Deep Learning Based Automatic Left Ventricle Segmentation from the Transgastric Short-Axis View on Transesophageal Echocardiography: A Feasibility Study

被引:0
|
作者
Tian, Yuan [1 ]
Qin, Wenting [2 ]
Zhao, Zihang [2 ]
Wang, Chunrong [1 ]
Tian, Yajie [1 ]
Zhang, Yuelun [1 ]
He, Kai [1 ]
Zhang, Yuguan [1 ]
Shen, Le [1 ]
Zhou, Zhuhuang [2 ]
Yu, Chunhua [1 ]
机构
[1] Chinese Acad Med Sci & Peking Union Med Coll, Peking Union Med Coll Hosp, Dept Anesthesiol, Beijing 100730, Peoples R China
[2] Beijing Univ Technol, Coll Chem & Life Sci, Dept Biomed Engn, Beijing 100124, Peoples R China
关键词
transesophageal echocardiography; deep learning; left ventricle segmentation; transgastric short-axis view; convolutional neural network; ULTRASOUND; SURGERY;
D O I
10.3390/diagnostics14151655
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Segmenting the left ventricle from the transgastric short-axis views (TSVs) on transesophageal echocardiography (TEE) is the cornerstone for cardiovascular assessment during perioperative management. Even for seasoned professionals, the procedure remains time-consuming and experience-dependent. The current study aims to evaluate the feasibility of deep learning for automatic segmentation by assessing the validity of different U-Net algorithms. A large dataset containing 1388 TSV acquisitions was retrospectively collected from 451 patients (32% women, average age 53.42 years) who underwent perioperative TEE between July 2015 and October 2023. With image preprocessing and data augmentation, 3336 images were included in the training set, 138 images in the validation set, and 138 images in the test set. Four deep neural networks (U-Net, Attention U-Net, UNet++, and UNeXt) were employed for left ventricle segmentation and compared in terms of the Jaccard similarity coefficient (JSC) and Dice similarity coefficient (DSC) on the test set, as well as the number of network parameters, training time, and inference time. The Attention U-Net and U-Net++ models performed better in terms of JSC (the highest average JSC: 86.02%) and DSC (the highest average DSC: 92.00%), the UNeXt model had the smallest network parameters (1.47 million), and the U-Net model had the least training time (6428.65 s) and inference time for a single image (101.75 ms). The Attention U-Net model outperformed the other three models in challenging cases, including the impaired boundary of left ventricle and the artifact of the papillary muscle. This pioneering exploration demonstrated the feasibility of deep learning for the segmentation of the left ventricle from TSV on TEE, which will facilitate an accelerated and objective alternative of cardiovascular assessment for perioperative management.
引用
收藏
页数:15
相关论文
共 50 条
  • [21] Evaluation of a Semi-automatic Right Ventricle Segmentation Method on Short-Axis MR Images
    Pinar Yilmaz
    Karel Wallecan
    Wisnumurti Kristanto
    Jean-Paul Aben
    Adriaan Moelker
    Journal of Digital Imaging, 2018, 31 : 670 - 679
  • [22] Deep learning network for fully automatic left ventricle segmentation
    Rostami, Maryam Talebi
    Raie, Abolghasem Asadollah
    2018 4TH IRANIAN CONFERENCE ON SIGNAL PROCESSING AND INTELLIGENT SYSTEMS (ICSPIS), 2018, : 141 - 144
  • [23] AUTOMATIC ANALYSIS OF LEFT VENTRICLE WALL THICKNESS USING SHORT-AXIS CINE CMR IMAGES
    Khalifa, F.
    Beache, G. M.
    Nitzken, M.
    Gimel'farb, G.
    Giridharan, G.
    El-Baz, A.
    2011 8TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO, 2011, : 1306 - 1309
  • [24] Integrated approach for fully automatic left ventricle segmentation using adaptive iteration based parametric model with deep learning in short axis cardiac MRI
    Bhan A.
    Mangipudi P.
    Journal of Ambient Intelligence and Humanized Computing, 2023, 14 (08) : 11071 - 11092
  • [25] Automatic Segmentation of Left Ventricle in Cardiac Cine MRI Images Based on Deep Learning
    Zhou, Tian
    Icke, Ilknur
    Dogdas, Belma
    Parimal, Sarayu
    Sampath, Smita
    Forbes, Joseph
    Bagchi, Ansuman
    Chin, Chih-Liang
    Chen, Antong
    MEDICAL IMAGING 2017: IMAGE PROCESSING, 2017, 10133
  • [26] Left ventricle segmentation in transesophageal echocardiography based on centripetal catmull-rom curve
    Ji X.
    Gao S.
    Huang Z.
    Fu Z.
    1600, Sichuan University (48): : 84 - 90
  • [27] 3D Segmentation of the Left Ventricle Combining Long- and Short-axis MR Images
    Saering, D.
    Relan, J.
    Groth, M.
    Muellerleile, K.
    Handels, H.
    METHODS OF INFORMATION IN MEDICINE, 2009, 48 (04) : 340 - 343
  • [28] MFP-Unet: A novel deep learning based approach for left ventricle segmentation in echocardiography
    Moradi, Shakiba
    Oghli, Mostafa Ghelich
    Alizadehasl, Azin
    Shiri, Isaac
    Oveisi, Niki
    Oveisi, Mehrdad
    Maleki, Majid
    Dhooge, Jan
    PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS, 2019, 67 : 58 - 69
  • [29] Convolutional neural network regression for short-axis left ventricle segmentation in cardiac cine MR sequences
    Tan, Li Kuo
    Liew, Yih Miin
    Lim, Einly
    McLaughlin, Robert A.
    MEDICAL IMAGE ANALYSIS, 2017, 39 : 78 - 86
  • [30] Segmentation of Left Ventricle in 2D Echocardiography Using Deep Learning
    Azarmehr, Neda
    Ye, Xujiong
    Sacchi, Stefania
    Howard, James P.
    Francis, Darrel P.
    Zolgharni, Massoud
    MEDICAL IMAGE UNDERSTANDING AND ANALYSIS, MIUA 2019, 2020, 1065 : 497 - 504