• Corpus ID: 221397092

Deep unsupervised learning for Microscopy-Based Malaria detection

  title={Deep unsupervised learning for Microscopy-Based Malaria detection},
  author={Alexander Tao and Boran Han},
  journal={arXiv: Image and Video Processing},
Malaria, a mosquito-borne disease caused by a parasite, kills over 1 million people globally each year. People, if left untreated, may develop severe complications, leading to death. Effective and accurate diagnosis is important for the management and control of malaria. Our research focuses on utilizing machine learning to improve the efficiency in Malaria diagnosis. We utilize a modified U-net architecture, as an unsupervised learning model, to conduct cell boundary detection. The blood cells… 

Figures from this paper


Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images
This study evaluates the performance of pre-trained CNN based DL models as feature extractors toward classifying parasitized and uninfected cells to aid in improved disease screening and experimentally determines the optimal model layers for feature extraction from the underlying data.
Deep learning approach to detect malaria from microscopic images
A novel deep neural network model is introduced for identifying infected falciparum malaria parasite using transfer learning approach, which shows the potential of transfer learning in the field of medical image analysis, especially malaria diagnosis.
Image analysis and machine learning for detecting malaria
Applying Faster R-CNN for Object Detection on Malaria Images
This work applies for the first time an object detection model previously used on natural images to identify cells and recognize their stages in brightfield microscopy images of malaria-infected blood to demonstrate that Faster R-CNN outperforms the authors' baseline and put the results in context of human performance.
Deep Learning for Smartphone-Based Malaria Parasite Detection in Thick Blood Smears
The first deep learning method that can detect malaria parasites in thick blood smear images and can run on smartphones is developed, a promising alternative to manual parasite counting for malaria diagnosis, especially in areas lacking experienced parasitologists.
Deep Learning Enhanced Extended Depth-of-Field for Thick Blood-Film Malaria High-Throughput Microscopy
A new deep learning method based on Convolutional Neural Networks (EDoF-CNN) that is able to rapidly perform the extended depth-of-field while also enhancing the spatial resolution of the resulting fused image is developed.
Malaria diagnosis: a brief review.
This review details the currently available diagnostic methods for malaria and describes how they have been developed and introduced to overcome the limitations.
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Annotated high-throughput microscopy image sets for validation
This work describes canonical ways to measure an algorithm’s performance so that algorithms can be compared against each other fairly, and provides an optional framework to do so conveniently within CellProfiler.
Adam: A Method for Stochastic Optimization
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.