{"title":"A hybrid segmentation approach for rapid and reliable liver volumetric analysis in daily clinical practice","authors":"Zygomalas Apollon, Karavias Dionissios, Koutsouris Dimitrios, Maroulis Ioannis, Karavias D. Dimitrios, Giokas Konstantinos, Megalooikonomou Vasileios","doi":"10.1109/BIBE.2015.7367715","DOIUrl":null,"url":null,"abstract":"Preoperative evaluation of liver future remnant volume is essential for liver oncologic and transplantation surgery. Segmentation of liver imaging studies allow for an excellent liver volumetric analysis. We developed a hybrid liver segmentation algorithm which is based on thresholding by pixel intensity value. The algorithm consists of a semiautomatic and an automatic part. The aim of this prospective study was to evaluate the efficacy of preoperative liver volumetric analysis in daily clinical practice using this hybrid approach. Accuracy and speed were validated on a random prospectively selected sample of 20 patients undergoing elective major liver resections at our institution from June 2013 to June 2015. Complete liver volumetric analysis was performed in average in 15.5 min/dataset SD±2.6 (computation and interaction time). Mean similarity index was 95.5% SD±2. The future liver remnant volume calculated by the application showed a correlation of 0.98 to that calculated using manual boundary tracing. The hybrid segmentation approach proved to be fast and accurate for the preoperative planning in oncologic liver surgery.","PeriodicalId":422807,"journal":{"name":"2015 IEEE 15th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"124 3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 IEEE 15th International Conference on Bioinformatics and Bioengineering (BIBE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BIBE.2015.7367715","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
Preoperative evaluation of liver future remnant volume is essential for liver oncologic and transplantation surgery. Segmentation of liver imaging studies allow for an excellent liver volumetric analysis. We developed a hybrid liver segmentation algorithm which is based on thresholding by pixel intensity value. The algorithm consists of a semiautomatic and an automatic part. The aim of this prospective study was to evaluate the efficacy of preoperative liver volumetric analysis in daily clinical practice using this hybrid approach. Accuracy and speed were validated on a random prospectively selected sample of 20 patients undergoing elective major liver resections at our institution from June 2013 to June 2015. Complete liver volumetric analysis was performed in average in 15.5 min/dataset SD±2.6 (computation and interaction time). Mean similarity index was 95.5% SD±2. The future liver remnant volume calculated by the application showed a correlation of 0.98 to that calculated using manual boundary tracing. The hybrid segmentation approach proved to be fast and accurate for the preoperative planning in oncologic liver surgery.