Analyzing Malaria Disease Using Effective Deep Learning Approach

Sriporn, Krit; Tsai, Chuen Jinn; Wang, Paohsi

doi:10.3390/diagnostics10100744

Cited by 41 publications

(23 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of these methods ranges between ∼80-98%. Similar performance levels have recently been achieved also by unbiased convolutional networks with minimal or no pre-processing of microscopy images [29][30][31][32] .…”

Section: Introductionsupporting

confidence: 56%

“…As a common solution for this problem, data augmentation can be used to equalise the number of images in the different categories (ring-, trophozoite-, schizont-stage, and healthy RBCs) by generating more data for the training set 29,30 . This has been demonstrated to improve the performance of the NN 31,32 and to further increase the generalisation ability.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Preißinger

Kellermayer

Vértessy

et al. 2022

Preprint

View full text Add to dashboard Cite

Although malaria has been known for more than 4 thousand years, it still imposes a global burden with approx. 240 million annual cases. 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 can be straightforwardly generalised for the classification of different parasites, cells and other types of objects.

show abstract

Section: Introductionsupporting

confidence: 56%

Section: Introductionmentioning

confidence: 99%

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

Preißinger

Kellermayer

Vértessy

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To our experience, this approach outperforms other standard methods in automated histopathological image classification. the study in [11] used 7000 images of exception, Inception-V3, ResNet-50,NasNetMobile, VGG-16, and AlexNet models for verifying and analysis. These are standard models that classify the image accuracy and use a rotational method to enhance the execution of validation and the training dataset with convolutional neural network models.…”

Section: Literature Reviewmentioning

confidence: 99%

A Proposed Model to eliminate the Confusion of Hematological Diseases in Thin Blood Smear by Using Deep Learning-Pretrained Model

Sharif

Mohammed

Hussein

2022

oiuj

View full text Add to dashboard Cite

This research aimed to developing and designing a model for resolving the confusion between hematology in a thin blood smear by means of a pre-defined deep learning model for detection and identification of hematological diseases in thin blood smear images for accurate diagnosis of the different diseases that leukemia and malaria were performed as a sample. There are catastrophic consequences that may lead to death as a result of a mistake in diagnosis and confusion in the knowledge of the disease in particular, especially in hematology, where another disease that was not originally found in the sample is identified for the similarity, which results in surgery and sometimes the administration of drugs in error. In this work, an image processing system was developed to identify patients with malaria and leukemia. The techniques in deep learning have been implemented where the CNN (Alexnet and Resnet50) image recognition model was applied to detect patterns and extract features of the different types of malaria and leukemia from the images. And that is through developing algorithms to distinguish between the two diseases, discovering the presence of similarities in the patterns of stages and the different types of malaria and leukemia in blood images, and reaching to solve the problem of confusion by training, verification, and testing using the mutual verification system that uses three folds. The system achieved an accuracy of 94.3% for Resnet50 and 92.3 for Alexnet in detecting and classifying the types and stages of the two diseases (malaria and leukemia). And 100% to distinguish between them.

show abstract

“…DT is used for classification problems and has an interpretability advantage over other classification algorithms [25]. It partitions data recursively into smaller subdivisions based on a set of a test at each node in the tree [26].…”

Section: Classificationmentioning

confidence: 99%

DeepFMD: Computational Analysis for Malaria Detection in Blood-Smear Images Using Deep-Learning Features

Abubakar

Ajuji

Yahya

2021

ASI

View full text Add to dashboard Cite

Malaria is one of the most infectious diseases in the world, particularly in developing continents such as Africa and Asia. Due to the high number of cases and lack of sufficient diagnostic facilities and experienced medical personnel, there is a need for advanced diagnostic procedures to complement existing methods. For this reason, this study proposes the use of machine-learning models to detect the malaria parasite in blood-smear images. Six different features—VGG16, VGG19, ResNet50, ResNet101, DenseNet121, and DenseNet201 models—were extracted. Then Decision Tree, Support Vector Machine, Naïve Bayes, and K-Nearest Neighbour classifiers were trained using these six features. Extensive performance analysis is presented in terms of precision, recall, f-1score, accuracy, and computational time. The results showed that automating the process can effectively detect the malaria parasite in blood samples with an accuracy of over 94% with less complexity than the previous approaches found in the literature.

show abstract

Analyzing Malaria Disease Using Effective Deep Learning Approach

Cited by 41 publications

References 61 publications

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

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

A Proposed Model to eliminate the Confusion of Hematological Diseases in Thin Blood Smear by Using Deep Learning-Pretrained Model

DeepFMD: Computational Analysis for Malaria Detection in Blood-Smear Images Using Deep-Learning Features

Contact Info

Product

Resources

About