Automatically detecting pathological voice disorders such as vocal cord paralysis or Reinke's edema is a challenging and important medical classification problem. While deep learning techniques have achieved significant progress in the speech recognition field there has been less research work in the area of pathological voice disorders detection. A novel system for pathological voice detection using convolutional neural network (CNN) as the basic architecture is presented in this work. The novel system uses spectrograms of normal and pathological speech recordings as the input to the network. Initially Convolutional deep belief network (CDBN) are used to pre-train the weights of CNN system. This acts as a generative model to explore the structure of the input data using statistical methods. Then a CNN is trained using supervised back-propagation learning algorithm to fine tune the weights. It will be shown that a small amount of data can be used to achieve good results in classification with this deep learning approach. A performance analysis of the novel method is provided using real data from the Saarbrucken Voice database.

Acoustic analysis using signal processing tools can be used to extract voice features to distinguish whether a voice is pathological or healthy. The proposed work uses spectrogram of voice recordings from a voice database as the input to a Convolutional Neural Network (CNN) for automatic feature extraction and classification of disordered and normal voice. The novel classifier achieved 88.5%, 66.2% and 77.0% accuracy on training, validation and testing data set respectively on 482 normal and 482 organic dysphonia speech files. It reveals that the proposed novel algorithm on the Saarbruecken Voice Database can effectively been used for screening pathological voice recordings.

There is increasing focus on applying deep learning methods to electrocardiograms (ECGs), with recent studies showing that neural networks (NNs) can predict future heart failure or atrial fibrillation from the ECG alone. However, large numbers of ECGs are needed to train NNs, and many ECGs are currently only in paper format, which are not suitable for NN training. We developed a fully-automated online ECG digitisation tool to convert scanned paper ECGs into digital signals. Using automated horizontal and vertical anchor point detection, the algorithm automatically segments the ECG image into separate images for the 12 leads and a dynamical morphological algorithm is then applied to extract the signal of interest. We then validated the performance of the algorithm on 515 digital ECGs, of which 45 were printed, scanned and redigitised. The automated digitisation tool achieved 99.0% correlation between the digitised signals and the ground truth ECG (n = 515 standard 3-by-4 ECGs) after excluding ECGs with overlap of lead signals. Without exclusion, the performance of average correlation was from 90 to 97% across the leads on all 3-by-4 ECGs. There was a 97% correlation for 12-by-1 and 3-by-1 ECG formats after excluding ECGs with overlap of lead signals. Without exclusion, the average correlation of some leads in 12-by-1 ECGs was 60–70% and the average correlation of 3-by-1 ECGs achieved 80–90%. ECGs that were printed, scanned, and redigitised, our tool achieved 96% correlation with the original signals. We have developed and validated a fully-automated, user-friendly, online ECG digitisation tool. Unlike other available tools, this does not require any manual segmentation of ECG signals. Our tool can facilitate the rapid and automated digitisation of large repositories of paper ECGs to allow them to be used for deep learning projects.

No abstract

No abstract