Yuhan Liu, Tianyu Fu, Qing Guo, Jingfan Fan, Hong Song, Yurong Jiang, Jian Yang
{"title":"Venous Tree Separation based on Local Feature","authors":"Yuhan Liu, Tianyu Fu, Qing Guo, Jingfan Fan, Hong Song, Yurong Jiang, Jian Yang","doi":"10.1145/3408127.3408202","DOIUrl":null,"url":null,"abstract":"The extraction of hepatic and portal vein structures from abdominal CT angiography (CTA) series plays an important role in the preoperative planning and intraoperative navigation of liver surgery. This study proposes a novel method for liver venous tree separation to solve touching hepatic and portal vessels. The proposed method initially focuses on extracting the connected minimal path. Intersections and bifurcation points are obtained through topologic analysis. Then, the proposed method analyzes the local features of breakpoints to separate the venous tree. Lastly, a blood flow direction-based branch completion for breakpoints is proposed to obtain more accurate vascular structures. The segmentation results of the hepatic and portal vein are reconstructed. Our method is tested on 19 clinical CTA series, and our method is demonstrated its effectiveness.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"64 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3408127.3408202","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The extraction of hepatic and portal vein structures from abdominal CT angiography (CTA) series plays an important role in the preoperative planning and intraoperative navigation of liver surgery. This study proposes a novel method for liver venous tree separation to solve touching hepatic and portal vessels. The proposed method initially focuses on extracting the connected minimal path. Intersections and bifurcation points are obtained through topologic analysis. Then, the proposed method analyzes the local features of breakpoints to separate the venous tree. Lastly, a blood flow direction-based branch completion for breakpoints is proposed to obtain more accurate vascular structures. The segmentation results of the hepatic and portal vein are reconstructed. Our method is tested on 19 clinical CTA series, and our method is demonstrated its effectiveness.