Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 7

MonkeyPox Skin Lesion Detection Using Machine Learning Application

Submitted By:
Sarwat Ali 16041
Muhammad Usama 16742

Session
2018-2022

Supervised by
Irfan Ullah Khan

A project proposal submitted to The IQRA National University, Peshawar in partial fulfillment of the
requirements for the degree of
BACHELOR OF SCIENCE (BS) IN COMPUTER SCIENCE

DEPARTMENT OF COMPUTER SCIENCE


IQRA NATIONAL UNIVERSITY, PESHAWAR-PAKISTAN

OCTOBER, 2022
i
Table of Contents

List of Figures................................................................................................................. ii
List of Tables................................................................................................................. iii
List of Acronyms........................................................................................................... iv
Abstract...............................................................................................................................1

Introduction..................................................................................................................... 1

Literature Review............................................................................................................ 1

Problem Statement.......................................................................................................... 2

Objectives of Project....................................................................................................... 2

Methodology for Implementation of Project...................................................................2

Project Proposed Time Schedule.....................................................................................7

Budget Description.......................................................................................................... 8

References....................................................................................................................... 9

Undertaking................................................................................................................... 10

Supervisor Comments................................................................................................... 11

FYP Coordinator Remarks............................................................................................ 12

i
LIST OF FIGURES

Fig. No. Fig. Description Page No.

1.1 Flow chart 5


1.2 Use case 6

i
LIST OF TABLES

Table. No. Table. Description Page No.

1.1 Metadata 4

1.2 Time schedule 7

1.3 Gantt chart 8

i
LIST OF ACRONYMS

ACRONYMS DESCRIPTION
INU IQRA National University
ML Machine Learning
IDE Integrated development environment
XML Extensible markup language
SDLC Software development lifecycle
AI Artificial intelligence
FDA Food and Drug Administration
App Application
BCC Basal Cell Carcinoma

i
1. INTRODUCTION

Over the last two decades, researchers and scientists worked on machine learning and deep learning
techniques to develop such mechanism for assisting and controlling of different disease. Recently,
Machine learning (ML) has demonstrated huge potential in image-based diagnoses such as cancer
detection, tumor cell identification, and COVID-19 patient detection. Therefore, a similar application
can be adapted to diagnose the Monkeypox related disease as it infected the human skin, which
image can be acquired and further used in diagnosing the disease.
Monkeypox is the most common form of cancer in many countries which arises in humans and
animals but it is an unusual asset of this disease interim. Due to the growing trend of Monkeypox
disease, it is having a huge impact on the world and creating a serious burden. It is found in people of
all ages but mostly targets young and elders.

In the authors select three well-known CNN architectures namely, VGG16, ResNet50 and
InceptionV3, pre-trained on the ImageNet dataset. These models are chosen as they have
demonstrated excellent classification performance across different fields of computer vision,
including medical images through transfer learning [1]. By using these 3 methods the ResNet50 have
the best accuracy (82:96_4:57%), while VGG16 shows competitive performance (81:48 _ 6:87%).
Further they introduce the web application for initial investigation of the disease because the PCR
test is not available. In the researchers address the ongoing data scarcity related to Monkeypox virus-
infected patient images [2]. A limited number of image data set is obtained from open sources.
Additionally, they conducted two studies considering small and moderate datasets wherein a
modified VGG16 model is implemented. Our findings suggest that using transfer learning
approaches, the proposed modified VGG16 can distinguish patients with Monkeypox symptoms
from others in both Study One and Two with accuracy ranging from 78% to 97%. Finally, they have
used LIME to present the proper explanation of the reason behind model’s prediction, which is one
of the current demands in deploying ML models for clinical trials.

2. Literature Review

3. Problem Statement
There is no such an application to detect the skin cancer and give us the result either it is effected or
not in early stage and there is no such a system to detect skin cancer without diagnoses a clinical test.
The clinical test does not show direct result without doctor access and not everyone afford the
clinical test and doctor fees. Therefore, to overcome this problem.

4. Objectives of Project
This project aim is to build an application which will work on analysis of Machine learning with AI
techniques for taking images of samples of skin injured place for identification of the skin cancer and
the use of different ML models to compare their accuracy and implement the best performing model
in the Application.

5. Methodology for Implementation of Project

6. Project Proposed Time Schedule

7. Budget Description
i
8. Undertaking

9. Supervisor Comments

10. FYP Coordinator Remarks

References:
1. Ali, Shams Nafisa, et al. "Monkeypox skin lesion detection using deep learning models: A
feasibility study." arXiv preprint arXiv:2207.03342 (2022).
2. Ahsan, Md Manjurul, et al. "Image Data collection and implementation of deep learning-based model in
detecting Monkeypox disease using modified VGG16." arXiv preprint arXiv:2206.01862 (2022).

You might also like