning models with the metrics were generated, which were lack of providing CP-specific information upon QA failures.Purpose: By generating 3D images from digital imaging and comminications in medicine in radiation therapy (DICOM RT) plan, we proposed a predictive model that can estimate the deliverability of VMAT plans and visualize CP-specific regions associated with plan deliverability.
Methods: The patient cohort consisted of 259 and 190 cases for left- and right-breast VMAT treatments, which were split into 235 and 166 cases for training and 24 cases from each treatment for testing the networks. Three-channel 3D images generated from DICOM RT plans were fed into a DenseNet-based deep learning network. To reflect VMAT plan complexity as an image, the first two channels described MLC and MU variations between two consecutive CPs, while the last channel assigned the beam field size. The network output was defined as binary classified PSQA results, indicating deliverability. The predictive performance was assessed by accuracy, sensitivity, specificity, F1-score, and area under the curve (AUC). The gradient-weighted class activation map (Grad-CAM) highlighted the regions of CPs in VMAT plans associated with deliverability, compared against PCMs by Spearman correlation.
Results: The DenseNet-based predictive model yielded AUCs of 92.2% and 93.8%, F1-scores of 97.0% and 93.8% and accuracies of 95.8% and 91.7% for the left- and right-breast VMAT cases. Additionally, the specificity of 87.5% for both cases indicated that the predictive model accurately detected QA failing cases. The activation maps significantly differentiated QA failing-labeled from passing-labeled classes for the non-deliverable cases. The PCM with the highest correlation to the Grad-CAM varied from patient cases, implying that plan deliverability would be considered patient-specific.
Conclusion: This work demonstrated that the deep learning-based network based on visualization of dynamic VMAT plan information successfully predicted plan deliverability, which also provided control-point specific planning parameter information associated with plan deliverability in a patient-specific manner.
Affiliations
Hyeonjeong Cho 1 2, Jae Sung Lee 2, Jin Sung Kim 1, Deok Kim 1, Jee Suk Chang 1, Hwa Kyung Byun 3, Ik Jae Lee 1, Yong Bae Kim 1, Changhwan Kim 1, Ho Lee 1, Hojin Kim 1
1Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea.
2Department of Biomedical Sciences, Seoul National University College of Medicine, Seoul, Republic of Korea.
3Department of Radiation Oncology, Yongin Severance Hospital, Yonsei University College of Medicine, Gyonggi-do, Republic of Korea.
- 키워드
- class activation map (CAM); deep learning; plan deliverability; predictive model; visualizing plan information; volumetric modulated arc therapy (VMAT).
- 연구소개
- 본 연구에서는 VMAT 방사선 치료계획의 선량 전달가능성(deliverability)을 예측하기 위한 딥러닝 학습모델을 개발하고자 했습니다. 이를 위해 치료계획 데이터를 3D 영상으로 변환하고, 이를 딥러닝 네트워크의 입력으로 활용하는 새로운 예측모델을 제안했습니다. 치료계획 정보의 영상화를 통해 현재 주목받고 있는 영상 기반 딥러닝 네트워크와 결합한 예측모델을 구성하였으며, 나아가 학습된 예측모델을 통해 deliverability와 연관된 치료계획 변수를 활성화하여 사용자에게 피드백 정보를 제공하는 플랫폼을 구축할 수 있었습니다. 세기변조가 강한 left/right-breast VMAT 방사선치료 계획정보를 활용하여 모델 학습 및 테스트를 진행했고, 그 결과 AUC (Area Under the Curve) 가 90% 달하는 우수한 예측 성능을 달성할 수 있었습니다. 또한 치료계획과 deliverability 간의 상관관계를 시각화하여 환자맞춤형 deliverability 정보를 전달할 수 있었습니다. Deliverability와 관련된 다양한 연구가 진행되고 있는 의학물리분야에서 치료계획의 영상화 기법이 새로운 접근방식으로 자리잡을 가능성을 제시했으며, 이를 기반으로 한 후속 연구를 이어가고자 합니다.
- 덧글달기
- 이전글 [Phys Med Biol .] Dual convolution-transformer UNet (DCT-UNet) for organs at risk and clinical target volume segmentation in MRI for cervical cancer brachytherapy
- 다음글 [Med Phys .] Feasibility study for the development of multilayered solar cells for proton linear energy transfer depth profile measurement