A feasible method to evaluate deformable image registration with deep learning–based segmentation. (March 2022)

• Record Type: Journal Article
• Authors: Yang, Bining; Chen, Xinyuan; Li, Jingwen; Zhu, Ji; Men, Kuo; Dai, Jianrong
• Is Part Of: Physica medica. Volume 95(2022)
• Page Start: 50
• Page End: 56
• Publication Date: 2022-03
• Subjects: Imaging registration -- Quantitative evaluation -- Deep learning; Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2022.01.006
• Languages: English
• ISSNs: 1120-1797

Abstract

Highlights: A deformable registration evaluation method based on deep learning segmentation. It reflects the registration accuracy in concerned areas quantitatively. It reduced time-consuming comparing with conventional methods. The decision criteria for each ROI were established by statistical information. Abstract: Purpose: We have developed a feasible method to evaluate deformable image registration using deep learning (DL)–based segmentation. Methods: Eighty patients with nasopharyngeal carcinoma were enrolled in this study. Two sets of fixed and moving computed tomography images acquired from each patient were input into the DL segmentation model to generate nine anatomic regions of interest (ROIs) separately and automatically. The ROIs generated in moving images were transferred to the fixed images using the registration transformation metric. The registration evaluation indexes, including the Dice similarity coefficient, derived from 60 well-registrated cases were then used to develop criteria for decision making. A double-blind study was performed to test the proposed method on quality assurance (QA) for image registration on a new test data set of 20 cases. Results: The values of evaluation indexes generated by our automated evaluation method were quite consistent with those from the manual method; however, the proposed method could save about 116 min per patient on average. The QA method achieved promising image registration error detection, with the following metrics for the nine ROIs: balanced accuracy, 0.946 ± 0.029; sensitivity, 0.959 ± 0.021; and specificity, 0.933 ± 0.050. Conclusions: The proposed method could potentially evaluate the deformable registration accuracy of specific areas. The preliminary NPC result shows that it has consistent performance with the conventional evaluation method with higher efficiency.