Your browser doesn't support javascript.
loading
A Deep Learning-based Method to Extract Lumen and Media-Adventitia in Intravascular Ultrasound Images.
Zhu, Fubao; Gao, Zhengyuan; Zhao, Chen; Zhu, Hanlei; Nan, Jiaofen; Tian, Yanhui; Dong, Yong; Jiang, Jingfeng; Feng, Xiaohong; Dai, Neng; Zhou, Weihua.
Afiliação
  • Zhu F; School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, Henan, China.
  • Gao Z; School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, Henan, China.
  • Zhao C; Department of Applied Computing, Michigan Technological University, Houghton, MI, USA.
  • Zhu H; School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, Henan, China.
  • Nan J; School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, Henan, China.
  • Tian Y; School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, Henan, China.
  • Dong Y; Department of Cardiology, The 7th People's Hospital of Zhengzhou, Zhengzhou, Henan, China.
  • Jiang J; Department of Biomedical Engineering, Michigan Technological University, Houghton, MI, USA.
  • Feng X; Department of Pediatrics, Yicheng Maternity and Child Health Care Hospital, Yicheng, Hubei, China.
  • Dai N; Department of Cardiology, Zhongshan Hospital, Fudan University, Shanghai Institute of Cardiovascular Diseases, Shanghai, China.
  • Zhou W; National Clinical Research Center for Interventional Medicine, Shanghai, China.
Ultrason Imaging ; 44(5-6): 191-203, 2022 11.
Article em En | MEDLINE | ID: mdl-35861418
Intravascular ultrasound (IVUS) imaging allows direct visualization of the coronary vessel wall and is suitable for assessing atherosclerosis and the degree of stenosis. Accurate segmentation and lumen and median-adventitia (MA) measurements from IVUS are essential for such a successful clinical evaluation. However, current automated segmentation by commercial software relies on manual corrections, which is time-consuming and user-dependent. We aim to develop a deep learning-based method using an encoder-decoder deep architecture to automatically and accurately extract both lumen and MA border. Inspired by the dual-path design of the state-of-the-art model IVUS-Net, our method named IVUS-U-Net++ achieved an extension of the U-Net++ model. More specifically, a feature pyramid network was added to the U-Net++ model, enabling the utilization of feature maps at different scales. Following the segmentation, the Pearson correlation and Bland-Altman analyses were performed to evaluate the correlations of 12 clinical parameters measured from our segmentation results and the ground truth. A dataset with 1746 IVUS images from 18 patients was used for training and testing. Our segmentation model at the patient level achieved a Jaccard measure (JM) of 0.9080 ± 0.0321 and a Hausdorff distance (HD) of 0.1484 ± 0.1584 mm for the lumen border; it achieved a JM of 0.9199 ± 0.0370 and an HD of 0.1781 ± 0.1906 mm for the MA border. The 12 clinical parameters measured from our segmentation results agreed well with those from the ground truth (all p-values are smaller than .01). Our proposed method shows great promise for its clinical use in IVUS segmentation.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Túnica Adventícia / Aprendizado Profundo Tipo de estudo: Diagnostic_studies / Guideline Limite: Humans Idioma: En Revista: Ultrason Imaging Ano de publicação: 2022 Tipo de documento: Article País de afiliação: China

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Túnica Adventícia / Aprendizado Profundo Tipo de estudo: Diagnostic_studies / Guideline Limite: Humans Idioma: En Revista: Ultrason Imaging Ano de publicação: 2022 Tipo de documento: Article País de afiliação: China