A dataset and benchmark for malaria life-cycle classification in thin blood smear images

Deep learning method for malaria parasite evaluation from microscopic blood smear

OBJECTIVE

Malaria remains a leading cause of global morbidity and mortality, responsible for approximately 5,97,000 deaths according to World Malaria Report 2024. The study aims to systematically review current methodologies for automated analysis of the Plasmodium genus in malaria diagnostics. Specifically, it focuses on computer-assisted methods, examining databases, blood smear types, staining techniques, and diagnostic models used for malaria characterization while identifying the limitations and contributions of recent studies.

METHODS

A systematic literature review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Peer-reviewed and published studies from 2020 to 2024 were retrieved from Web of Science and Scopus. Inclusion criteria focused on studies utilizing deep learning and machine learning models for automated malaria detection from microscopic blood smears. The review considered various blood smear types, staining techniques, and diagnostic models, providing a comprehensive evaluation of the automated diagnostic landscape for malaria.

RESULTS

The NIH database is the standardized and most widely tested database for malaria diagnostics. Giemsa stained-thin blood smear is the most efficient diagnostic method for the detection and observation of the plasmodium lifecycle. This study has been able to identify three categories of ML models most suitable for digital diagnostic of malaria, i.e., Most Accurate- ResNet and VGG with peak accuracy of 99.12 %, Most Popular- custom CNN-based models used by 58 % of studies, and least complex- CADx model. A few pre and post-processing techniques like Gaussian filter and auto encoder for noise reduction have also been discussed for improved accuracy of models.

CONCLUSION

Automated methods for malaria diagnostics show considerable promise in improving diagnostic accuracy and reducing human error. While deep learning models have demonstrated high performance, challenges remain in data standardization and real-world application. Addressing these gaps could lead to more reliable and scalable diagnostic tools, aiding global malaria control efforts.

A deep architecture based on attention mechanisms for effective end-to-end detection of early and mature malaria parasites in a realistic scenario

BACKGROUND

Malaria is a critical and potentially fatal disease caused by the Plasmodium parasite and is responsible for more than 600,000 deaths globally. Early and accurate detection of malaria parasites is crucial for effective treatment, yet conventional microscopy faces limitations in variability and efficiency.

METHODS

We propose a novel computer-aided detection framework based on deep learning and attention mechanisms, extending the YOLO-SPAM and YOLO-PAM models. Our approach facilitates the detection and classification of malaria parasites across all infection stages and supports multi-species identification.

RESULTS

The framework was evaluated on three publicly available datasets, demonstrating high accuracy in detecting four distinct malaria species and their life stages. Comparative analysis against state-of-the-art methodologies indicates significant improvements in both detection rates and diagnostic utility.

CONCLUSION

This study presents a robust solution for automated malaria detection, offering valuable support for pathologists and enhancing diagnostic practices in real-world scenarios.

MI-CSBO: a hybrid system for myocardial infarction classification using deep learning and Bayesian optimization

Myocardial Infarction (MI) refers to damage to the heart tissue caused by an inadequate blood supply to the heart muscle due to a sudden blockage in the coronary arteries. This blockage is often a result of the accumulation of fat (cholesterol) forming plaques (atherosclerosis) in the arteries. Over time, these plaques can crack, leading to the formation of a clot (thrombus), which can block the artery and cause a heart attack. Risk factors for a heart attack include smoking, hypertension, diabetes, high cholesterol, metabolic syndrome, and genetic predisposition. Early diagnosis of MI is crucial. Thus, detecting and classifying MI is essential. This paper introduces a new hybrid approach for MI Classification using Spectrogram and Bayesian Optimization (MI-CSBO) for Electrocardiogram (ECG). First, ECG signals from the PTB Database (PTBDB) were converted from the time domain to the frequency domain using the spectrogram method. Then, a deep residual CNN was applied to the test and train datasets of ECG imaging data. The ECG dataset trained using the Deep Residual model was then acquired. Finally, the Bayesian approach, NCA feature selection, and various machine learning algorithms (k-NN, SVM, Tree, Bagged, Naïve Bayes, Ensemble) were used to derive performance measures. The MI-CSBO method achieved a 100% correct diagnosis rate, as detailed in the Experimental Results section.

An optimised YOLOv4 deep learning model for efficient malarial cell detection in thin blood smear images

BACKGROUND

Malaria is a serious public health concern worldwide. Early and accurate diagnosis is essential for controlling the disease's spread and avoiding severe health complications. Manual examination of blood smear samples by skilled technicians is a time-consuming aspect of the conventional malaria diagnosis toolbox. Malaria persists in many parts of the world, emphasising the urgent need for sophisticated and automated diagnostic instruments to expedite the identification of infected cells, thereby facilitating timely treatment and reducing the risk of disease transmission. This study aims to introduce a more lightweight and quicker model-but with improved accuracy-for diagnosing malaria using a YOLOv4 (You Only Look Once v. 4) deep learning object detector.

METHODS

The YOLOv4 model is modified using direct layer pruning and backbone replacement. The primary objective of layer pruning is the removal and individual analysis of residual blocks within the C3, C4 and C5 (C3-C5) Res-block bodies of the backbone architecture's C3-C5 Res-block bodies. The CSP-DarkNet53 backbone is simultaneously replaced for enhanced feature extraction with a shallower ResNet50 network. The performance metrics of the models are compared and analysed.

RESULTS

The modified models outperform the original YOLOv4 model. The YOLOv4-RC3_4 model with residual blocks pruned from the C3 and C4 Res-block body achieves the highest mean accuracy precision (mAP) of 90.70%. This mAP is > 9% higher than that of the original model, saving approximately 22% of the billion floating point operations (B-FLOPS) and 23 MB in size. The findings indicate that the YOLOv4-RC3_4 model also performs better, with an increase of 9.27% in detecting the infected cells upon pruning the redundant layers from the C3 Res-block bodies of the CSP-DarkeNet53 backbone.

CONCLUSIONS

The results of this study highlight the use of the YOLOv4 model for detecting infected red blood cells. Pruning the residual blocks from the Res-block bodies helps to determine which Res-block bodies contribute the most and least, respectively, to the model's performance. Our method has the potential to revolutionise malaria diagnosis and pave the way for novel deep learning-based bioinformatics solutions. Developing an effective and automated process for diagnosing malaria will considerably contribute to global efforts to combat this debilitating disease. We have shown that removing undesirable residual blocks can reduce the size of the model and its computational complexity without compromising its precision.

YOLO-PAM: Parasite-Attention-Based Model for Efficient Malaria Detection

Malaria is a potentially fatal infectious disease caused by the Plasmodium parasite. The mortality rate can be significantly reduced if the condition is diagnosed and treated early. However, in many underdeveloped countries, the detection of malaria parasites from blood smears is still performed manually by experienced hematologists. This process is time-consuming and error-prone. In recent years, deep-learning-based object-detection methods have shown promising results in automating this task, which is critical to ensure diagnosis and treatment in the shortest possible time. In this paper, we propose a novel Transformer- and attention-based object-detection architecture designed to detect malaria parasites with high efficiency and precision, focusing on detecting several parasite sizes. The proposed method was tested on two public datasets, namely MP-IDB and IML. The evaluation results demonstrated a mean average precision exceeding 83.6% on distinct Plasmodium species within MP-IDB and reaching nearly 60% on IML. These findings underscore the effectiveness of our proposed architecture in automating malaria parasite detection, offering a potential breakthrough in expediting diagnosis and treatment processes.

Multiclass malaria parasite recognition based on transformer models and a generative adversarial network

Malaria is an extremely infectious disease and a main cause of death worldwide. Microscopic examination of thin slide serves as a common method for the diagnosis of malaria. Meanwhile, the transformer models have gained increasing popularity in many regions, such as computer vision and natural language processing. Transformers also offer lots of advantages in classification task, such as Fine-grained Feature Extraction, Attention Mechanism etc. In this article, we propose to assist the medical professionals by developing an effective framework based on transformer models and a generative adversarial network for multi-class plasmodium classification and malaria diagnosis. The Generative Adversarial Network is employed to generate extended training samples from multiclass cell images, with the aim of enhancing the robustness of the resulting model. We aim to optimize plasmodium classification to achieve an exact balance of high accuracy and low resource consumption. A comprehensive comparison of the transformer models to the state-of-the-art methods proves their efficiency in the classification of malaria parasite through thin blood smear microscopic images. Based on our findings, the Swin Transformer model and MobileVit outperform the baseline architectures in terms of precision, recall, F1-score, specificity, and FPR on test set (the data was divided into train: validation: test splits). It is evident that the Swin Transformer achieves superior detection performance (up to 99.8% accuracy), while MobileViT demonstrates lower memory usage and shorter inference times. High accuracy empowers healthcare professionals to conduct precise diagnoses, while low memory usage and short inference times enable the deployment of predictive models on edge devices with limited computational and memory resources.

Reducing data dimension boosts neural network-based stage-specific malaria detection

Although malaria has been known for more than 4 thousand years¹, it still imposes a global burden with approx. 240 million annual cases². Improvement in diagnostic techniques is a prerequisite for its global elimination. Despite its main limitations, being time-consuming and subjective, light microscopy on Giemsa-stained blood smears is still the gold-standard diagnostic method used worldwide. Autonomous computer assisted recognition of malaria infected red blood cells (RBCs) using neural networks (NNs) has the potential to overcome these deficiencies, if a fast, high-accuracy detection can be achieved using low computational power and limited sets of microscopy images for training the NN. Here, we report on a novel NN-based scheme that is capable of the high-speed classification of RBCs into four categories—healthy ones and three classes of infected ones according to the parasite age—with an accuracy as high as 98%. Importantly, we observe that a smart reduction of data dimension, using characteristic one-dimensional cross-sections of the RBC images, not only speeds up the classification but also significantly improves its performance with respect to the usual two-dimensional NN schemes. Via comparative studies on RBC images recorded by two additional techniques, fluorescence and atomic force microscopy, we demonstrate that our method is universally applicable for different types of microscopy images. This robustness against imaging platform-specific features is crucial for diagnostic applications. Our approach for the reduction of data dimension could be straightforwardly generalised for the classification of different parasites, cells and other types of objects.