PMID- 37651766 OWN - NLM STAT- MEDLINE DCOM- 20230927 LR - 20230927 IS - 1879-0534 (Electronic) IS - 0010-4825 (Linking) VI - 165 DP - 2023 Oct TI - An unsupervised dual contrastive learning framework for scatter correction in cone-beam CT image. PG - 107377 LID - S0010-4825(23)00842-9 [pii] LID - 10.1016/j.compbiomed.2023.107377 [doi] AB - PURPOSE: Cone-beam computed tomography (CBCT) is widely utilized in modern radiotherapy; however, CBCT images exhibit increased scatter artifacts compared to planning CT (pCT), compromising image quality and limiting further applications. Scatter correction is thus crucial for improving CBCT image quality. METHODS: In this study, we proposed an unsupervised contrastive learning method for CBCT scatter correction. Initially, we transformed low-quality CBCT into high-quality synthetic pCT (spCT) and generated forward projections of CBCT and spCT. By computing the difference between these projections, we obtained a residual image containing image details and scatter artifacts. Image details primarily comprise high-frequency signals, while scatter artifacts consist mainly of low-frequency signals. We extracted the scatter projection signal by applying a low-pass filter to remove image details. The corrected CBCT (cCBCT) projection signal was obtained by subtracting the scatter artifacts projection signal from the original CBCT projection. Finally, we employed the FDK reconstruction algorithm to generate the cCBCT image. RESULTS: To evaluate cCBCT image quality, we aligned the CBCT and pCT of six patients. In comparison to CBCT, cCBCT maintains anatomical consistency and significantly enhances CT number, spatial homogeneity, and artifact suppression. The mean absolute error (MAE) of the test data decreased from 88.0623 +/- 26.6700 HU to 17.5086 +/- 3.1785 HU. The MAE of fat regions of interest (ROIs) declined from 370.2980 +/- 64.9730 HU to 8.5149 +/- 1.8265 HU, and the error between their maximum and minimum CT numbers decreased from 572.7528 HU to 132.4648 HU. The MAE of muscle ROIs reduced from 354.7689 +/- 25.0139 HU to 16.4475 +/- 3.6812 HU. We also compared our proposed method with several conventional unsupervised synthetic image generation techniques, demonstrating superior performance. CONCLUSIONS: Our approach effectively enhances CBCT image quality and shows promising potential for future clinical adoption. CI - Copyright (c) 2023 Elsevier Ltd. All rights reserved. FAU - Wang, Tangsheng AU - Wang T AD - Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China; University of Chinese Academy of Sciences, Beijing 101408, China. Electronic address: ts.wang@siat.ac.cn. FAU - Liu, Xuan AU - Liu X AD - Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China. Electronic address: xuan.liu@siat.ac.cn. FAU - Dai, Jingjing AU - Dai J AD - Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China. Electronic address: jj.dai@siat.ac.cn. FAU - Zhang, Chulong AU - Zhang C AD - Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China. Electronic address: cl.zhang1@siat.ac.cn. FAU - He, Wenfeng AU - He W AD - Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China. Electronic address: wf.he@siat.ac.cn. FAU - Liu, Lin AU - Liu L AD - Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China; University of Chinese Academy of Sciences, Beijing 101408, China. Electronic address: lin.liu2@siat.ac.cn. FAU - Chan, Yinping AU - Chan Y AD - Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China. Electronic address: yp.chan@siat.ac.cn. FAU - He, Yutong AU - He Y AD - Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China. Electronic address: yt.he1@siat.ac.cn. FAU - Zhao, Hanqing AU - Zhao H AD - Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China; University of Chinese Academy of Sciences, Beijing 101408, China. Electronic address: hq.zhao@siat.ac.cn. FAU - Xie, Yaoqin AU - Xie Y AD - Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China. Electronic address: yq.xie@siat.ac.cn. FAU - Liang, Xiaokun AU - Liang X AD - Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China. Electronic address: xk.liang@siat.ac.cn. LA - eng PT - Journal Article PT - Research Support, Non-U.S. Gov't DEP - 20230815 PL - United States TA - Comput Biol Med JT - Computers in biology and medicine JID - 1250250 SB - IM MH - Humans MH - *Algorithms MH - *Cone-Beam Computed Tomography/methods MH - Artifacts MH - Image Processing, Computer-Assisted/methods MH - Phantoms, Imaging MH - Scattering, Radiation OTO - NOTNLM OT - CT reconstruction OT - Cone beam computed tomography OT - Contrastive learning OT - Shading correction COIS- Declaration of competing interest We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted. EDAT- 2023/09/01 00:41 MHDA- 2023/09/27 06:43 CRDT- 2023/08/31 18:00 PHST- 2023/04/02 00:00 [received] PHST- 2023/08/08 00:00 [revised] PHST- 2023/08/14 00:00 [accepted] PHST- 2023/09/27 06:43 [medline] PHST- 2023/09/01 00:41 [pubmed] PHST- 2023/08/31 18:00 [entrez] AID - S0010-4825(23)00842-9 [pii] AID - 10.1016/j.compbiomed.2023.107377 [doi] PST - ppublish SO - Comput Biol Med. 2023 Oct;165:107377. doi: 10.1016/j.compbiomed.2023.107377. Epub 2023 Aug 15.