Development of Artificial Intelligence to Support Needle Electromyography Diagnostic Analysis
10.4258/hir.2019.25.2.131
- Author:
Sangwoo NAM
1
;
Min Kyun SOHN
;
Hyun Ah KIM
;
Hyoun Joong KONG
;
Il Young JUNG
Author Information
1. Department of Biomedical Engineering, Chungnam National University Graduade School, Daejeon, Korea.
- Publication Type:Original Article
- Keywords:
Artificial Intelligence;
Deep Learning;
Electromyography;
Convolutional Neural Network;
Classification
- MeSH:
Artificial Intelligence;
Boidae;
Classification;
Clinical Coding;
Electromyography;
Membrane Potentials;
Methods;
Needles
- From:Healthcare Informatics Research
2019;25(2):131-138
- CountryRepublic of Korea
- Language:English
-
Abstract:
OBJECTIVES: This study proposes a method for classifying three types of resting membrane potential signals obtained as images through diagnostic needle electromyography (EMG) using TensorFlow-Slim and Python to implement an artificial-intelligence-based image recognition scheme. METHODS: Waveform images of an abnormal resting membrane potential generated by diagnostic needle EMG were classified into three types—positive sharp waves (PSW), fibrillations (Fibs), and Others—using the TensorFlow-Slim image classification model library. A total of 4,015 raw waveform data instances were reviewed, with 8,576 waveform images subsequently collected for training. Images were learned repeatedly through a convolutional neural network. Each selected waveform image was classified into one of the aforementioned categories according to the learned results. RESULTS: The classification model, Inception v4, was used to divide waveform images into three categories (accuracy = 93.8%, precision = 99.5%, recall = 90.8%). This was done by applying the pretrained Inception v4 model to a fine-tuning method. The image recognition model was created for training using various types of image-based medical data. CONCLUSIONS: The TensorFlow-Slim library can be used to train and recognize image data, such as EMG waveforms, through simple coding rather than by applying TensorFlow. It is expected that a convolutional neural network can be applied to image data such as the waveforms of electrophysiological signals in a body based on this study.
