Deep Learning Based Automatic Malaria Parasite Detection from Blood Smear and Its Smartphone Based Application
Open accessThe DOI matches its Crossref record; 59 of the 59 references it cites were found in a registry or an index.
Abstract
Malaria is a life-threatening disease that is spread by the Plasmodium parasites. It is detected by trained microscopists who analyze microscopic blood smear images. Modern deep learning techniques may be used to do this analysis automatically. The need for the trained personnel can be greatly reduced with the development of an automatic accurate and efficient model. In this article, we propose an entirely automated Convolutional Neural Network (CNN) based model for the diagnosis of malaria from the microscopic blood smear images. A variety of techniques including knowledge distillation, data augmentation, Autoencoder, feature extraction by a CNN model and classified by Support Vector Machine (SVM) or K-Nearest Neighbors (KNN) are performed under three training procedures named general training, distillation training and autoencoder training to optimize and improve the model accuracy and inference performance. Our deep learning-based model can detect malarial parasites from microscopic images with an accuracy of 99.23% while requiring just over 4600 floating point operations. For practical validation of model efficiency, we have deployed the miniaturized model in different mobile phones and a server-backed web application. Data gathered from these environments show that the model can be used to perform inference under 1 s per sample in both offline (mobile only) and online (web application) mode, thus engendering confidence that such models may be deployed for efficient practical inferential systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“evaluated the performances of AlexNet, VGG-16 [50], ResNet-50 [51], Xception [52], DenseNet-121 [53] along with their custom-built model [24].”
MethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“To find the optimal layer of a pre ‐ trained model to extract features from underlying malaria parasite data, Rajaraman et al. evaluated the performances of AlexNet, VGG ‐ 16 [50], ResNet ‐ 50 [51], Xception [52], DenseNet ‐ 121 [53] along with their custom ‐ built model [24].”
MethodImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 3×
“To find the optimal layer of a pre ‐ trained model to extract features from underlying malaria parasite data, Rajaraman et al. evaluated the performances of AlexNet, VGG ‐ 16 [50], ResNet ‐ 50 [51], Xception [52], DenseNet ‐ 121 [53] along with their custom ‐ built model [24].”
MethodImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“pre-trained a model on Imagenet [55] but fine-tuned it on own data for detecting malaria parasite [35].”
MethodCortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
A Threshold Selection Method from Gray-Level Histograms
Otsu, N. (1979) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/tsmc.1979.4310076 · Cited by 43,398 · cited 1×
“The RGB images were transformed to gray scale and binarized using the OTSU method [79].”
MethodXception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380 · cited 2×
“To find the optimal layer of a pre ‐ trained model to extract features from underlying malaria parasite data, Rajaraman et al. evaluated the performances of AlexNet, VGG ‐ 16 [50], ResNet ‐ 50 [51], Xception [52], DenseNet ‐ 121 [53] along with their custom ‐ built model [24].”
MethodLearning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,172
Wold, S., Esbensen, K., & Geladi, P. (1987) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/0169-7439(87)80084-9 · Cited by 11,606 · cited 2×
“For example, [42,43] relied on morphological factors for feature extraction and applied SVM and Principal Component Analysis (PCA) [44] for the classification purpose.”
MethodConvolutional networks for images, speech, and time series
LeCun, Y., & Bengio, Y. (1998) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.5555/303568.303704 · Cited by 4,231
Assumption-free analysis of quantitative real-time polymerase chain reaction (PCR) data
Ramakers, C., Ruijter, J. M., Deprez, R. H. L., & Moorman, A. F. M. (2003) · Neuroscience Letters · doi:10.1016/s0304-3940(02)01423-4 · Cited by 3,709
Buciluǎ, C., Caruana, R., & Niculescu-Mizil, A. (2006) · Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1150402.1150464 · Cited by 2,068
Snounou, G., Viriyakosol, S., Zhu, X. P., Jarra, W., Pinheiro, L., do Rosario, V. E., Thaithong, S., & Brown, K. N. (1993) · Molecular and Biochemical Parasitology · doi:10.1016/0166-6851(93)90077-b · Cited by 1,591
Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction
Sakurada, M., & Yairi, T. (2014) · Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis · doi:10.1145/2689746.2689747 · Cited by 1,438
A k-nearest neighbor classification rule based on Dempster-Shafer theory
Denoeux, T. (1995) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/21.376493 · Cited by 1,013 · cited 1×
“Support vector machine (SVM) and K ‐ Nearest Neighbor (KNN) are the core machine learning algorithms that were used as a classifier by implicitly mapping their inputs into high ‐ dimensional feature spaces [57,64].”
MethodA Review of Malaria Diagnostic Tools: Microscopy and Rapid Diagnostic Test (RDT)
Wongsrichanalai, C., Barcus, M. J., Muth, S., Sutamihardja, A., & Wernsdorfer, W. H. (2007) · The American Journal of Tropical Medicine and Hygiene · doi:10.4269/ajtmh.2007.77.119 · Cited by 939 · cited 3×
“RDT and microscopic diagnosis are two of the most impactful malaria diagnosis methods which make a very large contribution to malaria control today [13].”
BackgroundSnounou, G., Viriyakosol, S., Jarra, W., Thaithong, S., & Brown, K. N. (1993) · Molecular and Biochemical Parasitology · doi:10.1016/0166-6851(93)90050-8 · Cited by 906 · cited 1×
“Many techniques have been reported, in the literature, which detects malarial parasites in a patient such as clinical diagnosis [3,4], microscopic diagnosis [5–10], rapid diagnostic test (RDT) [11– 13] and polymerase chain reaction (PCR) [14–16].”
BackgroundA sparse auto-encoder-based deep neural network approach for induction motor faults classification
Sun, W., Shao, S., Zhao, R., Yan, R., Zhang, X., & Chen, X. (2016) · Measurement · doi:10.1016/j.measurement.2016.04.007 · Cited by 698 · cited 1×
“However, in this task, it is used as a classifier, inspired by [61,62].”
MethodA novel hybrid CNN–SVM classifier for recognizing handwritten digits
Niu, X.-X., & Suen, C. Y. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2011.09.021 · Cited by 671
Large-scale matrix factorization with distributed stochastic gradient descent
Gemulla, R., Nijkamp, E., Haas, P. J., & Sismanis, Y. (2011) · Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2020408.2020426 · Cited by 589
Rajaraman, S., Antani, S. K., Poostchi, M., Silamut, K., Hossain, M. A., Maude, R. J., Jaeger, S., & Thoma, G. R. (2018) · PeerJ · doi:10.7717/peerj.4568 · Cited by 566 · cited 4×
“In this study we trained multiple accurate and computationally efficient models for malaria parasite detection in single cells using a publicly available malaria dataset [24].”
MethodInfluentialImage analysis and machine learning for detecting malaria
Poostchi, M., Silamut, K., Maude, R. J., Jaeger, S., & Thoma, G. (2018) · Translational Research · doi:10.1016/j.trsl.2017.12.004 · Cited by 559 · cited 2×
“Automatic microscopic malaria parasite detection, which involves the acquisition of the microscopic blood smear image (for example by smartphone as demonstrated in [24,25]), segmentation of the cells and classification of the infected cells, can be an effective diagnostic tool [26].”
MethodCNN-based image analysis for malaria diagnosis
Liang, Z., Powell, A., Ersoy, I., Poostchi, M., Silamut, K., Palaniappan, K., Guo, P., Hossain, M. A., Sameer, A., Maude, R. J., et al. (2016) · 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2016.7822567 · Cited by 325 · cited 1×
“37% accuracy in detection with the help of their 16-layered CNN model and claimed that their model is superior to transfer learning models [54].”
MethodWatershed of a continuous function
Najman, L., & Schmitt, M. (1994) · Signal Processing · doi:10.1016/0165-1684(94)90059-0 · Cited by 317 · cited 4×
“For automatic segmentation, we used the Watershed algorithm to perform segmentation.”
MethodInfluentialHigh-Resolution SAR Image Classification via Deep Convolutional Autoencoders
Geng, J., Fan, J., Wang, H., Ma, X., Li, B., & Chen, F. (2015) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2015.2478256 · Cited by 291 · cited 1×
“However, in this task, it is used as a classifier, inspired by [61,62].”
MethodMachine learning approach for automated screening of malaria parasite using light microscopic images
Das, D. K., Ghosh, M., Pal, M., Maiti, A. K., & Chakraborty, C. (2013) · Micron · doi:10.1016/j.micron.2012.11.002 · Cited by 274
Dong, Y., Jiang, Z., Shen, H., David Pan, W., Williams, L. A., Reddy, V. V. B., Benjamin, W. H., & Bryan, A. W. (2017) · 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI) · doi:10.1109/bhi.2017.7897215 · Cited by 237 · cited 3×
“For automatic detection of malaria pathogens from the microscopic images, Convolutional Neural Network (CNN) [45] received much attention from the researchers in recent times.”
MethodApplying Faster R-CNN for Object Detection on Malaria Images
Hung, J., & Carpenter, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.112 · Cited by 230
Image Segmentation Using Gray‐Scale Morphology and Marker‐ControlledWatershed Transformation
Parvati, K., Prakasa Rao, B. S., & Mariya Das, M. (2008) · Discrete Dynamics in Nature and Society · doi:10.1155/2008/384346 · Cited by 213
Díaz, G., González, F. A., & Romero, E. (2009) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2008.11.005 · Cited by 211 · cited 1×
“Many techniques have been reported, in the literature, which detects malarial parasites in a patient such as clinical diagnosis [3,4], microscopic diagnosis [5–10], rapid diagnostic test (RDT) [11– 13] and polymerase chain reaction (PCR) [14–16].”
BackgroundUpdate on Malaria Diagnostics and Test Utilization
Mathison, B. A., & Pritt, B. S. (2017) · Journal of Clinical Microbiology · doi:10.1128/jcm.02562-16 · Cited by 210 · cited 1×
“Microscopic systems do not suffer from these shortcomings and is considered to be effective for malaria parasite detection [13,22], however this technique requires the presence of a trained microscopists [23].”
BackgroundMalaria Parasite Detection From Peripheral Blood Smear Images Using Deep Belief Networks
Bibin, D., Nair, M. S., & Punitha, P. (2017) · IEEE Access · doi:10.1109/access.2017.2705642 · Cited by 207 · cited 2×
“Previous works that concentrated on the classification of infected cells involve tools and techniques from image processing [31–33], computer vision [34–36] and machine learning [37–39].”
BackgroundParasite detection and identification for automated thin blood film malaria diagnosis
Tek, F. B., Dempster, A. G., & Kale, İ. (2010) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2009.08.003 · Cited by 202
Rajaraman, S., Jaeger, S., & Antani, S. K. (2019) · PeerJ · doi:10.7717/peerj.6977 · Cited by 196
Deep Convolutional Neural Networks for Microscopy-Based Point of Care DiagnosticsPreprint
Quinn, J. A., Nakasi, R., Mugagga, P. K. B., Byanyima, P., Lubega, W., & Andama, A. O. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.02989 · Cited by 175 · cited 2×
“A few notable exceptions are the works of Quinn et al. [25] and Rosado et al. [56] who also tackled the problem of computational efficiency of their models.”
BackgroundMethodImpact of Microscopy Error on Estimates of Protective Efficacy in Malaria‐Prevention Trials
Ohrt, C., Purnomo, Sutamihardja, M. A., Tang, D., & Kain, K. C. (2002) · The Journal of Infectious Diseases · doi:10.1086/341938 · Cited by 173
Gopakumar, G. P., Swetha, M., Sai Siva, G., & Sai Subrahmanyam, G. R. K. (2018) · Journal of Biophotonics · doi:10.1002/jbio.201700003 · Cited by 168 · cited 1×
“The use of deep learning technique, particularly those that leverage transfer learning [31,40,58] yield superior results when considering classification metrics.”
BackgroundComputer vision for microscopy diagnosis of malaria
Tek, F. B., Dempster, A. G., & Kale, I. (2009) · Malaria Journal · doi:10.1186/1475-2875-8-153 · Cited by 161
What is clinical malaria? Finding case definitions for field research in highly endemic areas
Schellenberg, J., Smith, T. A., Alonso, P. L., & Hayes, R. (1994) · Parasitology Today · doi:10.1016/0169-4758(94)90179-1 · Cited by 151 · cited 1×
“Many techniques have been reported, in the literature, which detects malarial parasites in a patient such as clinical diagnosis [3,4], microscopic diagnosis [5–10], rapid diagnostic test (RDT) [11–13] and polymerase chain reaction (PCR) [14–16].”
BackgroundLinder, N., Turkki, R., Walliander, M., Mårtensson, A., Diwan, V. K., Rahtu, E., Pietikäinen, M., Lundin, M., & Lundin, J. E. (2014) · PLoS ONE · doi:10.1371/journal.pone.0104855 · Cited by 147 · cited 1×
“For example, [42,43] relied on morphological factors for feature extraction and applied SVM and Principal Component Analysis (PCA) [44] for the classification purpose.”
MethodSegmentation of blood images using morphological operators
Rubeto, C. D., Dempster, A. G., Khan, S. M., & Jarra, B. (2002) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2000.903568 · Cited by 128
Zheng, Y., Jiang, Z., Xie, F., Zhang, H., Ma, Y., Shi, H., & Zhao, Y. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.05.010 · Cited by 127 · cited 1×
“Earlier work [65–67] reported the effectiveness of SVM or KNN classifier on the Convolutional neural network’s extracted features instead of using the softmax layer.”
MethodSignificance-linked connected component analysis for wavelet image coding
Chai, B.-B., Vass, J., & Zhuang, X. (1999) · IEEE Transactions on Image Processing · doi:10.1109/83.766856 · Cited by 123 · cited 1×
“Finally, we performed connected component analysis [81] on these local peaks and applied the Watershed algorithm.”
MethodDigital image analysis for automatic enumeration of malaria parasites using morphological operations
Arco, J. E., Górriz, J. M., Ramírez, J., Álvarez, I., & Puntonet, C. G. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.11.037 · Cited by 91
Automated status identification of microscopic images obtained from malaria thin blood smears
Anggraini, D., Nugroho, A. S., Pratama, C., Rozi, I. E., Iskandar, A. A., & Hartono, R. N. (2011) · doi:10.1109/iceei.2011.6021762 · Cited by 79
Das, D. K., MAITI, A. K., & Chakraborty, C. (2014) · Journal of Microscopy · doi:10.1111/jmi.12206 · Cited by 73
Alam, M. S., Mohon, A. N., Mustafa, S., Khan, W. A., Islam, N., Karim, M. J., Khanum, H., Sullivan, D. J., & Haque, R. (2011) · Malaria Journal · doi:10.1186/1475-2875-10-175 · Cited by 69 · cited 1×
“Many techniques have been reported, in the literature, which detects malarial parasites in a patient such as clinical diagnosis [3,4], microscopic diagnosis [5–10], rapid diagnostic test (RDT) [11– 13] and polymerase chain reaction (PCR) [14–16].”
BackgroundA portable image-based cytometer for rapid malaria detection and quantification
Yang, D., Subramanian, G., Duan, J., Gao, S., Bai, L., Chandramohanadas, R., & Ai, Y. (2017) · PLoS ONE · doi:10.1371/journal.pone.0179161 · Cited by 57
Tarimo, D. S., Minjas, J. N., & Bygbjerg, I. C. (2001) · Annals of Tropical Medicine & Parasitology · doi:10.1080/00034983.2001.11813657 · Cited by 55 · cited 1×
“Many techniques have been reported, in the literature, which detects malarial parasites in a patient such as clinical diagnosis [3,4], microscopic diagnosis [5–10], rapid diagnostic test (RDT) [11– 13] and polymerase chain reaction (PCR) [14–16].”
BackgroundRanjit, M., Das, A., Das, B., et al. (2005) · Transactions of the Royal Society of Tropical Medicine and Hygiene · doi:10.1016/j.trstmh.2004.09.010 · Cited by 54 · cited 1×
“Previous works that concentrated on the classification of infected cells involve tools and techniques from image processing [31–33], computer vision [34–36] and machine learning [37–39].”
BackgroundDevi, S. S., Roy, A., Singha, J., Sheikh, S. A., & Laskar, R. H. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-4264-7 · Cited by 48
Automated Image Analysis Method for p-vivax Malaria Parasite Detection in Thick Film Blood Images
Yunda, L., Alarcón, A., & Millán, J. R. (2012) · Sistemas y Telemática · doi:10.18046/syt.v10i20.1151 · Cited by 43 · cited 1×
“Previous works that concentrated on the classification of infected cells involve tools and techniques from image processing [31–33], computer vision [34–36] and machine learning [37–39].”
BackgroundMorphological Image Processing for Evaluating Malaria Disease
Ruberto, C. D., Dempster, A. G., Khan, S. M., & Jarra, B. (2001) · Lecture notes in computer science · doi:10.1007/3-540-45129-3_68 · Cited by 40
Automatic Malaria Diagnosis system
Mehrjou, A., Abbasian, T., & Izadi, M. (2013) · RSI International Conference on Robotics and Mechatronics (ICRoM) · doi:10.1109/icrom.2013.6510106 · Cited by 38 · cited 1×
“Many techniques have been reported, in the literature, which detects malarial parasites in a patient such as clinical diagnosis [3,4], microscopic diagnosis [5–10], rapid diagnostic test (RDT) [11– 13] and polymerase chain reaction (PCR) [14–16].”
BackgroundAhirwar, N., Pattnaik, S., & Acharya, B. (2014) · Cited by 24
Masanja, I. M., McMorrow, M., Maganga, M. B., Sumari, D., Udhayakumar, V., McElroy, P. D., Kachur, S. P., & Lucchi, N. W. (2015) · Malaria Journal · doi:10.1186/s12936-015-0597-3 · Cited by 15
Opoku-Ansah, J., Eghan, M. J., Anderson, B., & Boampong, J. N. (2014) · Applied Physics Research · doi:10.5539/apr.v6n2p47 · Cited by 15 · cited 1×
“For example, [42,43] relied on morphological factors for feature extraction and applied SVM and Principal Component Analysis (PCA) [44] for the classification purpose.”
Method
Metadata
- Authors
- Fuhad, K. M. F., Tuba, J. F., Sarker, M. R. A., Momen, S., Mohammed, N., & Rahman, T.
- Venue
- Diagnostics
- Publisher
- MDPI AG
- Published
- 2020-05-20
- Volume
- 10
- Issue
- 5
- Pages
- 329
- ISSN
- 2075-4418 (ISSN-L)
- OpenAlex
- W3027051205
- Cited by
- 185
- References
- 59
- FWCI
- 9.73
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.