On Improving Malaria Parasite Detection from Microscopic Images: A Comparative Analytics of Hybrid Deep Learning Models

Malaria, a life-threatening mosquito-borne disease, contributes to a significantly high number of fatalities in tropical/sub-tropical regions due to inadequate detection technology, lack of laboratory experience, and other barriers. From the design perspective of a general-purpose point-of-care solution for detecting malaria along with other tropical diseases, malaria parasite detection from blood work needs to integrate accurate and fast detection capabilities. In this vein, in this paper, we develop three hybrid data-driven models in this paper that combine a convolutional neural network (CNN) with long short-term memory (LSTM), bi-directional LSTM (BiLSTM), and gated recurrent unit (GRU), respectively. CNN is employed in all three proposed models to extract the relevant features that are passed to two cascaded layers of Recurrent Neural Networks (RNNs) in each model that acts as a classifier. Based on the experiments conducted with a public dataset, we demonstrate that our designed CNN-GRU-GRU hybrid model outperformed the other models in terms of accuracy (96.01%), less type-I error rate (1.81%), and type-II error rate (2.18%). On the other hand, the CNN-LSTM-LSTM model was attributed to a low computing (training) time of just 4 minutes and 46 seconds. Our findings clearly elucidate the potential of combining classifiers in biomedical analytics research and pave the way for portable point-of-care devices with reasonable accuracy and fast computation times, enabling them to be used for collaborative learning for large-scale, real-time disease modeling.