Your browser doesn't support javascript.
loading
Ultrasound image segmentation using Gamma combined with Bayesian model for focused-ultrasound-surgery lesion recognition.
Zhang, Quan; Liu, Xuan; Chang, Juntao; Lu, Mingzhu; Jing, Yanshu; Yang, Rongzhen; Sun, Weihao; Deng, Jie; Qi, Tingting; Wan, Mingxi.
Afiliação
  • Zhang Q; The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi' an Jiaotong University, Xi'an 710049, China.
  • Liu X; The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi' an Jiaotong University, Xi'an 710049, China.
  • Chang J; The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi' an Jiaotong University, Xi'an 710049, China.
  • Lu M; The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi' an Jiaotong University, Xi'an 710049, China. Electronic address: mzlu@mail.xjtu.edu.cn.
  • Jing Y; The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi' an Jiaotong University, Xi'an 710049, China.
  • Yang R; The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi' an Jiaotong University, Xi'an 710049, China.
  • Sun W; The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi' an Jiaotong University, Xi'an 710049, China.
  • Deng J; The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi' an Jiaotong University, Xi'an 710049, China.
  • Qi T; The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi' an Jiaotong University, Xi'an 710049, China.
  • Wan M; The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi' an Jiaotong University, Xi'an 710049, China.
Ultrasonics ; 134: 107103, 2023 Sep.
Article em En | MEDLINE | ID: mdl-37437399
This study aims to investigate the feasibility of combined segmentation for the separation of lesions from non-ablated regions, which allows surgeons to easily distinguish, measure, and evaluate the lesion area, thereby improving the quality of high-intensity focused-ultrasound (HIFU) surgery used for the non-invasive tumor treatment. Given that the flexible shape of the Gamma mixture model (GΓMM) fits the complex statistical distribution of samples, a method combining the GΓMM and Bayes framework is constructed for the classification of samples to obtain the segmentation result. An appropriate normalization range and parameters can be used to rapidly obtain a good performance of GΓMM segmentation. The performance values of the proposed method under four metrics (Dice score: 85%, Jaccard coefficient: 75%, recall: 86%, and accuracy: 96%) are better than those of conventional approaches including Otsu and Region growing. Furthermore, the statistical result of sample intensity indicates that the finding of the GΓMM is similar to that obtained by the manual method. These results indicate the stability and reliability of the GΓMM combined with the Bayes framework for the segmentation of HIFU lesions in ultrasound images. The experimental results show the possibility of combining the GΓMM with the Bayes framework to segment lesion areas and evaluate the effect of therapeutic ultrasound.
Assuntos
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Algoritmos / Hipertermia Induzida Tipo de estudo: Diagnostic_studies / Guideline / Prognostic_studies Idioma: En Revista: Ultrasonics Ano de publicação: 2023 Tipo de documento: Article País de afiliação: China

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Algoritmos / Hipertermia Induzida Tipo de estudo: Diagnostic_studies / Guideline / Prognostic_studies Idioma: En Revista: Ultrasonics Ano de publicação: 2023 Tipo de documento: Article País de afiliação: China