LANCASTER UNIVERSITY 2022 UNDERGRADUATE RESEARCH CONFERENCE
15th MARCH - 17th MARCH 2022
Rooney Adu-Gyamfi

Rooney Adu-Gyamfi

Computing and Digital Technologies (B&FC) | Year 3 | Degree: Computer Science
At what level can deep learning be applied towards eliminating the need for skilful experts towards the diagnosis of parasitized or healthy malaria patients in remote parts of the world.

Malaria is a serious mosquito-borne disease caused by the plasmodium parasite. It is transmitted when an infected mosquito bites a person. Early diagnosis of malaria is critical in the diagnosis of malaria before it multiplies and leads to death. The golden standard for diagnosis of malaria is the microscopic examination. The major drawback of this approach is that, it is time consuming and labour intensive. According to the WHO`s 2020 World malaria report, there was an estimated 241 malaria cases and 627,000 deaths worldwide in 2020 . About 47,000 of these cases were linked to improper diagnosis and disruptions. A study in Ghana found that there were only 1.72 microscopes per 100,000 population but only 0.85 trained technicians per 100,000 population . Due to this unavailability of microscopes and skill technicians, diagnosis are made on the basis of clinical signs and symptoms alone. The purpose of this study is to determine the effectiveness of convolutional neural networks in categorizing microscopic blood smear images as parasitized or healthy. This research aims to explore how the recent advancements in Artificial intelligence and Deep learning can be used to automate the diagnosis of malaria parasite. Two deep learning models VGG-19 and ResNet-50 will be largely examined and compared to determine the bet performing model on a malaria dataset.

Rooney Adu-Gyamfi
 
Rooney Adu-Gyamfi

Rooney Adu-Gyamfi

Computing and Digital Technologies (B&FC) | Year 3 | Degree: Computer Science
At what level can deep learning be applied towards eliminating the need for skilful experts towards the diagnosis of parasitized or healthy malaria patients in remote parts of the world.
<
>
 

Introduction

Malaria is an infectious mosquito borne disease the is caused by the plasmodium parasite. It is transmitted when an individual is bitten by an infected mosquito. According to the WHO`s 2020 World malaria report, there was an estimated 241 malaria cases and 627,000 deaths worldwide in 2020 (WHO, 2021). About 47,000 of these cases were linked to improper diagnosis and disruptions.

    Malaria is more commonly found in underdeveloped areas where the diagnosis of medical conditions are not easily accessible. The plasmodium parasite works by infecting the liver and multiplying in large numbers then attacking the red blood cells. If this is not diagnosed properly, it could lead to untimely death to the human infected with it. An early diagnosis is essential for the treatment of malaria. The medically accepted form of diagnosis worldwide is the light microscopy technique. Microscopic diagnosis while currently properly is long and tedious and also requires skilled technicians which may take about 15-20 minutes to count all the cells.  A study in Ghana found that there were only 1.72 microscopes per 100,000 population but only 0.85 trained technicians per 100,000 population (Bates, 2004). Due to this unavailability of microscopes and skill technicians, diagnosis are made on the basis of clinical signs and symptoms alone.

Research Aim

Light microscopy remains a good approach to diagnosing malaria however interpretation of the images is labour intensive intensive and limited to the skill level of the microscopist.

The purpose of this study is to determine the effectiveness of convolutional neural networks in categorizing microscopic blood smear images as parasitized or healthy. A deep learning approach to malaria diagnosis will limit the need for a human expert and furthermore decrease the cost of equipment and minimize the use of electricity. 

Parasitized vs Healthy Blood Smear Images
Parasitized Blood Smear Image
Healthy Blood Smear Image
This study aims to determine at what level deep learning can be applied towards eliminating the need for skilful experts towards the diagnosis of parasitized or healthy malaria patients in remote parts of the world
Proposed Solutions Majority of the work related to malaria diagnosis require human expert intervention to aid in interpretation of their results. Attempts made in automating the traditional microscopy has produced very little success as there is still the problem of differentiating the species and determining the parasitic stage. In this research, a deep learning approach is proposed as a viable solution to these problems. By comparing two different deep learning models VGG-19 and ResNet-60 , a smartphone based application will be created to determine which one is more accurate. The figure below is a pictorial diagram of a mobile based solution
Proposed Deep Learning Model
The Convolutional Neural Network Architecture Used here is the Resnet-60. It shows the client that interacts with the server a trained convolutional neural network model. Th architecture can be used to train millions of images. The cell image is given as an input then the convolutional neural network will learn the basic characteristics such as the edges, spots, shape and size. The output results will indicate whether a patient is infected or healthy.  
 

References

Bates, V. a.-A. (2004). Improving the accuracy of malaria-related laboratory tests. Brydegaard, M. M. (2011). Versatile multispectral microscope based on light emiting diodes. Review of Scientific Instruments, 82.
  1. Ohrt, D. T. (1999). “Impact of microscopy error on protective efficacy estimates in. Clinical Pharmacology and Therapeutics, 134.
D, P. (1988). Use and limitations of light microscopy for diagnosing malaria at the primary health care level. Bulletin of the World Health Organization, 621–626. Omucheni, D. (2012). Multispectral imaging of human blood media applied to malaria. M.Sc thesis, University of Nairobi. Ross, N. P. (2006). Automated image processing method for the diagnosis and classification of malaria on thin blood smears. Medical and Biological Engineering and Computing, 427-436. WHO. (2021). World malaria report 2021. Retrieved from World Health Organization: https://www.who.int/teams/global-malaria-programme/reports/world-malaria-report-2021 Zoueu, J. T. (2008). Optical Microscope Based on Multispectral Imaging Applied to Plasmodium Diagnosis. Journal of Applied Sciences, 2711-2717.    
Page saved!
Add default layout Add text Add image/symbol Add audio/video
Preview page
CloseCanvas height (pixels)
Background colour
Background image (max: 2mb)
Clear
Drop files here to upload
CloseEmail Website address Facebook Twitter Instagram Profile image
Close
Slide 1 image (max 2mb)
Clear
Drop files here to upload
Slide 1 video (YouTube/Vimeo embed code)
Clear
Image 1 Caption
Slide 2 image (max 2mb)
Clear
Drop files here to upload
Slide 2 video (YouTube/Vimeo embed code)
Clear
Image 2 Caption
Slide 3 image (max 2mb)
Clear
Drop files here to upload
Slide 3 video (YouTube/Vimeo embed code)
Clear
Image 3 Caption
Slide 4 image (max 2mb)
Clear
Drop files here to upload
Slide 4 video (YouTube/Vimeo embed code)
Clear
Image 4 Caption
Slide 5 image (max 2mb)
Clear
Drop files here to upload
Slide 5 video (YouTube/Vimeo embed code)
Clear
Image 5 Caption
Slide 6 image (max 2mb)
Clear
Drop files here to upload
Slide 6 video (YouTube/Vimeo embed code)
Clear
Image 6 Caption
Slide 7 image (max 2mb)
Clear
Drop files here to upload
Slide 7 video (YouTube/Vimeo embed code)
Clear
Image 7 Caption
Slide 8 image (max 2mb)
Clear
Drop files here to upload
Slide 8 video (YouTube/Vimeo embed code)
Clear
Image 8 Caption
Slide 9 image (max 2mb)
Clear
Drop files here to upload
Slide 9 video (YouTube/Vimeo embed code)
Clear
Image 9 Caption
Slide 10 image (max 2mb)
Clear
Drop files here to upload
Slide 20 video (YouTube/Vimeo embed code)
Clear
Image 10 Caption
Caption font Text
CloseImage (max size: 2mb)
Clear
Or drag a symbol into the upload area
Image description/alt-tag Image caption Image link Rollover Image (max size: 2mb)
Clear
Or drag a symbol into the upload area
Border colour
Rotate
Skew (x-axis)
Skew (y-axis)
CloseVideo/audio player embed code (YouTube/Vimeo/Soundcloud)
Rotate
CloseText Rollover Text Background colour
Rotate
CloseText Rollover Text Background colour
Rotate
CloseText Rollover Text Background colour
Rotate
CloseImage (max size: 2mb)
Clear
Drop files here to upload
Or drag a symbol into the upload area
Image description/alt-tag Image caption Image link Rollover Image (max size: 2mb)
Clear
Drop files here to upload
Or drag a symbol into the upload area
Border colour
 
Rotate
Skew (x-axis)
Skew (y-axis)
CloseText Rollover Text Background colour
Rotate
CloseText Rollover Text Background colour
Rotate
CloseText Rollover Text Background colour
Rotate
CloseImage (max size: 2mb)
Clear
Drop files here to upload
C1_thinF_IMG_20150604_104722_cell_60.png
11.9 KB
C1_thinF_IMG_20150604_104722_cell_60.png
Or drag a symbol into the upload area
Image description/alt-tag Image caption Image link Rollover Image (max size: 2mb)
Clear
Drop files here to upload
Or drag a symbol into the upload area
Border colour
 
Rotate
Skew (x-axis)
Skew (y-axis)
CloseImage (max size: 2mb)
Clear
Drop files here to upload
C39P4thinF_original_IMG_20150622_110115_cell_118.png
16.1 KB
C39P4thinF_original_IMG_20150622_110115_cell_118.png
Or drag a symbol into the upload area
Image description/alt-tag Image caption Image link Rollover Image (max size: 2mb)
Clear
Drop files here to upload
Or drag a symbol into the upload area
Border colour
 
Rotate
Skew (x-axis)
Skew (y-axis)
CloseText Rollover Text Background colour
Rotate
CloseText Rollover Text Background colour
Rotate
CloseImage (max size: 2mb)
Clear
Drop files here to upload
Or drag a symbol into the upload area
Image description/alt-tag Image caption Image link Rollover Image (max size: 2mb)
Clear
Drop files here to upload
Or drag a symbol into the upload area
Border colour
 
Rotate
Skew (x-axis)
Skew (y-axis)
CloseImage (max size: 2mb)
Clear
Drop files here to upload
Or drag a symbol into the upload area
Image description/alt-tag Image caption Image link Rollover Image (max size: 2mb)
Clear
Drop files here to upload
Or drag a symbol into the upload area
Border colour
 
Rotate
Skew (x-axis)
Skew (y-axis)
CloseText Rollover Text Background colour
Rotate
CloseText Rollover Text Background colour
Rotate
CloseText Rollover Text Background colour
Rotate
GO TO CONFERENCE