CHAPTER ONE

INTRODUCTION

1. 1. Background of the Study

Malaria is a disease caused by a plasmodium parasite, transmitted by the bite of infected female anopheles mosquitoes. Red blood cells that have been infected with plasmodium parasite can lead to symptoms, such as fever, malaise, seizures, and coma, in severe cases. Urgent and reliable diagnosis and early treatment of malaria is one of the most effective ways of fighting the disease, together with better treatments and mosquito control (Mahdieh et al., 2018).

The examination of microscopic blood smears is still regarded as the main standard for malaria diagnosis. It offers the ability to characterize parasite species, quantify parasite density, and assess the effectiveness of anti-malarial treatment etc. However, regions that are suffering from malaria disease are often still lacking in qualified personnel that can carry out high-quality microscopy examination due to the high costs of training such experts in our tradition institutions (Hang et al., 2020).

Diagnosis of malaria can be difficult, where malaria is not endemic anymore, health-care providers may not be familiar with the disease. Clinicians while examining a malaria patient tend to forget to consider malaria among a potential disease and hence don't suggest the necessary diagnostic tests. Detecting parasites while examining blood smears under the microscope requires experience, which the laboratorians may lack and thus fail to detect (Mohd et al., 2020).

In some malaria-endemic areas, a large section of the population is infected by the parasites but are still not ill or sick. Such carriers have the malaria infection but they have developed just enough immunity to not get the malaria illness or to show any symptoms in their system. In that case, finding malaria parasites in an ill person doesn't necessarily mean that malaria is the root cause of the person's illness or the parasites are solely responsible for the illness. The proposed system would sense the presence of malaria parasites on a regular blood-smeared slide. A phone camera can be attached to the microscope's ocular to take the blood smear photographs and then analyze it. Traditional malaria detection approaches are very time consuming, may produce inaccurate reports due to human errors, and are laborious for extensive diagnoses. Based on the weaknesses of the state-of-the-art solution, a Deep learning technique is been proposed (Faza et al., 2021).

Deep learning techniques are now generally used for image classification and medical image analysis. It has been a proven method which increases the performance in any field. A convolutional neural network (CNN), a type of deep neural networks, is essentially considered for research in the computer vision field. The deep architecture of CNN is its main power. The convolutional layer in the CNN works as an automatic feature extract-tor that extracts hidden and important features. Extracted features are passed to a fully connected neural network which performs classification images by maximizing the probability scores. In this research, a mobile based classification system, for classifying red blood cell smears, for either being infected or not, of plasmodium parasite is proposed using Convolutional Neural Network (Çinar et al., 2020).

1.2     Statement of the Problem

Malaria is a disease caused by a plasmodium parasite, transmitted by the bite of infected mosquitoes., the female Anopheles mosquito is the sole transmitter of the Plasmodium parasites among humans. Malaria is a transmittable disease caused by the parasites which belong to the Plasmodium family. The African region is one of the continents that is inflicted by high malaria cases and high death rates. The high percentage of these deaths is due to the fact that most individuals fail to detect the disease early, especially in third world Africa (Çinar et al., 2020).

The traditional mechanism commonly used in diagnosing plasmodium parasite in red blood smear of diseased individuals, has been to visually examine the blood smears through microscope by a laboratory technician, in which case, the diagnosis accuracy is dependent on the level of expertise and experience of the laboratory scientist/technician. This mechanism is inefficient due to the dependent nature of its diagnosis accuracy and also the diagnosis process is time consuming (Kaewkamnerd et al., 2011).

The aim of this research is to identify the presence or absence of malaria parasites in red blood smear. In resolving these challenges and assuaging the problems in the traditional malaria diagnosis system, an automated mobile based system to detect malaria parasites on blood smears and to improve diagnostic accuracy is been proposed, using Convolutional Neural Network (CNN), a computer vision Deep Learning (DL) algorithm to train a classification model with Python TensorFlow(TF) library module, and deploy the model in an android application, which will run on a mobile device, such that “microscopic view images” of red blood smear can be capture from the mobile device camera, for preprocessing, classification and display of the model prediction result. The proposed method of malaria detection as opposed to the traditional method aforementioned, would give an unbiased and consistent diagnosis classification result of malaria in red blood smears regardless of the experience and expertise of the laboratory scientist/technician involved and it will also take lesser diagnosis time as opposed to the traditional method.

1.3     Aim and Objectives of the Study

The aim of this study is to develop a malaria diagnosis system based on CNN. The objectives of the study are as follows;

1. Development of CNN based model for malaria disease
2. Develop an algorithm
3. Implement the algorithm developed
4. Evaluate the system performance

1.4     Significance of the Study

The study will serve as an avenue that would aid medical laboratory scientist and technicians to carry out malaria diagnosis using their mobile device.

The software is also relevant in the following ways:

1. Enable easy classification of red blood smears for malaria disease.
2. Reduce the cost of carrying out a full microscopic test on red blood smears.
3. Reduce the time of carrying out the conventional microscopic test on red blood smears.

1.5     Scope of the Study

This research is limited to the classification of malaria disease in a red blood cell using computer vision and convolutional Neural Network on a mobile device.

1.6   Limitation of the Study

The researcher faced some limitations during the course of this research. Some of this limitations/constraint includes;

i.        Time constraint: Time factor was the major factors as the timeframe to submit the project was too short for rigorous research.

ii.       financial constraint:  Lack of adequate finance to fund the researcher as to the purchase of data to review related works online was another major setback.

1.7     Definition of Terms

1. Artificial Intelligence: It is an intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and animals.
2. Artificial Neural Networks:    These are computing systems that are inspired by, but not necessarily identical to biological neural networks, that constitute animal brain. Such systems learn to perform task by considering examples, generally with being programmed with any task or specific rules.
3. Convolutional Neural Network (CNN):   Is a class of Deep Neural Networks, most commonly applied to analyzing visual imagery.
4. Data Argumentation:   Is use in deep learning to regularize, normalize the information on data to be trained.
5. Data Notation:    This is the process of labeling data to make it usable for machine learning.
6. Dataset:      A collection of related sets of information that is composed of separate elements but can be manipulated as a unit by a computer.
7. Deep Learning: It is a part of broader family of machine learning model base on artificial neural networks.
8. Disease Detection:    It is a process of determining which disease or condition explains a tree/person’s symptoms and sign. It is most often referred to as diagnosis with the medical context.
9. Disease Diagnosis:   It is process of determining which disease or condition explains a tree/persons symptom and signs.
10. Image:     This refers to the optical counterpart of an object produced by an optical device (such as a lens or mirror) or an electronic device.
11. Machine Learning: It is a scientific study of algorithms and statistical model that computer system uses in other to perform a specific task effectively, without using an explicit instruction relying on patterns and inference instead. It is seen as subset of artificial intelligence.
12. Malaria: an intermittent and remittent fever caused by a protozoan parasite that invades the red blood cells. The parasite is transmitted by mosquitoes in many tropical and subtropical regions.
13. Mobile App:  A mobile app or mobile application is a computer program or software application designed to run on a mobile device such as a phone-tablet or watch.
14. Model: Is a description or analogy used to help visualize something that cannot be directly observed.
15. Multilayer Perceptron: This refers to fully connected networks, that is, each neuron in one layer is connected to all neurons in the next layer.
16. Pathogen:   It is a bacterium, virus, or other microorganism that can cause disease.
17. Perceptron: This refers to a linear classifier (binary) use in supervised learning. It helps to classify the given input data.
18. Software:   It is a program and other operating information use by a computer system.
19. Tensor-Flow: is a free and open-source software library for dataflow and differentiable programming across a range of tasks. It is a symbolic math library, and is also used for machine learning applications such as neural networks.