Multithresholding Approach for Segmenting Plasmodium Parasites

Nugroho, Hanung Adi; Marsiano, Akmalazakia Fatan Derana; Xaphakdy, Khampaserth; Sihakhom, Phounsiri; Frannita, Eka Legya; Nurfauzi, Rizki; Murhandarwati, E. Elsa Herdiana

doi:10.1109/iciteed.2019.8929995

Cited by 7 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Oliveira et al [12] combine artificial intelligence [13] with mathematical morphology, the search space for the classification operations are reduced using preprocessing by removing the background using erosion to train and test the classifier model. Nugroho et al [14] proposed multilevel Otsu's thresholding combined with closing operator, the model proposed by this paper obtained 96.74 ± 0.7075 %, 76.77 ± 2.1441 %, 99.74 ± 0.1397 %, 97.84 ±1.2514 % and 96.61 ± 0.8021 % of accuracy, sensitivity, specificity, prediction value positive and prediction value negative, respectively.…”

Section: Introductionmentioning

confidence: 71%

“…The testing results cannot be compared directly with [14] because this paper has a different evaluation scheme and different images size due to the resizing, but it can be said that the U-Net may be able to surpass the sensitivity and F1 values of [14].…”

Section: Testing Resultsmentioning

confidence: 99%

“…The dataset used in this study was 30 images of Plasmodium in thin blood smears with three channels in PNG format used by [14], along with the corresponding ideal segmentation images. The images have a size of 200×200 pixels.…”

Section: Datasetmentioning

confidence: 99%

“…Plasmodium has a small size and is difficult to distinguish from noise such as white blood cells, thus requiring an enhancement method designed to improve segmentation accuracy. Dataset used in this study has been preprocessed before by [14], which has been proven to be optimal for conducting Plasmodium segmentation, hence preprocessing used in this study only resizes the images to 224×224 pixels and convert them to grayscale images using (1). = 0.299 + 0.587 + 0.114…”

Section: Preprocessing and Augmentationmentioning

confidence: 99%

See 3 more Smart Citations

Malaria parasite segmentation using U-Net: Comparative study of loss functions

Abraham¹

2019

CST

View full text Add to dashboard Cite

The convolutional neural network is commonly used for classification. However, convolutional networks can also be used for semantic segmentation using the fully convolutional network approach. U-Net is one example of a fully convolutional network architecture capable of producing accurate segmentation on biomedical images. This paper proposes to use U-Net for Plasmodium segmentation on thin blood smear images. The evaluation shows that U-Net can accurately perform Plasmodium segmentation on thin blood smear images, besides this study also compares the three loss functions, namely mean-squared error, binary cross-entropy, and Huber loss. The results show that Huber loss has the best testing metrics: 0.9297, 0.9715, 0.8957, 0.9096 for F1 score, positive predictive value (PPV), sensitivity (SE), and relative segmentation accuracy (RSA), respectively.

show abstract

Section: Introductionmentioning

confidence: 71%

Section: Testing Resultsmentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%

Section: Preprocessing and Augmentationmentioning

confidence: 99%

See 2 more Smart Citations

Malaria parasite segmentation using U-Net: Comparative study of loss functions

Abraham¹

2019

CST

View full text Add to dashboard Cite

show abstract

“…These issues will potentially become obstacles. They will affect the objectivity of the results if the identification is made by microscope observation [4][5].…”

Section: Introductionmentioning

confidence: 99%

A Systematic Review on Automatic Detection of Plasmodium Parasite

Sumi

Nugroho

Hartanto

2021

Int. j. eng. technol. innov.

Self Cite

View full text Add to dashboard Cite

Plasmodium parasite is the main cause of malaria which has taken many lives. Some research works have been conducted to detect the Plasmodium parasite automatically. This research aims to identify the development of current research in the area of Plasmodium parasite detection. The research uses a systematic literature review (SLR) approach comprising three stages, namely planning, conducting, and reporting. The search process is based on the keywords which were determined in advance. The selection process involves the inclusion and exclusion criteria. The search yields 45 literatures from five different digital libraries. The identification process finds out that 28 methods are applied and mainly categorizes as machine learning algorithms with performance achievements between 60% and 95%. Overall, the research of Plasmodium parasite detection today has focused on the development with artificial intelligence specifically related to machine and deep learning. These approaches are believed as the most effective approach to detect Plasmodium parasites.

show abstract

Saturation channel extraction of HSV color space for segmenting Plasmodium parasite

Nugroho

Goratama

Frannita

2021

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

Malaria is one of the dangerous diseases in the world. Despite it has been decreased every year, the number of patients for this disease is still reasonably a lot. Technical problems that arise in the malaria cases are due to malaria examination and diagnosis analysis, which are carried out manually. At the same time, there are still medical personnel scarcities in some rural areas including of some districts in Indonesia. Moreover, the required examination process demands accuracy and takes a long time. Thus, an effective solution is necessary to help parasitologist to reduce malaria cases. One of the alternative ways to solve those problems is by utilizing technology to assist medical personnel in conducting examinations and analyzing the diagnosis results. This research was conducted to reach this objective. In achieving this objective, an image segmentation approach for finding the Plasmodium parasites was developed. The proposed approach consisted of four stages, which are the pre-processing stage, the segmentation stage, the refinement of segmentation results stage, and the evaluation stage. This proposed method was performed on 25 digital microscopy images of the thin blood smear digital microscopic images. The experiment yielded a good performance with the accuracy, sensitivity, and specificity of 99.83%, 85.06%, and 99.90%, respectively. These results indicate that the proposed method has an outstanding performance in segmenting Plasmodium parasite and can be utilized as a preliminary project to assist doctors in examining or identifying the Plasmodium parasites location.

show abstract

Multithresholding Approach for Segmenting Plasmodium Parasites

Cited by 7 publications

References 14 publications

Malaria parasite segmentation using U-Net: Comparative study of loss functions

Malaria parasite segmentation using U-Net: Comparative study of loss functions

A Systematic Review on Automatic Detection of Plasmodium Parasite

Saturation channel extraction of HSV color space for segmenting Plasmodium parasite

Contact Info

Product

Resources

About