Вы находитесь на странице: 1из 7

ABSTRACT

Dermatological disorders are one of the most widespread diseases in the world. The diagnosis of the
skin diseases requires a high level of expertise and they are subjective to the dermatologist, so
computer aided skin prediction system is proposed to provide more objective and reliable solution to
this problem. Skin diseases might cause severe health and monetary consequences for patients if not
detected and controlled early. Early recognition can forestall the condition from worsening.
This project aims to develop skin diseases prediction system with a mobile interface, the system
is to build on a machine learning model. The developed system takes images of an effected skin area as
an input by user and predicts the type of skin diseases. We use the dual stage approach which
effectively combines machine learning and image processing on clinically evaluated histopathological
attributes to accurately identify the disease. In the first stage, the image of skin disease is subject to
numerous types of pre-processing techniques followed by feature extraction. The extracted features for
each image are then converted to a feature vector. In the second stage, the feature vectors are fed to a
machine learning algorithm to identify disease and predict accordingly. On training and testing for 5
diseases (eczema, psoriasis, impetigo, melanoma, and scleroderma) system produces an overall
prediction accuracy of 90%.

©2019 Iqra University


ACKNOWLEGMENT

First, we would like to thank Almighty Allah for giving us the strength, knowledge, and opportunity to
undertake this research study and complete it satisfactorily. Secondly, we are grateful to Dr.Mansoor
Ebrahim for his constant supervision and support throughout FYP.He has been there to lend his sincere
support and advice all the times and has given us invaluable advice, inspiration and suggestions in our
journey to knowledge. He gave us all the freedom to continue our research, without his wise advice, this
project would not be possible.
We would like to express our gratitude to project co coordinator Dr.Sadique Ahmad for his trust,
support and valuable advice throughout the project.
We would also like to express our thanks to all the teachers, they through the studies helps
Us and guide us, and without their guidance, this journey would not have been possible.

©2019 Iqra University


LIST OF ACRONYMS AND ABBREVIATIONS

ML Machine Learning

DBMS Data Base Management System

SQL Structured Query Language

ANN Artificial Neural Network

UI User Network

CNN Convolutional Neural Network

DL Deep Learning

IP Image Processing

ERD Entity Relationship Diagram


Table of Contents
Type chapter title (level 1) ........................................................................................................................... 1
Type chapter title (level 2) ........................................................................................................................ 2
Type chapter title (level 3) .................................................................................................................... 3
Type chapter title (level 1) ........................................................................................................................... 4
Type chapter title (level 2) ........................................................................................................................ 5
Type chapter title (level 3) .................................................................................................................... 6
1. INTRODUCTION

The skin is the largest organ in the human body and has numerous potential
abnormalities; there are about 1500 distinct skin diseases. We are relatively ignorant
about the symptoms of the majority of these diseases although knowledge is rapidly
increasing, however, that makes it a challenge for dermatologist to diagnose them.
Now day’s technologies have changed our day-to-day life in all aspects and the medical
field is not an exception many medical systems have been developed to help both
patients and doctors in different ways, starting from registration process ending with the
use of technologies for diagnosing diseases.
With the increase in medical technology the concept of computer being used for the
diagnosis of skin diseases has been around recently. Use of computer technology can
make it simpler to detect the diseases just from the images of the infected skin image
and could assist the human’s ability to analyze complex information. Artificial
Intelligence is taking up automation in all fields of application even in the healthcare
field.
A computer can efficiently and effortlessly interpret a lot of images where it is difficult for
the human to interpret such a high number of data and look into the details of the image
inside. Therefore Computer-Aided-Detection and Computer-Based-Diagnosis have
become desirable and are under development by many research groups. Computer
based diagnosis have proven to be very helpful in disease diagnosis.
The most prevalent technology which is being used for the prediction is Artificial
Intelligence using Machine Learning. Artificial Intelligence uses learning methods to
learn about the images to predict the diseases based upon the common patterns. The
machine interprets the images and its slices and processes the image and predicts.

1.1. Motivation:
Skin diseases are common to everyone and different types of allergies are becoming
more and more common. Many of these diseases are very dangerous, particularly if not
treated at an early stage. Human habits tend to assume that some skin diseases are not
serious problems. Sometimes, most of the people try to treat these infections of the skin
using their own method. However, if these treatments are not suitable for that particular
skin problem then it would make it worse. And also sometimes they may not be aware
of the dangerousness of their skin diseases, for instance skin cancers. Skin diseases
tend to pass on from one person to another very easily and therefore it is important to
control it at initial stages to prevent it from spreading. Also damage done to the skin
through skin diseases could damage the mental confidence and wellbeing of people.
Therefore this has become a huge problem among people and it has become a crucial
thing to treat these skin diseases properly at the initial stages itself to prevent serious
damage. Our application would help address this problem to a great extent since it
would allow users to recognize skin diseases and provide advises or treatments for it in
a shorter time period by making use of images of the diseased area and by obtaining
information from the patient. This would make the treatment of skin diseases convenient
hence motivating the people to address these problems at the initial stages.
The skin diseases can be prevented by investigating the infected region at an early
stage. The characteristic of the skin images are diversified, so that it is challenging job
to devise an efficient and robust algorithm for automatic detection of the skin disease
and its severity. Skin tone and skin color plays an important role in skin disease
detection. Color and coarseness of skin are visually different. Image processing of such
images for skin analysis requires quantitative discriminator to differentiate the diseases.
On the other-
1.2. Related work:
In the past two decades, strong impulse has been given to developing automated
systems capable of assisting physicians in medical imaging task. The paper proposed
by Muhammad Zubair Asghar presents an online expert system to detect certain skin
diseases that make use of forward chaining with depth first search method. However,
using a system based on set rules and symptoms is not feasible due to the various
manifestations of a single skin disease. The system created by us would be superior in
performance in such a manner as the issue we are addressing is probabilistic in itself
and thus we require a system which has the ability to adapt and learn from the
underlying pattern that exists in the skin disease which can be inferred by the image.

Secondly, the system is implemented i.e. Image-based diagnosis method; this system is
mainly focuses on diagnosing diseases of skin that are occurred by viruses and
bacteria. This system used image of diverse area and those images are taken and then
machine learning techniques and image processing applied to train the computer to
diagnose the ski n diseases. This is an optional diagnosis method for these skin disease
and it is safe and no risks, side effects or inconvenient from the patient perspective. It
also gives advantageous tom doctors because it is fast and can be implemented in
various ways (mobile phones, computers and digital cameras).

1.3. Challenges:

 Dataset:
One of the major issue when developing machine learning or data science
application is the data to be used, because it’s the base that the application
will be built on, so the data must be correct and large enough to develop the
good model.
To solve this common issue there are many website that provide datasets for
machine learning applications, they gather a large amount of data in different
domains, organize and categorize them in a way hat to be useful for the
implementation in these applications. For skin diseases diagnose systems
there are DERMNET & OLE they have large amount of skin diseases images,
and these images are categorized into some general taxonomy of the skin
diseases but we faced many problems during gathering of data.On the other
hand, we also visited hospitals for collecting data which was very time
consuming.

Вам также может понравиться