A novel registration‐based algorithm for prostate segmentation via the combination of SSM and CNN. Issue 8 (11th May 2022)

• Record Type: Journal Article
• Authors: Qin, Chunxia; Tu, Puxun; Chen, Xiaojun; Troccaz, Jocelyne
• Is Part Of: Medical physics. Volume 49:Issue 8(2022)
• Page Start: 5268
• Page End: 5282
• Publication Date: 2022-05-11
• Subjects: boundary distance map -- probability map -- registration‐based segmentation -- statistical shape model; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1002/mp.15698
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract: Purpose: Precise determination of target is an essential procedure in prostate interventions, such as prostate biopsy, lesion detection, and targeted therapy. However, the prostate delineation may be tough in some cases due to tissue ambiguity or lack of partial anatomical boundary. In this study, we propose a novel supervised registration‐based algorithm for precise prostate segmentation, which combines the convolutional neural network (CNN) with a statistical shape model (SSM). Methods: The proposed network mainly consists of two branches. One called SSM‐Net branch was exploited to predict the shape transform matrix, shape control parameters, and shape fine‐tuning vector, for the generation of the prostate boundary. Furthermore, according to the inferred boundary, a normalized distance map was calculated as the output of SSM‐Net. Another branch named ResU‐Net was employed to predict a probability label map from the input images at the same time. Integrating the output of these two branches, the optimal weighted sum of the distance map and the probability map was regarded as the prostate segmentation. Results: Two public data sets PROMISE12 and NCI‐ISBI 2013 were utilized to evaluate the performance of the proposed algorithm. The results demonstrated that the segmentation algorithm achieved the best performance with an SSM of 9500 nodes, which obtained a dice of 0.907 and an average surface distance of 1.85 mm. Compared with other methods, our algorithm delineates the prostate region more accurately and efficiently. In addition, we verified the impact of model elasticity augmentation and the fine‐tuning item on the network segmentation capability. As a result, both factors have improved the delineation accuracy, with dice increased by 10% and 7%, respectively. Conclusions: Our segmentation method has the potential to be an effective and robust approach for prostate segmentation.