Embedded System‐Based Malaria Detection From Blood Smear Images Using Lightweight Deep Learning Model

Embedded System‐Based Malaria Detection From Blood Smear Images Using Lightweight Deep Learning Model Abdus Salam Department of Electrical and Computer Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh Department of Electrical Engineering Qatar University Doha Qatar S. M. Nahid Hasan Department of Electrical and Computer Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh Md. Jawadul Karim Department of Electrical and Computer Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh https://orcid.org/0009-0006-4226-3652 Shamim Anower Department of Electrical and Electronic Engineering Rajshahi University of Engineering and Technology Rajshahi Bangladesh Md Nahiduzzaman Department of Electrical and Computer Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh Muhammad E. H. Chowdhury Department of Electrical Engineering Qatar University Doha Qatar https://orcid.org/0000-0003-0744-8206 M. Murugappan Intelligent Signal Processing (ISP) Research Lab, Department of Electronics and Communication Engineering Kuwait College of Science and Technology Doha Kuwait Department of Electronics and Communication Engineering Vels Institute of Sciences, Technology, and Advanced Studies Chennai Tamilnadu India https://orcid.org/0000-0002-5839-4589 ABSTRACT

The disease of malaria, transmitted by female Anopheles mosquitoes, is highly contagious, resulting in numerous deaths across various regions. Microscopic examination of blood cells remains one of the most accurate methods for malaria diagnosis, but it is time‐consuming and can produce inaccurate results occasionally. Due to machine learning and deep learning advances in medical diagnosis, improved diagnostic accuracy can now be achieved while costs can be reduced compared to conventional microscopy methods. This work utilizes an open‐source dataset with 26 161 blood smear images in RGB for malaria detection. Our preprocessing resized the original dimensions of the images into 64 × 64 due to the limitations in computational complexity in developing embedded systems‐based malaria detection. We present a novel embedded system approach using 119 154 trainable parameters in a lightweight 17‐layer SqueezeNet model for the automatic detection of malaria. Incredibly, the model is only 1.72 MB in size. An evaluation of the model's performance on the original NIH malaria dataset shows that it has exceptional accuracy, precision, recall, and F1 scores of 96.37%, 95.67%, 97.21%, and 96.44%, respectively. Based on a modified dataset, the results improved further to 99.71% across all metrics. Compared to current deep learning models, our model significantly outperforms them for malaria detection, making it ideal for embedded systems. This model has also been rigorously tested on the Jetson Nano B01 edge device, demonstrating a rapid single image prediction time of only 0.24 s. The fusion of deep learning with embedded systems makes this research a crucial step toward improving malaria diagnosis. In resource‐constrained settings, the model's lightweight architecture and accuracy enhancements hold great promise for addressing the critical challenge of malaria detection.
10 29 2024 11 2024 e23205 10.1002/ima.23205 2 10.1002/crossmark_policy onlinelibrary.wiley.com true 2024-03-20 2024-10-10 2024-10-29 http://onlinelibrary.wiley.com/termsAndConditions#vor 10.1002/ima.23205 https://onlinelibrary.wiley.com/doi/10.1002/ima.23205 https://onlinelibrary.wiley.com/doi/pdf/10.1002/ima.23205 10.1016/j.cell.2016.07.055 10.1016/S1473‐3099(04)01043‐6 10.1098/rstb.2011.0091 M.RoserandH.Ritchie “Our World in Data Malaria ” accessed April 2024 https://ourworldindata.org/malaria. 10.1186/1475-2875-10-297 “Clincial Guidance: Malaria Diagnosis & Treatment in the U.S ” accessed June 5 2024 https://www.cdc.gov/malaria/hcp/clinical‐guidance/index.html. 10.1186/s40249‐018‐0392‐9 10.1109/ACCESS.2023.3234279 “Institute of Health Metrics and Evaluation ”2024 https://www.healthdata.org/research‐analysis/health‐risks‐issues/child‐health. 10.1002/ima.22953 10.1007/s00530‐022‐00917‐7 10.1117/1.JMI.8.5.054502 10.18280/ria.340506 10.1007/s11042-021-10946-5 10.1109/ACCESS.2020.2994810 10.1109/BIBM.2016.7822567 10.1002/jbio.201700003 10.32604/cmc.2022.025577 10.1007/s11042-019-7162-y 10.1109/ICOEI48184.2020.9143023 10.1155/2022/3922763 10.1109/ACCESS.2017.2705642 10.32604/cmc.2023.033860 10.1016/j.eswa.2022.116554 10.3390/informatics9040076 Journal of Science and Technology Shuleenda Devi S. 1 9 2016 Malaria Infected Erythrocyte Classification Based on the Histogram Features Using Microscopic Images of Thin Blood Smear, Indian 10.1007/s00521-017-2937-4 10.1186/s40537-021-00415-z 10.1109/JBHI.2020.3034863 10.7717/peerj.4568 10.3390/diagnostics10050329 K.SimonyanandA.Zisserman “Very Deep Convolutional Networks for Large‐Scale Image Recognition ” 2014 arXiv Preprint arXiv:1409.1556. 10.1109/ICCV.2017.74 Proc.—2018 IEEE Winter Conf. Appl. Comput. Vision, WACV 2018 Chattopadhay A. 839 2018 2nd International Conference on Learning Representations Simonyan K. 2014 10.1109/BHI.2017.7897215 10.1007/s11042‐024‐19062‐6 10.18653/v1/n16‐3020 10.1109/ACCESS.2024.3407153 Advances in Neural Information Processing Systems Adebayo J. 1 31 2018 Sanity Checks for Saliency Maps 10.1007/978-3-319-10590-1_53 10.1109/TVCG.2016.2598831 10.1109/MCSE.2007.55