Evaluating the Performance of Deep Learning Frameworks for Malaria Parasite Detection Using Microscopic Images of Peripheral Blood Smears

被引:14
作者
Ozsahin, Dilber Uzun [1 ,2 ]
Mustapha, Mubarak Taiwo [2 ,3 ]
Duwa, Basil Bartholomew [2 ,3 ]
Ozsahin, Ilker [2 ,4 ]
机构
[1] Univ Sharjah, Coll Hlth Sci, Dept Med Diagnost Imaging, Sharjah 27272, U Arab Emirates
[2] Near East Univ, Operat Res Ctr Healthcare, TRNC Mersin 10, TR-99138 Nicosia, Turkey
[3] Near East Univ, Dept Biomed Engn, TRNC Mersin 10, TR-99138 Nicosia, Turkey
[4] Weill Cornell Med, Dept Radiol, Brain Hlth Imaging Inst, New York, NY 10065 USA
关键词
blood smear; detection; malaria; parasite; transfer learning;
D O I
10.3390/diagnostics12112702
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Malaria is a significant health concern in many third-world countries, especially for pregnant women and young children. It accounted for about 229 million cases and 600,000 mortality globally in 2019. Hence, rapid and accurate detection is vital. This study is focused on achieving three goals. The first is to develop a deep learning framework capable of automating and accurately classifying malaria parasites using microscopic images of thin and thick peripheral blood smears. The second is to report which of the two peripheral blood smears is the most appropriate for use in accurately detecting malaria parasites in peripheral blood smears. Finally, we evaluate the performance of our proposed model with commonly used transfer learning models. We proposed a convolutional neural network capable of accurately predicting the presence of malaria parasites using microscopic images of thin and thick peripheral blood smears. Model evaluation was carried out using commonly used evaluation metrics, and the outcome proved satisfactory. The proposed model performed better when thick peripheral smears were used with accuracy, precision, and sensitivity of 96.97%, 97.00%, and 97.00%. Identifying the most appropriate peripheral blood smear is vital for improved accuracy, rapid smear preparation, and rapid diagnosis of patients, especially in regions where malaria is endemic.
引用
收藏
页数:15
相关论文
共 29 条
[1]  
[Anonymous], 2022, Biology
[2]   Malaria in Europe: A Historical Perspective [J].
Boualam, Mahmoud A. ;
Pradines, Bruno ;
Drancourt, Michel ;
Barbieri, Remi .
FRONTIERS IN MEDICINE, 2021, 8
[3]  
cdc, DIS WHAT IS MAL
[4]   Activation functions in deep learning: A comprehensive survey and benchmark [J].
Dubey, Shiv Ram ;
Singh, Satish Kumar ;
Chaudhuri, Bidyut Baran .
NEUROCOMPUTING, 2022, 503 :92-108
[5]   Malaria in the USA: How Vulnerable Are We to Future Outbreaks? [J].
Dye-Braumuller, Kyndall C. ;
Kanyangarara, Mufaro .
CURRENT TROPICAL MEDICINE REPORTS, 2021, 8 (01) :43-51
[6]  
Feng V., An overview of resnet and its variants
[7]  
Huilgol P, TOP 4 PRETRAINED MOD
[8]   Diagnosing Malaria Patients with Plasmodium falciparum and vivax Using Deep Learning for Thick Smear Images [J].
Kassim, Yasmin M. ;
Yang, Feng ;
Yu, Hang ;
Maude, Richard J. ;
Jaeger, Stefan .
DIAGNOSTICS, 2021, 11 (11)
[9]   Clustering-Based Dual Deep Learning Architecture for Detecting Red Blood Cells in Malaria Diagnostic Smears [J].
Kassim, Yasmin M. ;
Palaniappan, Kannappan ;
Yang, Feng ;
Poostchi, Mahdieh ;
Palaniappan, Nila ;
Maude, Richard J. ;
Antani, Sameer ;
Jaeger, Stefan .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2021, 25 (05) :1735-1746
[10]  
Kumar V, CONVOLUTIONAL NEURAL