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

By S. Rajaraman, Sameer Kiran Antani, Mahdieh Poostchi, Kamolrat Silamut, Md Amir Hossain, Richard James Maude, Stefan Jaeger, George R. Thoma. PeerJ, 2018

514 citations recorded by the source corpus.

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.

Subfields: Biophysics, Computer Vision and Pattern Recognition, Plant Science

View Paper: https://www.semanticscholar.org/paper/a759c9cc7d2839e8b227acf6514ec0f7c50ce434

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

1. Ahad Nasab
2. Nafiseh Ghaffar Nia
3. Erkan Kaplanoglu

In Computer Vision and Pattern Recognition

1. Eloy J. Mata
2. Ahad Nasab
3. Á. Casado-García
4. Adrián Inés
5. Manuel García-Domínguez
6. César Domínguez
7. Jónathan Heras
8. Nafiseh Ghaffar Nia

Citations in the corpus

• Diagnosing COVID-19 pneumonia from x-ray and CT images using deep learning and transfer learning algorithms (2020, methodology): “In this study, for the purpose of diagnosing COVID-19 cases, a CNN architecture (as a deep learning algorithm) and modified AlexNet network (as a transfer learning algorithm) have been utilized.”
• CLoDSA: a tool for augmentation in classification, localization, detection, semantic segmentation and instance segmentation tasks (2019, methodology): “To this aim, we consider the classification of Malaria images [31], where images are labelled as parasitized or uninfected; and, we analyse the impact of”
• Evaluation of artificial intelligence techniques in disease diagnosis and prediction (2023, methodology): “Another study used the CNN model for feature extraction in malaria-infected blood cell images [40].”