Milica Badža Atanasijević, Tijana Radović, M. Janković, M. Barjaktarović
{"title":"Open-Source Application for Mri and Ct Registration Using Homography Transformation","authors":"Milica Badža Atanasijević, Tijana Radović, M. Janković, M. Barjaktarović","doi":"10.1145/3569192.3569210","DOIUrl":null,"url":null,"abstract":"Medical imaging is substantial in diagnosing and treatment of various types of diseases, however, a single modality may not be sufficient. Therefore, gathering more than one imaging modality to provide additional information is needed. Thus, an open-source application for the registration of the two medical imaging modalities using a homography transformation was implemented. Using homography, the mapping of the points of the magnetic resonance image to the corresponding points of the computer tomography image was performed. The application enables the radiologist to finely adjust the two modalities by moving the homography points and performing isometric transformations on the slices. The usage of the developed open-source application was evaluated by one experienced radiologist, and calculating the mutual information (MI) on the data of the axial plane from three pediatric patients (8.33±4.19 years), collected from the University Children's Hospital, Belgrade, Serbia. The radiologist adjusted the registered images until a satisfactory level of alignment was achieved, and the increase of the initial MI∼0.65 ranging from 0.17 to 0.23 was achieved. The developed software, based on the homography transformations combined with feedback in the form of MI, a simple graphical interface, and an open-source implementation enable its easy use in everyday clinical practice.","PeriodicalId":249004,"journal":{"name":"Proceedings of the 9th International Conference on Bioinformatics Research and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 9th International Conference on Bioinformatics Research and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3569192.3569210","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
Medical imaging is substantial in diagnosing and treatment of various types of diseases, however, a single modality may not be sufficient. Therefore, gathering more than one imaging modality to provide additional information is needed. Thus, an open-source application for the registration of the two medical imaging modalities using a homography transformation was implemented. Using homography, the mapping of the points of the magnetic resonance image to the corresponding points of the computer tomography image was performed. The application enables the radiologist to finely adjust the two modalities by moving the homography points and performing isometric transformations on the slices. The usage of the developed open-source application was evaluated by one experienced radiologist, and calculating the mutual information (MI) on the data of the axial plane from three pediatric patients (8.33±4.19 years), collected from the University Children's Hospital, Belgrade, Serbia. The radiologist adjusted the registered images until a satisfactory level of alignment was achieved, and the increase of the initial MI∼0.65 ranging from 0.17 to 0.23 was achieved. The developed software, based on the homography transformations combined with feedback in the form of MI, a simple graphical interface, and an open-source implementation enable its easy use in everyday clinical practice.