.png){kind=icon}
返回
Seq2Morph: A deep learning deformable image registration algorithm for longitudinal imaging studies and adaptive radiotherapy
.png){kind=icon}
OA
AI
DOI：10.1002/mp.16026.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Purpose To simultaneously register all the longitudinal images acquired in a radiotherapy course for analyzing patients' anatomy changes for adaptive radiotherapy (ART). Methods To address the unique needs of ART, we designed Seq2Morph, a novel deep learning-based deformable image registration (DIR) network. Seq2Morph was built upon VoxelMorph which is a general-purpose framework for learning-based image registration. The major upgrades are (1) expansion of inputs to all weekly cone-beam computed tomography (CBCTs) acquired for monitoring treatment responses throughout a radiotherapy course, for registration to their planning CT; (2) incorporation of 3D convolutional long short-term memory between the encoder and decoder of VoxelMorph, to parse the temporal patterns of anatomical changes; and (3) addition of bidirectional pathways to calculate and minimize inverse consistency errors (ICEs). Longitudinal image sets from 50 patients, including a planning CT and 6 weekly CBCTs per patient, were utilized for network training and cross-validation. The outputs were deformation vector fields for all the registration pairs. The loss function was composed of a normalized cross-correlation for image intensity similarity, a DICE for contour similarity, an ICE, and a deformation regularization term. For performance evaluation, DICE and Hausdorff distance (HD) for the manual versus predicted contours of tumor and esophagus on weekly basis were quantified and further compared with other state-of-the-art algorithms, including conventional VoxelMorph and large deformation diffeomorphic metric mapping (LDDMM). Results Visualization of the hidden states of Seq2Morph revealed distinct spatiotemporal anatomy change patterns. Quantitatively, Seq2Morph performed similarly to LDDMM, but significantly outperformed VoxelMorph as measured by GTV DICE: (0.799 +/- 0.078, 0.798 +/- 0.081, and 0.773 +/- 0.078), and 50% HD (mm): (0.80 +/- 0.57, 0.88 +/- 0.66, and 0.95 +/- 0.60). The per-patient inference of Seq2Morph took 22 s, much less than LDDMM (similar to 30 min). Conclusions Seq2Morph can provide accurate and fast DIR for longitudinal image studies by exploiting spatial-temporal patterns. It closely matches the clinical workflow and has the potential to serve both online and offline ART.
Keyword:
adaptive radiotherapy
deep learning
deformable image
lung cancer
registration
期刊
IF:
3.2
论文数:
3.7W
被引数:
3.2W
机构
引用论文
Deformation driven Seq2Seq longitudinal tumor and organs-at-risk prediction for radiotherapy.png)
MEDICAL PHYSICS
OAAI
MEDICAL PHYSICSIF3.2
OAAI分享收藏Deep-learning-based image registration and automatic segmentation of organs-at-risk in cone-beam CT scans from high-dose radiation treatment of pancreatic cancerMEDICAL PHYSICSOAAI
MEDICAL PHYSICSIF3.2
OAAI分享收藏CycleMorph: Cycle consistent unsupervised deformable image registrationCycleMorph: 循环一致的无监督可变形图像配准MEDICAL IMAGE ANALYSISOAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAI分享收藏VoxelMorph: A Learning Framework for Deformable Medical Image RegistrationVoxelMorph: 可变形医学图像配准的学习框架
PREAI
分享收藏
查看更多内容