Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images

• Published in: PeerJ (San Francisco, CA) Vol. 6; p. e4568
• Main Authors: Rajaraman, Sivaramakrishnan, Antani, Sameer K., Poostchi, Mahdieh, Silamut, Kamolrat, Hossain, Md. A., Maude, Richard J., Jaeger, Stefan, Thoma, George R.
• Format: Journal Article
• Language: English
• Published: United States PeerJ. Ltd 16.04.2018; PeerJ, Inc; PeerJ Inc
• Subjects: Analysis; Artificial intelligence; Artificial neural networks; Automation; Blood; Blood smear; Computational Science; Convolutional Neural Networks; Data Mining and Machine Learning; Data Science; Decision making; Deep Learning; Diagnosis; Diagnostic imaging; Disease transmission; Health aspects; Health screening; Image processing; Infectious Diseases; Learning algorithms; Machine Learning; Malaria; Medicine; Methods; Neural networks; Parasitemia; Parasites; Plasmodium falciparum; Pre-trained models; United States > US; Screening; Blood smear; Malaria; Pre-trained models; Feature extraction; Convolutional Neural Networks; Machine Learning; Computer-aided diagnosis; Deep Learning
• DOI: 10.7717/peerj.4568
• ISSN: 2167-8359

Malaria is a blood disease caused by the Plasmodium parasites transmitted through the bite of female Anopheles mosquito. Microscopists commonly examine thick and thin blood smears to diagnose disease and compute parasitemia. However, their accuracy depends on smear quality and expertise in classifying and counting parasitized and uninfected cells. Such an examination could be arduous for large-scale diagnoses resulting in poor quality. State-of-the-art image-analysis based computer-aided diagnosis (CADx) methods using machine learning (ML) techniques, applied to microscopic images of the smears using hand-engineered features demand expertise in analyzing morphological, textural, and positional variations of the region of interest (ROI). In contrast, Convolutional Neural Networks (CNN), a class of deep learning (DL) models promise highly scalable and superior results with end-to-end feature extraction and classification. Automated malaria screening using DL techniques could, therefore, serve as an effective diagnostic aid. In this study, we evaluate the performance of pre-trained CNN based DL models as feature extractors toward classifying parasitized and uninfected cells to aid in improved disease screening. We experimentally determine the optimal model layers for feature extraction from the underlying data. Statistical validation of the results demonstrates the use of pre-trained CNNs as a promising tool for feature extraction for this purpose.