Comparison of Deep Learning Techniques in Detection of Sickle Cell Disease

Abstract

Recently, transfer learning technique has proved to be powerful in enhancing development of deep learning methods for sickle cell disease (SCD) detection as a complement to the clinical method where a hemoglobin electrophoresis machine is used. This is evidenced by a number of models and algorithms with ≥90% prediction accuracy. From literature, most of the proposed methods are trained and tested on pre-trained deep learning models like VGG16, VGG19, ResNet, Inception_V3 and ReNet. However, training and testing of these methods are limited on one model and separate dataset which may lead to biased results due to implementation in variation of these models which affects results produced. To this end, there exists a need to evaluate the SCD models using the same dataset. Thus, in this research study, we carried out a comparative investigation and evaluated predominate pre-trained models used to detect SCD using the same dataset to ascertain which one has the best accuracy. We used secondary dataset obtained from an online dataset. In our study, we have discovered that Inception V3 yielded the highest accuracy of 97.3% followed by VGG19 at 97.0%, VGG16 at 91%, ResNet50 at 82% and ReNet at 67%, and the CNN-scratch model achieved 81% accuracy. Results from our study will aid researchers and industry practitioners to make decision on the best deep learning model to use while detecting SCD.