A Comprehensive Analysis of Deformable Image Registration Methods for CT Imaging
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study aimed to assess the practical feasibility of advanced deformable image registration (DIR) algo- rithms in radiotherapy by employing two distinct datasets. The first dataset included 14 4D lung CT scans and 31 head and neck CT scans. In the 4D lung CT dataset, we employed the DIR algorithm to register organs at risk and tumors based on respiratory phases. The second dataset comprised pre-, mid-, and post-treatment CT images of the head and neck region, along with organ at risk and tumor delineations. These images underwent registration using the DIR algorithm, and Dice similarity coefficients (DSCs) were compared. In the 4D lung CT dataset, registration accuracy was evaluated for the spinal cord, lung, lung nodules, esophagus, and tumors. The average DSCs for the non-learning-based SyN and NiftyReg algorithms were 0.92±0.07 and 0.88±0.09, respectively. Deep learning methods, namely Voxelmorph, Cyclemorph, and Transmorph, achieved average DSCs of 0.90±0.07, 0.91±0.04, and 0.89±0.05, respectively. For the head and neck CT dataset, the average DSCs for SyN and NiftyReg were 0.82±0.04 and 0.79±0.05, respectively, while Voxelmorph, Cyclemorph, and Transmorph showed average DSCs of 0.80±0.08, 0.78±0.11, and 0.78±0.09, respectively. Additionally, the deep learning DIR algorithms demonstrated faster trans- formation times compared to other models, including commercial and conventional mathematical algorithms (Vox- elmorph: 0.36 sec/images, Cyclemorph: 0.3 sec/images, Transmorph: 5.1 sec/images, SyN: 140 sec/images, NiftyReg: 40.2 sec/images). In conclusion, this study highlights the varying clinical applicability of deep learning-based DIR methods in different anatomical regions. While challenges were encountered in head and neck CT registrations, 4D lung CT registrations exhibited favorable results, indicating the potential for clinical implementation. Further research and development in DIR algorithms tailored to specific anatomical regions are warranted to improve the overall clinical utility of these methods.
Abstract
This study aimed to assess the practical feasibility of advanced deformable image registration (DIR) algo- rithms in radiotherapy by employing two distinct datasets. The first dataset included 14 4D lung CT scans and 31 head and neck CT scans. In the 4D lung CT dataset, we employed the DIR algorithm to register organs at risk and tumors based on respiratory phases. The second dataset comprised pre-, mid-, and post-treatment CT images of the head and neck region, along with organ at risk and tumor delineations. These images underwent registration using the DIR algorithm, and Dice similarity coefficients (DSCs) were compared. In the 4D lung CT dataset, registration accuracy was evaluated for the spinal cord, lung, lung nodules, esophagus, and tumors. The average DSCs for the non-learning-based SyN and NiftyReg algorithms were 0.92±0.07 and 0.88±0.09, respectively. Deep learning methods, namely Voxelmorph, Cyclemorph, and Transmorph, achieved average DSCs of 0.90±0.07, 0.91±0.04, and 0.89±0.05, respectively. For the head and neck CT dataset, the average DSCs for SyN and NiftyReg were 0.82±0.04 and 0.79±0.05, respectively, while Voxelmorph, Cyclemorph, and Transmorph showed average DSCs of 0.80±0.08, 0.78±0.11, and 0.78±0.09, respectively. Additionally, the deep learning DIR algorithms demonstrated faster trans- formation times compared to other models, including commercial and conventional mathematical algorithms (Vox- elmorph: 0.36 sec/images, Cyclemorph: 0.3 sec/images, Transmorph: 5.1 sec/images, SyN: 140 sec/images, NiftyReg: 40.2 sec/images). In conclusion, this study highlights the varying clinical applicability of deep learning-based DIR methods in different anatomical regions. While challenges were encountered in head and neck CT registrations, 4D lung CT registrations exhibited favorable results, indicating the potential for clinical implementation. Further research and development in DIR algorithms tailored to specific anatomical regions are warranted to improve the overall clinical utility of these methods.
참고문헌 (19)
- Avants BB, "Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain", Medical image analysis, 12(1), pp.26~41 (2008)
- Yipeng Hu, "Barratt, Tom Vercauteren, Weakly-supervised convolutional neural networks for multimodal image registration", Medical image analysis, 49, pp.1~13 (2018)
- Rohé MM, "Pennec SVFNet:learning deformable image registration using shape matching", pp.266~274 (2017), Springer International Publishing
- Shen D, "Deep learning in medical image analysis", Annu, rev, of biomedical engineering, 19, pp.221~248 (2017)
- Jaderberg M, "Spatial transformer networks", Advances in neural information processing systems, 28 (2015)
- Balakrishnan G, "VoxelMorph: a learning framework for deformable medical image registration", IEEE transactions on medical imaging, 38(8), pp.1788~1800 (2019)
- De Vos BD, "A deep learning framework for unsupervised affine and deformable image registration", MIA, 52, pp.128~143 (2019)
- Clark K, "The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository", Journal of digital imaging, 26, pp.1045~1057 (2013)
- Bejarano T, "Head-andneck squamous cell carcinoma patients with CT taken during pre-treatment, mid-treatment, and post-treatment Dataset", The Cancer Imaging Archive, 10, pp.K9~ (2018)
- Modat M, "Fast free-form deformation using graphics processing units", Computer methods and programs in biomedicine, 98(3), pp.278~284 (2010)
- Kim, BA, "CycleMorph:cycle consistent unsupervised deformable image registration", Medical image analysis, 71, pp.102036~ (2021)
- Chen, "Transmorph:Transformer for unsupervised medical image registration", Medical image analysis, 82, pp.102615~ (2022)
- Yang, "Quicksilver:Fast predictive image registration a deep learning approach", NeuroImage, 158, pp.378~396 (2017)
- Sokooti H, "Nonrigid image registration using multi-scale 3D convolutional neural networks", pp.232~239 (2017), Springer International Publishing
- Adam Paszke, "Pytorch: An imperative style, highperformance deep learning library", Advances in neural information processing systems, 32 (2019)
- Pukala J, "Benchmarking of five commercial deformable image registration algorithms for head and neck patients", Journal of applied clinical medical physics, 17(3), pp.25~40 (2016)
- Varadhan R, "A framework for deformable image registration validation in radiotherapy clinical applications", Journal of applied clinical medical physics, 14(1), pp.192~213 (2013)
- Brock KK, "Use of image registration and fusion algorithms and techniques in radiotherapy: Report of the AAPM Radiation Therapy Committee Task Group No. 132", Medical physics, 44(7), pp.43~76 (2017)
- Balik S, "Evaluation of 4-dimensional computed tomography to 4-dimensional cone-beam computed tomography deformable image registration for lung cancer adaptive radiation therapy", International Journal of Radiation Oncology Biology Physics, 86(2), pp.372~379 (2013)