Deep learn-based computer-assisted transthoracic echocardiography: approach to the diagnosis of cardiac amyloidosis

被引:1
|
作者
Zhang, Xiaofeng [1 ]
Liang, Tianyi [1 ]
Su, Chunxiao [1 ]
Qin, Shiyun [1 ]
Li, Jingtao [1 ]
Zeng, Decai [1 ]
Cai, Yongzhi [1 ]
Huang, Tongtong [1 ]
Wu, Ji [1 ]
机构
[1] Guangxi Med Univ, Affiliated Hosp 1, Dept Med Ultrason, 6 Shuangyong Rd, Nanning 530021, Peoples R China
来源
基金
中国国家自然科学基金;
关键词
Machine learning; Transthoracic echocardiography; Myocardial texture; Cardiac amyloidosis; Left ventricular hypertrophy; HYPERTROPHIC CARDIOMYOPATHY; ULTRASOUND IMAGES; RECOMMENDATIONS; RADIOMICS; SOCIETY;
D O I
10.1007/s10554-023-02806-0
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Myocardial amyloidosis (CA) differs from other etiological pathologies of left ventricular hypertrophy in that transthoracic echocardiography is challenging to assess the texture features based on human visual observation. There are few studies on myocardial texture based on echocardiography. Therefore, this paper proposes an adaptive machine learning method based on ultrasonic image texture features to identify CA. In this retrospective study, a total of 289 participants (50 cases of myocardial amyloidosis; Hypertrophic cardiomyopathy: 70 cases; Uremic cardiomyopathy: 92 cases; Hypertensive heart disease: 77 cases). We extracted the myocardial ultrasonic imaging features of these patients and screened the features, and four models of random forest (RF), support vector machine (SVM), logistic regression (LR) and gradient decision-making lifting tree (GBDT) were established to distinguish myocardial amyloidosis from other diseases. Finally, the diagnostic efficiency of the model was evaluated and compared with the traditional ultrasonic diagnostic methods. In the overall population, the four machine learning models we established could effectively distinguish CA from nonCA diseases, AUC (RF 0.77, SVM 0.81, LR 0.81, GBDT 0.71). The LR model had the best diagnostic efficiency with recall, F1-score, sensitivity and specificity of 0.21, 0.34, 0.21 and 1.0, respectively. Slightly better than the traditional ultrasonic diagnosis model. In further subgroup analysis, the myocardial amyloidosis group was compared one-by-one with the patients with hypertrophic cardiomyopathy, uremic cardiomyopathy, and hypertensive heart disease groups, and the same method was used for feature extraction and data modeling. The diagnostic efficiency of the model was further improved. Notably, in identifying of the CA group and HHD group, AUC values reached more than 0.92, accuracy reached more than 0.87, sensitivity equal to or greater than 0.81, specificity 0.91, and F1 score higher than 0.84. This novel method based on echocardiography combined with machine learning may have the potential to be used in the diagnosis of CA.
引用
收藏
页码:955 / 965
页数:11
相关论文
共 50 条
  • [21] CAD-PsorNet: deep transfer learning for computer-assisted diagnosis of skin psoriasis
    Chakraborty, Chandan
    Achar, Unmesh
    Nayek, Sumit
    Achar, Arun
    Mukherjee, Rashmi
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [22] A DEEP LEARNING COMPUTER-ASSISTED DIAGNOSIS AIDING PROGRAM WITH CT SCAN FOR SCREENING OF ASBESTOSIS
    Myong, Jun Pyo
    Song, Jae Seung
    Han, Sung Won
    RESPIROLOGY, 2019, 24 : 18 - 18
  • [23] Computer-Assisted Differential Diagnosis of Pyoderma Gangrenosum and Venous Ulcers with Deep Neural Networks
    Birkner, Mattias
    Schalk, Julia
    von den Driesch, Peter
    Schultz, Erwin S.
    JOURNAL OF CLINICAL MEDICINE, 2022, 11 (23)
  • [24] Computer-assisted diagnosis of early-stage lung adenocarcinoma using deep learning
    Trandafir, T.
    Wolf, J.
    Akram, F.
    Li, Y.
    Dingemans, A.
    Stubbs, A.
    von der Thusen, J.
    VIRCHOWS ARCHIV, 2022, 481 (SUPPL 1) : S81 - S81
  • [25] COMPUTER-ASSISTED MANAGEMENT OF CONSULTING PROJECTS - A RULE-BASED APPROACH
    KLEIN, J
    KONIG, W
    WIRTSCHAFTSINFORMATIK, 1992, 34 (05): : 494 - 508
  • [26] A multi-modal approach to computer-assisted deep brain stimulation trajectory planning
    Beriault, Silvain
    Al Subaie, Fahd
    Collins, D. Louis
    Sadikot, Abbas F.
    Pike, G. Bruce
    INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2012, 7 (05) : 687 - 704
  • [27] A multi-modal approach to computer-assisted deep brain stimulation trajectory planning
    Silvain Bériault
    Fahd Al Subaie
    D. Louis Collins
    Abbas F. Sadikot
    G. Bruce Pike
    International Journal of Computer Assisted Radiology and Surgery, 2012, 7 : 687 - 704
  • [28] A New Approach for Effective Retrieval of Medical Images: A Step towards Computer-Assisted Diagnosis
    Sharma, Suchita
    Aggarwal, Ashutosh
    JOURNAL OF IMAGING, 2024, 10 (09)
  • [29] Computer-assisted differential diagnosis of malignant mesothelioma based on syntactic structure analysis
    Weyn, B
    van de Wouwer, G
    Kumar-Singh, S
    van Daele, A
    Scheunders, P
    van Marck, E
    Jacob, W
    CYTOMETRY, 1999, 35 (01): : 23 - 29
  • [30] Computer-assisted Diagnosis of Dyschondrosteosis Based on Skeletal X-ray Geometry
    De Filippo, Gianpaolo
    Quintus, Fabien
    Hejblum, Gilles
    Bougneres, Pierre
    HORMONE RESEARCH IN PAEDIATRICS, 2016, 86 : 172 - 172