Diagnosis of left ventricular hypertrophy using convolutional neural network

• Published in: BMC medical informatics and decision making Vol. 20; no. 1; pp. 243 - 12
• Main Authors: Jian, Zini, Wang, Xianpei, Zhang, Jingzhe, Wang, Xinyu, Deng, Youbin
• Format: Journal Article
• Language: English
• Published: London BioMed Central 25.09.2020; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Accuracy; Algorithms; Artificial neural networks; Cardiology; Classification; Contours; Convolutional neural network; Deep Learning; Design; Diagnosis of left ventricular hypertrophy; Diagnostic systems; Disease; Echocardiography; Echocardiography - methods; Edge detection; Electrocardiography; Error analysis; Health Informatics; Heart; Heart hypertrophy; Heart Ventricles - diagnostic imaging; Humans; Hypertrophy; Hypertrophy, Left Ventricular - diagnostic imaging; Image processing; Image segmentation; Information Systems and Communication Service; machine learning; Management of Computing and Information Systems; Measurement methods; Medical diagnosis; Medical errors; Medical imaging; Medical imaging equipment; Medical prognosis; Medicine; Medicine & Public Health; modeling; Neural networks; Neural Networks, Computer; Patients; Physicians; Research Article; Shape; Streaming media; Target recognition; technology; Thickness measurement; Ultrasonic imaging; Ventricle; Video data; Wall thickness; Deep learning; Echocardiography; Diagnosis of left ventricular hypertrophy; Convolutional neural network
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-020-01255-2

Background Clinically, doctors obtain the left ventricular posterior wall thickness (LVPWT) mainly by observing ultrasonic echocardiographic video stream to capture a single frame of images with diagnostic significance, and then mark two key points on both sides of the posterior wall of the left ventricle with their own experience for computer measurement. In the actual measurement, the doctor’s selection point is subjective, and difficult to accurately locate the edge, which will bring errors to the measurement results. Methods In this paper, a convolutional neural network model of left ventricular posterior wall positioning was built under the TensorFlow framework, and the target region images were obtained after the positioning results were processed by non-local mean filtering and opening operation. Then the edge detection algorithm based on threshold segmentation is used. After the contour was extracted by adjusting the segmentation threshold through prior analysis and the OTSU algorithm, the design algorithm completed the computer selection point measurement of the thickness of the posterior wall of the left ventricle. Results The proposed method can effectively extract the left ventricular posterior wall contour and measure its thickness. The experimental results show that the relative error between the measurement result and the hospital measurement value is less than 15%, which is less than 20% of the acceptable repeatability error in clinical practice. Conclusions Therefore, the measurement method proposed in this paper has the advantages of less manual intervention, and the processing method is reasonable and has practical value.