ABSTRACT
Malaria, caused by Plasmodium parasites, remains a critical global health issue, particularly in tropical regions. Traditional microscopic diagnosis is time-consuming and reliant on expert skills. This study proposes DepthResInceptNet, an innovative deep learning model that integrates depthwise convolution, inception, and residual learning for malaria detection in red blood cell images. The dataset comprised 27,557 images, split into training, validation, and testing subsets and pre-processed to standardize and augment data. The model’s architecture leverages parallel convolutional filters and residual connections to enhance feature extraction and mitigate degradation, reducing computational costs and parameters. Evaluation metrics indicated high performance with an accuracy of 94.2% and recall of 97.0%. Comparative analysis with state-of-the-art models demonstrated the proposed model’s superior reliability and efficiency. The application of Grad-CAM for model interpretability highlighted the decision-making regions, enhancing trustworthiness. DepthResInceptNet offers a robust and precise tool for automated malaria diagnosis, outperforming existing methods.
References
[1] D.O. Oyewola, E.G. Dada, S. Misra, R. Damaševičius, A novel data augmentation convolutional neural network for detecting malaria parasite in blood smear images, Appl. Artif. Intell. 36 (1) (2022) 2033473.
[2] S. Suraksha, C. Santhosh, B. Vishwa, Classification of malaria cell images using deep learning approach, in: 2023 Third International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies(ICAECT),2023,pp. 1–5, http://dx.doi.org/10.1109/ICAECT57570.2023.10117649.
[3] B. Kakkar, M. goyal, P. Johri, Y. Kumar, Artificial intelligence-based approaches for detection and classification of different classes of malaria parasites using microscopic images: A systematic review, Arch. Comput. Methods Eng. (2023) 1–20.
[4] S.N. Mahmood, S.S. Mohammed, A.G. Ismaeel, H.G. Clarke, I.N. Mahmood, D.A. Aziz, S. Alani, Improved malaria cells detection using deep convolutional neural network, in: 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), 2023, pp. 1–4, http://dx.doi. org/10.1109/HORA58378.2023.10156747.
[5] Diker, A. (2022). An efficient model of residual based convolutional neural network with Bayesian optimization for the classification of malarial cell images. Computers in Biology and Medicine, 148, 105635.
[6] A.M. Qadir, P.A. Abdalla, M.I. Ghareb, Malaria parasite identification from red blood cell images using transfer learning models, Passer J. Basic Appl. Sci. 4 (Special issue) (2022) 63–79.
[7] Yang, F., Poostchi, M., Yu, H., Zhou, Z., Silamut, K., Yu, J., Maude, R.J., Jaeger, S., Antani, S., 2019. Deep learning for smartphone-based malaria parasite detection in thick blood smears. IEEE J. Biomed. Health Informatics 24 (5), 1427–1438.
[8] Rohan Bhansali, MalariaNet, A computationally efficient convolutional neural network architecture for automated malaria detection, Int. J. Eng. Res. V9 (12) (2020).
[9] A. Maqsood, M.S. Farid, M.H. Khan, M. Grzegorzek, Deep malaria parasite detection in thin blood smear microscopic images, Appl. Sci. 11 (5) (2021) 1–19.
[10] Jiang, Y., Li, X., Luo, H., Yin, S. and Kaynak, O., 2022. Quo vadis artificial intelligence? Discover Artificial Intelligence, 2(1), p.4.
Download all article in PDF
