A hybrid machine learning approach for automated malaria diagnosis from thin blood smear images

Abstract Background Malaria remains a significant global health challenge, requiring diagnostic approaches that are rapid, cost-effective, and accurate. The present study proposes a hybrid deep learning framework for malaria diagnosis using thin blood smear cell images obtained from the National Institute of Malaria Research (NIMR), a leading research institution of the Indian Council of Medical Research (ICMR). Methods A total of 15,938 thin blood smear microscopic images were preprocessed to enhance the visibility of cellular structures and suppress background noise. Segmentation was performed using the Otsu thresholding method, which automatically determines the optimal threshold to maximize cell contrast and improve feature extraction. The processed images were then used to train the proposed Hybrid Inception-v3 convolutional neural network (CNN), specifically designed for automated cell classification. To establish the robustness of the proposed CNN, comparative and statistical analyses were performed against conventional diagnostic techniques and other state-of-the-art machine learning models. Results The proposed hybrid CNN model achieved a training accuracy of 98.9%, sensitivity of 97.3%, specificity of 99.9%, along with high F 1 score and area under the curve (AUC) values. These results were obtained using the ICMR-NIMR microscopic image dataset, demonstrating the robustness and generalizability of our approach. The model consistently outperformed other evaluated methods, including state-of-the-art machine learning classifiers, and demonstrated performance comparable to or better than conventional microscopy-based examinations. Conclusions The hybrid deep learning framework demonstrated robust performance for malaria diagnosis using microscopic images, suggesting potential to reduce reliance on expert microscopists. These findings highlight its potential to improve diagnostic precision and strengthen malaria control efforts, especially in resource-limited settings. Graphical Abstract