Automated detection of diabetic subject using pre-trained 2D-CNN models with frequency spectrum images extracted from heart rate signals. (October 2019)

• Record Type: Journal Article
• Authors: Yildirim, Ozal; Talo, Muhammed; Ay, Betul; Baloglu, Ulas Baran; Aydin, Galip; Acharya, U. Rajendra
• Is Part Of: Computers in biology and medicine. Volume 113(2019)
• Publication Date: 2019-10
• Subjects: Diabetes mellitus -- Heart rate signals -- Deep learning -- Transfer learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2019.103387
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: In this study, a deep-transfer learning approach is proposed for the automated diagnosis of diabetes mellitus (DM), using heart rate (HR) signals obtained from electrocardiogram (ECG) data. Recent progress in deep learning has contributed significantly to improvement in the quality of healthcare. In order for deep learning models to perform well, large datasets are required for training. However, a difficulty in the biomedical field is the lack of clinical data with expert annotation. A recent, commonly implemented technique to train deep learning models using small datasets is to transfer the weighting, developed from a large dataset, to the current model. This deep learning transfer strategy is generally employed for two-dimensional signals. Herein, the weighting of models pre-trained using two-dimensional large image data was applied to one-dimensional HR signals. The one-dimensional HR signals were then converted into frequency spectrum images, which were utilized for application to well-known pre-trained models, specifically: AlexNet, VggNet, ResNet, and DenseNet. The DenseNet pre-trained model yielded the highest classification average accuracy of 97.62%, and sensitivity of 100%, to detect DM subjects via HR signal recordings. In the future, we intend to further test this developed model by utilizing additional data along with cloud-based storage to diagnose DM via heart signal analysis. Highlights: A deep-transfer learning approach was proposed for automated diagnosis of diabetes mellitus. The HR signals were converted into frequency spectrum images. Well-known 2D-CNN models were applied on the spectrogram images. Classification performance was improved on small HR signals (71 DM and 71 health) via transferring 2D-CNN weights. High classification performance was obtained with 97.62% accuracy and 100% sensitivity.