WSEAS Transactions on Computer Research
Print ISSN: 1991-8755, E-ISSN: 2415-1521
Volume 9, 2021
Ηyper-sinh-Convolutional Neural Network for Early Detection of Parkinson’s Disease from Spiral Drawings
Authors: , , ,
Abstract: Modern developments in the state-of-the-art open-source activation functions for Convolutional NeuralNetworks (CNNs) have broadened the selection of benchmark activations for Deep Learning (DL)-aidedclassification. Nevertheless, achieving discrimination of non-linear input image data in CNN is still notstraightforward and it is unclear how such novel activation functions can have translational applications withtangible impact. hyper-sinh, made freely available in TensorFlow and Keras, was demonstrated as a benchmarkactivation function on five (N=5) datasets in its ground-breaking paper. Measuring the value from deploying thisactivation in a specific application is pivotal to supply the required evidence of its performance on real-lifesupervised DL-based image classification tasks. In this study, a CNN was for the first time combined with hypersinh to aid early detection of Parkinson’s Disease (PD) from discriminating pathophysiological patterns extractedfrom spiral drawings. Thus, the hyper-sinh activation was deployed to maximise the separability of the inputfeatures from spiral drawings via automated pattern recognition. We demonstrate the accuracy and reliability ofhyper-sinh-CNN to aid early diagnosis of PD, evaluated against other gold standard activation functions, includingthe recent Quantum ReLU (QReLU) and the modified Quantum ReLU (m-QReLU) that solved the ‘dying ReLU’problem for the first time in the literature of DL. Two (N=2) benchmark datasets from the database of the BotucatuMedical School, São Paulo State University in Brazil, scaled to be in 28 by 28 pixels as the MNIST benchmarkdata, were used to discriminate between input image patterns of 158 subjects (53 healthy controls and 105 patientswith PD) from spirals drawn on graphics tablets. Overtraining was avoided via early stopping and the models weredeveloped and tested in TensorFlow and Keras (Python 3.6). The supervised model (hyper-sinh-CNN) could detectearly Parkinson’s Disease with 81% and 91% classification accuracy from the two datasets respectively (F1-scores:73% and 91% correspondingly). Furthermore, the model achieved high sensitivity (81% and 91%). Thus, this studyvalidates the application of hyper-sinh to aid real-life supervised DL-based image classification, in particular earlydiagnosis of PD from spiral drawings.
Search Articles
Pages: 1-7
DOI: 10.37394/232018.2021.9.1