Revealing Unforeseen Diagnostic Image Features With Deep Learning by Detecting Cardiovascular Diseases From Apical 4‐Chamber Ultrasounds

Journal of the American Heart Association, vol. 11, pp. e024168

Abstract

Background With the increase of highly portable, wireless, and low-cost ultrasound devices and automatic ultrasound acquisition techniques, an automated interpretation method requiring only a limited set of views as input could make preliminary cardiovascular disease diagnoses more accessible. In this study, we developed a deep learning method for automated detection of impaired left ventricular (LV) function and aortic valve (AV) regurgitation from apical 4-chamber ultrasound cineloops and investigated which anatomical structures or temporal frames provided the most relevant information for the deep learning model to enable disease classification. Methods and Results Apical 4-chamber ultrasounds were extracted from 3554 echocardiograms of patients with impaired LV function (n=928), AV regurgitation (n=738), or no significant abnormalities (n=1888). Two convolutional neural networks were trained separately to classify the respective disease cases against normal cases. The overall classification accuracy of the impaired LV function detection model was 86%, and that of the AV regurgitation detection model was 83%. Feature importance analyses demonstrated that the LV myocardium and mitral valve were important for detecting impaired LV function, whereas the tip of the mitral valve anterior leaflet, during opening, was considered important for detecting AV regurgitation. Conclusions The proposed method demonstrated the feasibility of a 3-dimensional convolutional neural network approach in detection of impaired LV function and AV regurgitation using apical 4-chamber ultrasound cineloops. The current study shows that deep learning methods can exploit large training data to detect diseases in a different way than conventionally agreed on methods, and potentially reveal unforeseen diagnostic image features.

Authors 7

1. Li‐Hsin Cheng corresponding Aachen Division of Image Processing Department of Radiology Leiden University Medical Center Leiden the Netherlands

   Leiden University Medical Center

   Affiliation as printed

   Division of Image Processing Department of Radiology Leiden University Medical Center Leiden the Netherlands

2. Pablo B. J. Bosch corresponding

   Vrije Universiteit Amsterdam

   Affiliation as printed

   Department of Science Vrije Universiteit Amsterdam Amsterdam the Netherlands

   Ynformed Utrecht the Netherlands

   Department of Science Vrije Universiteit Amsterdam Amsterdam the Netherlands; Ynformed Utrecht the Netherlands

3. Rutger F. H. Hofman

   Vrije Universiteit Amsterdam

   Affiliation as printed

   Department of Science Vrije Universiteit Amsterdam Amsterdam the Netherlands

4. Timo B. Brakenhoff
   Affiliation as printed

   Ynformed Utrecht the Netherlands

5. Eline F. Bruggemans Aachen Department of Cardiothoracic Surgery Leiden University Medical Center Leiden The Netherlands

   Leiden University Medical Center

   Affiliation as printed

   Department of Cardiothoracic Surgery Leiden University Medical Center Leiden the Netherlands

6. Rob J. van der Geest Aachen Division of Image Processing Department of Radiology Leiden University Medical Center Leiden the Netherlands

   Leiden University Medical Center

   Affiliation as printed

   Division of Image Processing Department of Radiology Leiden University Medical Center Leiden the Netherlands

7. Eduard R. Holman corresponding Aachen Department of Cardiology Leiden University Medical Center Leiden The Netherlands

   Leiden University Medical Center

   Affiliation as printed

   Department of Cardiology Leiden University Medical Center Leiden the Netherlands