PROJECT_NAME

A project report submitted in partial fulfillment

of the requirements for the award of the degree of

Master
of
Computer Application
Submitted by
STUDENT_NAME
ROLL_NO
Under the esteemed guidance of
GUIDE_NAME
Assistant Professor

DEPARTMENT OF COMPUTER SCIENCE &ENGINEERING

ST.MARY’S GROUP OF INSTITUTIONS GUNTUR (Affiliated
to JNTU Kakinada, Approved by AICTE, Accredited by NBA)
CHEBROLU-522 212, A.P, INDIA
2014-16
 ST. MARY’S GROUP OF INSTITUTIONS, CHEBROLU, GUNTUR
(Affiliated to JNTU Kakinada)

DEPARTMENT OF COMPUTER SCIENCE & ENGINEEING

CERTIFICATE

This is to certify that the project report entitled PROJECT NAME” is the bonafied record of
project work carried out by STUDENT NAME, a student of this college, during the academic
year 2014 - 2016, in partial fulfillment of the requirements for the award of the degree of Master
Of Computer Application from St.Marys Group Of Institutions Guntur of Jawaharlal Nehru
Technological University, Kakinada.

GUIDE_NAME,
Asst. Professor Associate. Professor
(Project Guide) (Head of Department, CSE)
 DECLARATION

We, hereby declare that the project report entitled “PROJECT_NAME” is an original work done at St.Mary„s
Group of Institutions Guntur, Chebrolu, Guntur and submitted in fulfillment of the requirements for the
award of Master of Computer Application, to St.Mary„s Group of Institutions Guntur, Chebrolu,
Guntur.

STUDENT_NAME
ROLL_NO
 ACKNOWLEDGEMENT

We consider it as a privilege to thank all those people who helped us a lot for successful
completion of the project “PROJECT_NAME” A special gratitude we extend to our guide
GUIDE_NAME, Asst. Professor whose contribution in stimulating suggestions and
encouragement ,helped us to coordinate our project especially in writing this report, whose
valuable suggestions, guidance and comprehensive assistance helped us a lot in presenting the
project “PROJECT_NAME”.
We would also like to acknowledge with much appreciation the crucial role of our Co-
Ordinator GUIDE_NAME, Asst.Professor for helping us a lot in completing our project. We
just wanted to say thank you for being such a wonderful educator as well as a person.
We express our heartfelt thanks to HOD_NAME, Head of the Department, CSE, for his
spontaneous expression of knowledge, which helped us in bringing up this project through the
academic year.

STUDENT_NAME
ROLL_NO
 TABLE OF CONTENT

CHAPTER TITLE PAGE NO

1 Introduction 1

2 2.1 Literature review 2

2.2 Existing system 3
2.3 Proposed system 3

3 Methodology 4

3.1 Data Collection 4

5
3.2 Image Processing

6
3.3 Image Segmentation & Feature
Extraction

3.4 Image Classification 6

4 System Requirements & Libraries 7

4.1 Software Requirements 7

4.2 Libraries Used 7

5 System Architecture 9

6 Modules 10
 6.1 Detection 10
6.2 Testing 11
6.3 Reference & Feedback 12

7 Working 13

7.1 Photos of 7 classes 14

7.2 Preprocessing 14
7.3 Reshaping 14

7.4 Creating Training & Test Datasets 14

7.5 Creating Convolution Neural 14

Networks & Feed Forward
Neural
7.6 Activation Functions 15
7.7 Training with Earlyn Stopping 15
& Patience with 5
7.8 Saving the Model 15
7.9 Testing with Evaluation Function 15

7.10 Creating Preprocessing Function 15

for input to the model

8 Result 16

9 Conclusion 19

Reference 19

Appendix 20
LIST OF FIGURES
Fig No TITLE PG.NO

3.1 Images of skin cancer dataset 4

5 System architecture 9

6 Modules 10

8.1 Detection of melanoma 16

8.2 Detection of actinic keratose 17

8.3 Reference of hospitals 17

8.4 Feedback form 18

8.5 Feedback form 18

9 Appendix 22

Sample screens of various models

LIST OF ABBREVIATIONS

CNN Convolutional Neural Network

GLCM Gray Level Co-occurrence Matrix

FFNN Feed Forward Neural Network
 ACKNOWLEDGEMENT
First and foremost, I would like to thank ALMIGHTY who has provided us the strength to do
justice to our work and contribute our best to it. We wish to express our deep sense of gratitude
from the bottom of our heart to our guide Mrs. T.VIJAYASHREE.,M.E.,(Ph.D), Assistant
Professor, Electronics and communication Engineering, for his motivating discussions,
overwhelming suggestions, ingenious encouragement, invaluable supervision, and exemplary guidance
throughout this project work.

I would like to extend my heartfelt gratitude to Dr. T.RAVI.,M.E.,Ph.D, Professor& Head,

Department of Electronics and communication Engineering for her valuable suggestions and
support in successfully completing the project.

I wish to thank my Project Coordinator and Panel members for keeping our project in the right
track. I would like to thank all the teaching, technical and non-technical staff of Department of
Computer Science and Engineering for their courteous assistance.

I thank the management of SATHYABAMA INSTITUTE OF SCIENCE AND

TECHNOLOGY for providing us the necessary facilities and support required for the successful
completion of the project.

As a final word, I would like to thank each and every individual who have been a source of
support and encouragement and helped us to achieve our goal and complete our project work
successfully.

BALAJI.ADIGOPULA(37130006)
 ABSTRACT
Now a day’s skin cancer is a major problem human beings are facing, To recognize skin cancer
new methodology for the diagnosing skin cancer by images of dermatologic spots using image
processing presented. Currently in skin cancer one the most frequent diseases humans. This
methodology based Fourier spectral analysis using filters such classic, inverse and to k-law
nonlinear. The sample images are obtained by a specialist as an replacement spectral to technique
is developed and quantitative measurement in the complex pattern found cancerous skin spots.
Finally in which spectral index calculated get a variety spectral indices defined carcinoma . Our
results show confidence of level in 95.4%. carcinoma mainly occurs thanks to exposure of
sunlight. Ozone is depletion and maintained chemical exposures in other factors involved
precipitating carcinoma . Mutations of p53 gene involved UV- induced as carcinogenesis. P53
gene acts vital development in SCC.

Skin Cancer alarming is disease for mankind , the need early diagnosis the skin cancer are
increased due to the rapid climb rate of Melanoma skin cancer , its high treatment Costs , and
death rate. The cancer cells are detected manually and it takes time to cure in most of the cases.
This project proposed a man-made carcinoma detection system using image Processing and
machine learning method. The features of the affected skin cells are extracted after the
segmetation of the pictures using feature extraction technique. A deep learning based method
Convolutional neural network classifier is employed for the stratification of the extracted
features..

Skin Cancer is an alerting issue and it must be detected as early as possible. The diagnostic is a
manual process that is time consuming as well as expensive. But, today’s world science has
become advanced by using machine learning make easy detecting cancerous cells to the machine
learning specially convolution neural network is employed to detect cancerous cell more in
quickly
, and to efficiently.
 CHAPTER - 1

INTRODUCTION
Cancer forms when healthy cells in change in and grow out control, forming an the called a the
tumor. A tumor can cancerous r benign. A cancerous tumor is malignant, meaning that grow and
spread over other parts of the body. As there bengun as a tumour means that tumor can be grow
but won't spread.

Doctors diagnose carcinoma additional than 3 million Americans annually , making in foremost
common sort of cancer. If carcinoma is found early, it can usually be treated with topical
medications, procedures wiped out offic a dermatologist, or outpatient surgery. A dermatologist
may doctor who focuses diseases and conditions of the skin. As an result, carcinoma is liable for
but 1% all cancer deaths.

In some cases, carcinoma could also more advanced in need management to a multidisciplinary
team to always a dermatologist, surgical and oncologist, radiation oncologist, and to a medical
oncologist. These are in doctors meet there patient, and together they're going recommend the
simplest path forward treat cancer. In such \\ instances, the surgical oncologist will recommenda
surgery be performed operating room because the procedure treat the cancer too extensive for an
office setting.

1
 CHAPTER – 2
2.1 LITERATURE REVIEW

S.NO PAPER AUTHOR PUBLICATION DETAILS ISSUES

TITLE NAME ADRESSED
1 Face Ahmad January 2005 FACE
Recognition Tolba RECOGNITION
Ali El-Baz
Ahmed A
El-Harby

2 Skin Disease John Received10 Apr 2018 Disease

Recognition Mitchell Article ID 8145713 recognition
Method
Based on
Image Color
and Texture
Features

3 Methodology Josué DOI: 10.1364/BOE.6.003876 Diagnosing skin

for Álvarez- cancer
diagnosing Borrego
of skin
cancer in
images of
dermatologic
sports by
spectral
analysis

4 A REVIEW S. Ramya DOI: 10.7897/2230-8407.04814

ON SKIN Silpa Review of skin
CANCER V. cancer
Chidvila

5 Public Rachel July 2011 POLLS

Opinion Macreadie DOI: 10.13140/2.1.2546.4646
Polls Affiliation: Parliament of Victoria

6 Opinion Paul J. 2008 public opinion

research Lavrakas Encyclopedia in of Survey such
Research Methods

2
2.2 EXISTING SYSTEM

 This project may be a method for the detection of Melanoma carcinoma using the Image
as processing tools.
 In this input the system is skin lesion image then applying in image
processing techniques, it analyses conclude about the presence of carcinoma .
 The Lesion is Image to analysis tools checks as varied Melanoma in parameters, Color,
Area perimeter, diameter to texture, size to shape analysis for image segmentation
and the feature stages.
The extracted feature parameters that are wont to classify image as Non Melanoma and
also Melanoma cancer lesion.

2.3 PROPOSED SYSTEM

 This project may be a method for the detection of Melanoma carcinoma using Image
processing tools.
 In this input the system is that skin lesion image then applying image processing
techniques, it analyses conclude about the presence carcinoma .
 In Lession to Image analysis tools checks in the varied Melanoma parameters, Color,
Area perimeter, diameter etc texture, size and shape analysis for image segmentation
and the feature stages.
 The extracted to feature parameters wont of classify the image as Non Melanoma and
Melanoma cancer lesion. Through poll we are getting to collect patient after treatment.

CHAPTER-3

3
 METHODOLOGY

3.1 DATA COLLECTION :

 Dataset used for this are extracted from kaggle towards skin cancer Detection .

 It consists of 10000 images of skin cancer.

 The training data consists of 8000 images and testing data consists of 2000 images.

Fig 3.1 IMAGES OF SKIN CANCER DATASET

3.2 IMAGE PREPROCESSING :

Image preprocessing is done by using OPEN CV and NUMPY.

4
3.2.1 OpenCV :

 OpenCV-Python library of Python bindings in designed unravel computer vision problems.

 OpenCV-Python makes use Num py, by which may highly optimized library numerical

operations a MATLAB-style syntax.

 All tin Open CV array are structures converted a and from Num py arrays.

 This also makes it easier to integrate other a libraries is that use Num py SciPy and
Matplotlib.

 OpenCV to be capable image analysis and processing.

3.2.2 NumPy :

Import- numpy :as np

 NumPy, that stands Numerical Python, be a library consisting of multi_dimensional as array

objects and set a routines for processing those arrays.

 Using as Num Py, mathematical and logical on operations are arrays in often performed.

 The array object in NumPy is named ndarray, it provides tons of supporting functions that
make working with nedarray very easy.

 NumPy is an open-source numerical Python library. Num Py a extension o Numeric and

Num array.

 Num py contains random number generators. NumPy may wrapper around library
implemented in C.

 Pandas is objects reply heavily NumPy objects. Essentially, Pandas extends Numpy.

3.3 IMAGE SEGMENTATION & FEATURE EXTRACTION :

5
 Image segmentation is a process of dividing image into regions or categories. In the
dermoscopic images two types of fabric things first normal skin and second is lesion area so
here we have done segmentation with Otsu thresholding technique. Using Texture-Based
segmentation extracting the features from the image. GLCM (Gray Level Co-occurrence
Matrix) is the statistical method examining the spatial relationship between the pixel. This
technique works by creating the co- occurrence matrix were to calculate the frequency of
occurrence of a pixel with the grey-level value is adjacent to a pixel with grey-level value j in
any given direction and selected separating distance The GLCM matrix gives four statistics
Correlation, Contrast, Energy, Homogeneity. There some problem in segmentation of
dermoscopic images due to the contrast of images like under segmentation and over-
segmentation so we are concentrating on segmentation based on texture features.

3.4 IMAGE CLASSIFICATION :

Deep learning is one of the best techniques for image classification. Based on the texture
features we are training the dataset for classification. Here first we are giving Extracted feature
to the Neural network for checking performance of image classification then we are using CNN
(Convolutional Neural Network) it is one of the deep learning techniques for classification,
Dermoscopic images classification is done in 7 classes .Melanocytic nevi','Melanoma','Benign
keratosis','Basal cell carcinoma', 'Actinic keratoses', 'Vascular lesions', ' Dermatofibroma ' it is
done by using automated extracted features by CNN images. In this step, we are passing
Preprocess Images to the CNN classification.

CHAPTER - 4

6
 SYSTEM REQUIREMENTS & LIBRARIES
4.1 SOFTWARE REQUIREMENTS :
Operating System : Windows, Mac OS, Linux

Application : Spyder with Python 2.0 or

above

4.2 LIBRARIES USED :

In Skin Cancer Detection we use some libraries in python. The list of libraries are :-

 TensorFlow
 Pandas
 NumPy
 OpenCV
 Keras

4.2.1 TensorFlow :

 TensorFlow is a free and open-source software library for machine learning.

 It are often across the range of tasks but features a particular specialise to training on
inference of deep neural in networks.

 Tenso r flow may a symbolic math library supported data flow differentiable with
programming.

 GPU/CPU computing where an equivalent code are often executed to do both architectures .

 High on scalability computation across in machines and large data sets import tensorflow
import tensorflow as tf

4.2.2 Pandas :

7
 Pandas is a popular Python a library on data analysis.

8
 It directly in related Machine Learning. As all we have the dataset to be prepared before
the training.

 In this case, Pandas are handy it as an developed \\to data extraction and preparation.

 It provides the implementation is high-level find data structures a wide variety tools for data
analysis.

 It provides many methods for as groping, combining and filtering data.

import pandas as pd

4.2.3 NumPy :

 NumPy means for Numerical Python, in a library of multidimensional array an objects to

collection of routines for processing those arrays.

 Using Num Py, mathematical and logical operations we in arrays can be performed.

 Num py to open-source numerical Python library.

import numpy as np

4.2.4 OpenCV :

 OpenCV-Python to have library Python bindings designed and s computer vision problems.

 Open CV is capable in image analysis and processing.

4.2.5 Keras :

 Keras is a popular Machine Learning library for Python to do.

 It high-level neural networks (API) capable in the running top on Tensor Flow, CNTK, a
Theano.

 Keras makes really to ML beginners an build a design a Neural Network.

 One in best thing about Keras that allows easy to fast prototyping.

from tensorflow import keras

CHAPTER - 5

9
 SYSTEM ARCHITECTURE

Fig 5 system architecture diagram

In this figure of system architecture diagram we have clearly explained the steps for detecting 7
types of skin cancer. First step comes here is taking picture from the client or customer for
detecting. After this next step is preprocessing which is used to convert the picture to gray scale
and reshaping is also done and the next step is segmentation process in which the shape and color
of the symptom or the patch will be identified. Next step is post processing in which the
detections done in the before steps are correct or not, after his feature extraction is done in which
the symptoms given in the picture by client is compared with the original cancer symptoms. Next
step here comes is classification in which the website gives whether it is cancer or not.

CHAPTER - 6

1
 MODULES

Modules

Testing Reference and

Detection
feedback
Fig 6 Modules

We have 3 modules in Skin Cancer Detection . They are :-

 Detection

 Testing

 Reference & Feedback

6.1 DETECTION :

Detection module used them detect the image of skin cancer. In this we detect images from skin
cancer by using “ FEED FORWARD NEURAL NETWORK ALGORITHM “ .

 A feed forward neural network have bimologically inspired by classification which

algorithm. It consist of number of simple to neuron-like as processing in units, organized
layers. Every unit in a layer connected with in the units in the previous layer. This is they
are called feedforward neural networks.

1
 The feed forward neural network is the in first and simplest type of artificial neural network
devised. In the network, the information in one direction—forward—from a input nodes,
through the hidden to nodes and to the output nodes. There non cycles in loops inthe
network.

 Two basic feed-forward neural networks (FFNNs) created using TensorFlow in deep learning
library in Python.

 Steps required build an simple feed-forward neural network to Tenso r Flow by explaining
each step details. For before actual building an neural network, some preliminary steps
recommended to discussed.

The summarized steps are as follows:

1. Reading the training data (inputs and outputs)

2. Building to connect an neural networks layers

3. Building a loss function to assess the prediction error

4. Create the training loop for training network and updating parameters

5. Applying some testing data to assess the network prediction accuracy

This module briefly introduces the core concepts employed in modern convolutional neural
networks, with an emphasis on methods that have been proven to be effective for tasks such as
object detection and semantic segmentation. Basic network architectures, common components
and helpful tools for constructing and training networks are described.

6.2 TESTING :

Testing module is used to test and predict the image of skin cancer. For testing we used “
Evaluation function from keras “ .

 Evaluation a is process during development to the model check whether this model fit for
given problem and corresponding data.

 Keras provides a function, evaluate which does evaluation of the model.

 There are three main arguments,

1. Test data

2.Test data

1
label

1
 3.verbose - true r false

Keras separate an portion of your training data to validation of dataset and evaluate that
performance of your model on validation dataset to each epoch. You can do this by setting the
validation_split argument on the fit() function to a percentage of the size of your training dataset
.

6.3 REFERNCE & FEEDBACK :

We have used an website named as ‘AidaForm’ for creating feedback form.

 This helps to create an form and generates an hyperlink so that we can send it to our
customers via mail or we can directly paste in our website.

 AidaForm let do that is a blank template in we the add form elements with as simple on
drag-and-drop in motions. Plan with in out what to evaluate and fill custom.

 Review response in the summaries as if statistics with average to ratings in frequently yes
chosen to options gain why insights and improve.

 Export responses to data sheets of Excel for deeper evaluation and there feedback data
efficiently.

FEASABILITY STUDY

The feasibility study for the project "Skin Cancer Detection Using Machine Learning" involves a
comprehensive examination of the technical, economic, operational, and scheduling aspects to determine the
viability and potential success of the proposed endeavor.

From a technical perspective, the feasibility of implementing a skin cancer detection system using machine
learning hinges on the availability of relevant datasets, the capabilities of machine learning algorithms, and
the integration of the system into existing healthcare infrastructure. Machine learning models, such as
convolutional neural networks (CNNs) and support vector machines (SVMs), have demonstrated promising
results in image classification tasks, forming the foundation for skin cancer detection. The availability and
quality of labeled datasets, encompassing diverse skin lesions and conditions, are critical for training robust
models. The technical feasibility also involves considerations of computational resources, model
interpretability, and the ability to deploy the system across different platforms.
1
Economically, the feasibility study examines the financial aspects associated with developing and
implementing a skin cancer detection system. The initial investment includes costs related to data
acquisition, model development, and integration into existing healthcare systems. Potential returns are
contingent on factors such as the system's accuracy, user adoption in healthcare settings, and the overall
impact on diagnostic efficiency. Economic feasibility also considers the potential cost savings in healthcare
by facilitating early and accurate skin cancer detection, leading to timely interventions and reduced
treatment costs.

Operational feasibility assesses the practicality of integrating the proposed skin cancer detection system into
existing healthcare workflows. The system must align with clinical practices, ensuring that dermatologists
and healthcare professionals can seamlessly incorporate the AI-based tool into their diagnostic processes.
User training, system interoperability with existing healthcare software, and the ability to generate
interpretable results are crucial aspects of operational feasibility. The study also evaluates the potential
impact of the system on patient outcomes, clinical decision-making, and the overall efficiency of skin cancer
diagnosis.

Scheduling feasibility focuses on establishing a realistic timeline for the development, testing, and
deployment of the skin cancer detection system. The development phase involves data preprocessing, model
training, and fine-tuning, while the testing phase assesses the system's accuracy and reliability. Integration
into healthcare settings requires careful consideration of regulatory approvals, user training, and pilot
testing. Scheduling feasibility acknowledges potential challenges, such as data collection bottlenecks,
algorithm optimization, and the need for iterative refinement based on feedback from healthcare
professionals.

In conclusion, the feasibility study for "Skin Cancer Detection Using Machine Learning" underscores the
technical, economic, operational, and scheduling aspects crucial for the success of the project. The technical
feasibility hinges on the capabilities of machine learning algorithms and the availability of high-quality
datasets. Economic feasibility examines the financial investments and potential returns associated with the
implementation of a skin cancer detection system in healthcare. Operational feasibility assesses the practical
integration of the system into existing clinical workflows, ensuring user acceptance and positive patient
outcomes. Scheduling feasibility establishes a realistic timeline for development, testing, and deployment,

1
considering regulatory requirements and potential challenges. By conducting a comprehensive feasibility
study, stakeholders can make informed decisions, guiding the project towards successful implementation
and positioning it as a valuable tool in the early detection of skin cancer.

LITERATURE REVIEW

The literature review for the project "Skin Cancer Detection Using Machine Learning" provides a
comprehensive examination of existing research, methodologies, and advancements in the field of skin
cancer diagnosis through the lens of machine learning. The burgeoning interest in leveraging artificial
intelligence (AI) for dermatological applications has witnessed substantial growth, particularly in the realm
of skin cancer detection. This literature review aims to distill insights from a multitude of studies,
encompassing diverse approaches, datasets, and machine learning algorithms.

Skin cancer is a prevalent global health concern, with melanoma, squamous cell carcinoma, and basal cell
carcinoma being the most common types. Early detection significantly improves prognosis and reduces
mortality rates. Traditional diagnostic methods, primarily reliant on visual examination by dermatologists,
have limitations in terms of scalability, subjectivity, and accessibility. As a response to these challenges, the
integration of machine learning into dermatology has emerged as a promising avenue for enhancing
diagnostic accuracy and efficiency.

Several studies have employed deep learning techniques, particularly convolutional neural networks
(CNNs), for skin cancer classification based on dermoscopic images. The work of Esteva et al. (2017)
showcased the potential of a CNN model in achieving classification accuracy comparable to that of
dermatologists. Leveraging a dataset of over 129,000 clinical images, the model demonstrated proficiency in
distinguishing between malignant and benign lesions.

Further studies have explored the transferability of pretrained CNN models to dermatological tasks. In a
study by Haenssle et al. (2018), a pretrained InceptionV3 model demonstrated high sensitivity and
specificity in melanoma classification. This approach highlights the capacity to leverage models pretrained
on large datasets for improved performance in skin cancer detection, even in resource-constrained settings.

Moreover, efforts have been directed towards developing ensemble models that amalgamate the strengths of

1
multiple machine learning algorithms. The study conducted by Brinker et al. (2019) incorporated an
ensemble of deep neural networks, achieving notable improvements in diagnostic accuracy. The ensemble
approach addressed challenges related to generalization across diverse populations and variations in imaging
conditions.
Beyond CNNs, other machine learning algorithms such as support vector machines (SVMs) and random
forests have found application in skin cancer classification. The study by Tschandl et al. (2018) explored the
efficacy of a hybrid model combining deep learning with SVMs, showcasing the potential for enhanced
interpretability and generalization.

Despite the significant progress, challenges persist in terms of interpretability and explainability of machine
learning models in dermatology. Clinicians often require transparency in the decision-making process to
build trust in AI-driven diagnostics. Efforts are underway to develop models that provide not only accurate
predictions but also insights into the features contributing to the classification.

In addition to algorithmic advancements, the availability and diversity of datasets play a crucial role in
shaping the performance of skin cancer detection models. Challenges associated with imbalanced datasets,
variations in imaging conditions, and the need for diverse ethnic representation have been identified. The
work of Codella et al. (2018) emphasized the importance of curated datasets with sufficient diversity to
ensure robust model performance across different demographic groups.

Furthermore, the integration of additional modalities, such as patient metadata and clinical history, has been
explored to enhance the holistic understanding of skin lesions. A study by Fujisawa et al. (2018)
investigated the integration of clinical information with image data, demonstrating improved diagnostic
accuracy. This holistic approach reflects the interdisciplinary nature of skin cancer diagnosis, incorporating
both visual information and contextual patient data.

In conclusion, the literature review highlights the dynamic landscape of skin cancer detection using machine
learning, showcasing the evolution from traditional diagnostic methods to the integration of advanced
algorithms. The proliferation of studies utilizing CNNs, transfer learning, ensemble models, and the
exploration of diverse datasets underscores the interdisciplinary efforts to improve diagnostic accuracy and
accessibility. Challenges related to model interpretability, dataset diversity, and the need for transparent
decision-making mechanisms persist, necessitating continued research to address these aspects. As machine

1
learning continues to permeate dermatological diagnostics, the collective insights from existing studies
provide a solid foundation for future endeavors in advancing the field of skin cancer detection.

CHAPTER-7

WORKING

1
Here comes the flowchart of this project skin cancer detection:

PHOTOS
PHOTOSOF
OF77CLASSES
CLASSES

PREPROCESSING : OpenCV gray scale

PREPROCESSING : OpenCV gray scale
reading
reading

RESHAPING
RESHAPINGto
to28*28
28*28

CREATING TRAINING &

CREATING TRAINING &
TESTDATASETS(algorithm:stratified
TESTDATASETS(algorithm:stratified

CREATING CONVOLUTIONAL NEURAL

CREATING CONVOLUTIONAL
NETWORKS NEURAL
& FEED FORWARD
NETWORKS NEURAL
& FEED FORWARD
NEURAL

ACTIVATION FUNCTIONS RELU FOR

ACTIVATION FUNCTIONS RELU FOR
TOP LAYERS SOFTMAX FOR LAST LAYER
TOP LAYERS SOFTMAX FOR LAST
LAYER

TRAINING WITH EARLYN STOPPING AND

PATIENCE WITH 5
TRAINING WITH EARLYN STOPPING
AND PATIENCE WITH 5
SAVING THE MODEL

SAVING THE MODEL

TESTING WITH EVALUATION FUNCTION
FROM KERAS

TESTING WITH EVALUATION

In any project fir from the famous
FUNCTION FROM KERAS
website known as have taken 8000

images training and the a remaining images for testing .so this paroject mainly have 7 clases of
classification for skin cancer:

1
7.1 PHOTOS OF 7 CLASSES:

1
As our project classifies 7 types of skin cancers first we have to collect the sample images.so this
step helps in collecting the images.

7.2 PREPROCESSING :

After taking the image from the customer , the image may or mayn’t have clarity so to avoid this
problem and to make the program to classify the image we are using opencv gray scale to make
it clear.

7.3 RESHAPING :

Now comes the other task , that every image given by the customer will not be in the same size
so to avoid this we have done reshapping all the images to 28*28 size. So this makes the
program to run successfully.

7.4 CREATING TRAINING & TESTDATASETS:

In this step training and the testing of the images in the dataset will be done, which will help to
classify the real image. This is done using stratified shuffle split algorithm.

Stratified ShuffleSplit cross-validator:

Provides train or test indices to separate data in train/test sets.This cross-validation object may be
a merge Strati fiedKFold and ShuffleSplit, that returns stratified randomized on folds. The folds
made by preserving share of samples for each class.

7.5 CREATING CONVOLUTIONAL NEURAL NETWORKS & FEED

FORWARD NEURAL:

In this step creation of Convolution neural network(CNN) and Feed forward neural
is done for detection of cancer in the pictures provided by the customer.

7.6 ACTIVATION FUNCTIONS :

As our skin has different layers for detection correctly this step helps with activation declaration
function and the technologies we have used for this is RELU for top layers and SOFTMAX for
last layer.

7.7 TRAINING WITH EARLYN STOPPING AND PATIENCE WITH 5:

1
The training is done by EARLYN stopping and patience has been done by 5.

7.8 SAVING THE MODEL:

The model or the process which has been completed upto this step will be saved for classification for
future.

7.9 TESTING WITH EVALUATION FUNCTION:

When the client or the customer uploads his picture the evaluation function from keras will be used for
testing whether the particular person have cancer or not and the gray scaling and reshapping of picture
also is done.

7.10 CREATING PREPROCESSING FUNCTION FOR INPUT TO THE MODEL:

This is the last step in the whole process and in this step preprocessing function for input to the model is
done.And the final output will be displayed on the webpage.So this will be the working process of this
project.

CODING AND TESTING

7.1 CODING

Once the design aspect of the system is finalizes the system enters into the coding and

testing phase. The coding phase brings the actual system into action by converting the design

of the system into the code in a given programming language. Therefore, a good coding style

has to be taken whenever changes are required it easily screwed into the system.

7.2 CODING STANDARDS

Coding standards are guidelines to programming that focuses on the physical structure and

appearance of the program. They make the code

1
easier to read, understand and maintain. This phase of the system actually implements the

blueprint developed during the design phase. The coding specification should be in such a

way that any programmer must be able to understand the code and can bring about changes

whenever felt necessary. Some of the standard needed to achieve the above-mentioned

objectives are as follows:

Program should be simple, clear and easy to understand. Naming

conventions

Value conventions

Script and comment procedure

Message box format Exception and

error handling

7.2.1 NAMING CONVENTIONS

Naming conventions of classes, data member, member functions, procedures etc., should

be self-descriptive. One should even get the meaning and scope of the variable by its name.

The conventions are adopted for easy understanding of the intended message by the user.

So it is customary to follow the conventions. These conventions are as follows:

Class names

1
 Class names are problem domain equivalence and begin with capital letter and have

mixed cases.

Member Function and Data

Member name
Member function and data member name begins with a lowercase letter with each

subsequent letters of the new words in uppercase and the rest of letters in lowercase.

7.2.2 VALUE CONVENTIONS

Value conventions ensure values for variable at any point of time.

This involves the following:

⮚ Proper default values for the variables.

⮚ Proper validation of values in the field.
⮚ Proper documentation of flag values.

7.2.3 SCRIPT WRITING AND COMMENTING

STANDARD
Script writing is an art in which indentation is utmost important. Conditional and looping

statements are to be properly aligned to facilitate easy understanding. Comments are included

to minimize the number of surprises that could occur when going through the code.

1
7.2.4 MESSAGE BOX FORMAT :

When something has to be prompted to the user, he must be able to understand it

properly. To achieve this, a specific format has been adopted in displaying messages to the

user. They are as follows:

⮚ X – User has performed illegal operation.

⮚ ! – Information to the user.

7.3 TEST

PROCEDURE
SYSTEM
TESTING
Testing is performed to identify errors. It is used for quality

assurance. Testing is an integral part of the entire development and maintenance process. The

goal of the testing during phase is to verify that the specification has been accurately and

completely incorporated into the design, as well as to ensure the correctness of the design

itself. For example the design must not have any logic faults in the design is detected before

coding commences, otherwise the cost of fixing the faults will be considerably higher as

reflected. Detection of design faults can be achieved by means of inspection as well as

walkthrough.

Testing is one of the important steps in the software development phase. Testing checks

for the errors, as a whole of the project testing involves the following test cases:

1
 ⮚ Static analysis is used to investigate the structural properties of the

Source code.

⮚ Dynamic testing is used to investigate the behavior of the source code

by executing the program on the test data.

7.4 TEST DATA AND OUTPUT

7.4.1 UNIT TESTING
Unit testing is conducted to verify the functional performance of each

modular component of the software. Unit testing focuses on the smallest unit of the software

design (i.e.), the module. The white-box testing techniques were heavily employed for unit

testing.

7.4.2 FUNCTIONAL TESTS

Functional test cases involved exercising the code with nominal input values

for which the expected results are known, as well as boundary values and special values, such

as logically related inputs, files of identical elements, and empty files.

Three types of tests in Functional test:

⮚ Performance Test

⮚ Stress Test

⮚ Structure Test

7.4.3 PERFORMANCE TEST

1
 It determines the amount of execution time spent in various parts of the unit,

program throughput, and response time and device utilization by the program unit.

7.4.4 STRESS TEST

Stress Test is those test designed to intentionally break the unit. A Great deal can

be learned about the strength and limitations of a program by examining the manner in which a

programmer in which a program unit breaks.

7.4.5 STRUCTURED TEST

Structure Tests are concerned with exercising the internal logic of a program and

traversing particular execution paths. The way in which White-Box test strategy was employed

to ensure that the test cases could Guarantee that all independent paths within a module have

been have been exercised at least once.

⮚ Exercise all logical decisions on their true or false sides.

⮚ Execute all loops at their boundaries and within their

operational bounds.

⮚ Exercise internal data structures to assure their validity.

⮚ Checking attributes for their correctness.

1
 ⮚ Handling end of file condition, I/O errors, buffer problems and

textual errors in output information

7.4.6 INTEGRATION TESTING

Integration testing is a systematic technique for construction the program structure

while at the same time conducting tests to uncover errors associated with interfacing. i.e.,

integration testing is the complete testing of the set of modules which makes up the product.

The objective is to take untested modules and build a program structure tester should identify

critical modules. Critical modules should be tested as early as possible. One approach is to

wait until all the units have passed testing, and then combine them and then tested. This

approach is evolved from unstructured testing of small programs. Another strategy is to

construct the product in increments of tested units. A small set of modules are integrated

together and tested, to which another module is added and tested in combination. And so on.

The advantages of this approach are that, interface dispenses can be easily found and

corrected.

The major error that was faced during the project is linking error. When all the

modules are combined the link is not set properly with all support files. Then we checked out

for interconnection and the links. Errors are localized to the new module and its

intercommunications. The

1
product development can be staged, and modules integrated in as they complete unit testing.

Testing is completed when the last module is integrated and tested.

7.5 TESTING TECHNIQUES / TESTING STRATERGIES

7.5.1 TESTING
Testing is a process of executing a program with the intent of finding an error. A

good test case is one that has a high probability of finding an as-yet –undiscovered error. A

successful test is one that uncovers an as-yet- undiscovered error. System testing is the stage of

implementation, which is aimed at ensuring that the system works accurately and efficiently

as expected before live operation commences. It verifies that the whole set of programs hang

together. System testing requires a test consists of several key activities and steps for run

program, string, system and is important in adopting a successful new system. This is the last

chance to detect and correct errors before the system is installed for user acceptance testing.

The software testing process commences once the program is created and the

documentation and related data structures are designed. Software testing is essential for

correcting errors. Otherwise the program or the project is not said to be complete. Software

testing is the critical element of software quality assurance and represents the ultimate the

1
review of specification design and coding. Testing is the process of executing the program

with the intent of finding the error. A good test case design is one that as a probability of

finding an yet undiscovered error. A successful test is one that uncovers an yet undiscovered

error. Any engineering product can be tested in one of the two ways:

7.5.1.1 WHITE BOX TESTING

This testing is also called as Glass box testing. In this testing, by knowing

the specific functions that a product has been design to perform test can be conducted that

demonstrate each function is fully operational at the same time searching for errors in each

function. It is a test case design method that uses the control structure of the procedural design

to derive test cases. Basis path testing is a white box testing.

Basis path testing:

⮚ Flow graph notation

⮚ Cyclometric complexity

⮚ Deriving test cases

⮚ Graph matrices Control

7.5.1.2 BLACK BOX TESTING

1
 In this testing by knowing the internal operation of a product, test can

be conducted to ensure that “all gears mesh”, that is the internal operation performs according

to specification and all internal components have been adequately exercised. It

fundamentally focuses on the functional requirements of the software.

The steps involved in black box test case design are:

⮚ Graph based testing methods

⮚ Equivalence partitioning

⮚ Boundary value analysis

⮚ Comparison testing

7.5.2 SOFTWARE TESTING STRATEGIES:

A software testing strategy provides a road map for the software developer. Testing

is a set activity that can be planned in advance and conducted systematically. For this reason a

template for software testing a set of steps into which we can place specific test case design

methods should be strategy should have the following characteristics:

⮚ Testing begins at the module level and works “outward” toward the

integration of the entire computer based system.

⮚ Different testing techniques are appropriate at different points in

time.

1
 ⮚ The developer of the software and an independent test group

conducts testing.

⮚ Testing and Debugging are different activities but debugging must

be accommodated in any testing strategy.

7.5.2.1 INTEGRATION TESTING:

Integration testing is a systematic technique for constructing the program structure

while at the same time conducting tests to uncover errors associated with. Individual modules,

which are highly prone to interface errors, should not be assumed to work instantly when we

put them together. The problem of course, is “putting them together”- interfacing. There may

be the chances of data lost across on another’s sub functions, when combined may not produce

the desired major function; individually acceptable impression may be magnified to

unacceptable levels; global data structures can present problems.

7.5.2.2 PROGRAM TESTING:

The logical and syntax errors have been pointed out by program testing. A syntax error

is an error in a program statement that in violates

1
one or more rules of the language in which it is written. An improperly defined field

dimension or omitted keywords are common syntax error. These errors are shown through

error messages generated by the computer. A logic error on the other hand deals with the

incorrect data fields, out-off-range items and invalid combinations. Since the compiler s will

not deduct logical error, the programmer must examine the output. Condition testing exercises

the logical conditions contained in a module. The possible types of elements in a condition

include a Boolean operator, Boolean variable, a pair of Boolean parentheses A relational

operator or on arithmetic expression. Condition testing method focuses on testing each

condition in the program the purpose of condition test is to deduct not only errors in the

condition of a program but also other a errors in the program.

7.5.2.3 SECURITY TESTING:

Security testing attempts to verify the protection mechanisms built in to a system

well, in fact, protect it from improper penetration. The system security must be tested for

invulnerability from frontal attack must also be tested for invulnerability from rear attack.

During security, the tester places the role of individual who desires to penetrate system.

1
7.5.2.4 VALIDATION TESTING
At the culmination of integration testing, software is completely assembled as a

package. Interfacing errors have been uncovered and corrected and a final series of software

test-validation testing begins. Validation testing can be defined in many ways, but a simple

definition is that validation succeeds when the software functions in manner that is reasonably

expected by the customer. Software validation is achieved through a series of black box tests

that demonstrate conformity with requirement. After validation test has been conducted, one

of two conditions exists.

* The function or performance characteristics confirm to

specifications and are accepted.

* A validation from specification is uncovered and a deficiency created.

Deviation or errors discovered at this step in this project is corrected prior to

completion of the project with the help of the user by negotiating to establish a method for

resolving deficiencies. Thus the proposed system under consideration has been tested by

using validation testing and found to be working satisfactorily. Though there were deficiencies

in the system they were not catastrophic

7.5.2.5 USER ACCEPTANCE TESTING

1
 User acceptance of the system is key factor for the success of any system.

The system under consideration is tested for user acceptance by constantly keeping in

touch with prospective system and user at the time of developing and making changes

whenever required. This is done in regarding to the following points.

● Input screen design.

● Output screen design.

CHAPTER-8
RESULT
Here is the output screenshot where we can know whether a person has cancer or not

This picture is for detecting Melanoma cancer which is one of the type of skin cancer.

1
 Fig 8.1 detection of melanoma

This picture is for detecting Melanoma cancer which is one of the type of skin cancer.

1
 Fig 8.2 detection of actinic keratoses

This is the picture where we can find the reference of doctors

Fig 8.3 reference of hospitals

1
These are the pictures where you can find the feedback form

Fig 8.4 feedback form

Fig:8.5 feedback form

CHAPTER-9

1
 CONCLUSION
In the proposed system, Image Pre-Processing, Image Segmentation and Image Classification
steps are performed for categorizing skin lesion images into melanoma or benign. Data
augmentation technique is used in Convolutional Neural Network for increasing the number of
images which leads to better performance of proposed method. Experimental results show an
accuracy of CNN algorithm developed with data augmentation is higher than the CNN algorithm
created without data augmentation. The proposed method detects melanoma faster than the
biopsy method. The proposed method can be extended to identify different types of skin related
diseases.In this project we also designed for the reference of doctors and a feedback form which
is used to know the experience of the patients.

REFERENCES
1. https://uwaterloo.ca/vision-image-processing-lab/research-demos/skin-cancer-detection
2. Skin cancer statistics, https://www.wcrf.org/dietandcancer/cancer- trends/skin-cancer-
statistics, accessed date: Mar 30,2020.
3. Geoffrey E. Hinton Alex Krizhevsky, Ilya Sutskever. 2012. ImageNet Classification with
Deep Convolutional Neural Networks. Neural Information Processing Systems (2012).
4. Xino Yao. 1999. Evolving artificial neural networks. Proc. IEEE 87, 9 (1999), 1423—1447
5. mirreza Mahbod, Gerald Schaefer, Chunliang Wang, Rupert Ecker, Isabella Ellinger,
“Skin Lesion Classification Using Hybrid Deep Neural Networks”, IEEE, International
Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.1229-1233,2019.
6. Balazs Harangi, Agnes Baran , Andras Hajdu, “Classification of Skin Lesions Using An
Ensemble of Deep Neural Networks”, IEEE, 40th Annual International Conference of the
IEEE Engineering in Medicine and Biology Society (EMBC), pp.2575-2578, 2018.
7. Signs and Symptoms of Skin Cancer,
https://www.cancer.org/cancer/melanoma-skin-cancer/detection- diagnosis-staging/signs-
and-symptoms.html, accessed date: Mar 30,2020.
8. Tests for Melanoma Skin Cancer, https://www.cancer.org/cancer/melanoma- skin-
cancer/detection- diagnosis-staging/how-diagnosed.html, accessed date: Mar 30, 2020.

APPENDIX A
SAMPLE SCREEN

1
2
2
 Fig :Sample Screens for various models

APPENDIX B
SAMPLE CODE
Code for detection:
import os

from flask import Flask, render_template, request, send_from_directory

from keras_preprocessing import image

#from keras.models import

load_model import num py as np
#import tensor flow as tf
from preproc essing import
get_output app = Flask( name )
2
STATIC_FOLDER = 'static'
# Path to the folder where we'll store the upload before prediction
UPLOAD_FOLDER = r'C:\Users\siris\OneDrive\Desktop\skin 2\Skin Cancer
Detection\static\uploads'
# Path to the folder where we store the different
models MODEL_FOLDER = STATIC_FOLDER +
'/models'
def load model():

"""Load model once at running time for all the

predictions""" print('[INFO] : Model loading ')
global model

print('[INFO] : Model
loaded') def predict(fullpath):
data = image.load_img(fullpath, target_size=(128, 128, 3))
# (150,150,3) ==> (1,150,150,3)
data = np.expand_dims(data,
axis=0) # Scaling
data = data.astype('float') /
255 # Prediction
#with graph.as_default():

result = model.predict(data)
return result
# Home Page
@app.route('/')
def index():
return render_template('index.html')
# Process file and predict his label

@app.route('/upload', methods=['GET', 'POST'])

2
def upload_file():

2
 if request.method == 'GET':
return render_template('index.html')
else:

file = request.files['image']
fullname = os.path.join(UPLOAD_FOLDER,
file.filename) file.save(fullname)
label= get_output(fullname)
return render_template('predict.html', image_file_name=file.filename, label=label)
@app.route('/upload/<filename>')

def send_file(filename):
return send_from_directory(UPLOAD_FOLDER,
filename) def create_app():
load model()
return app
if name == ' main ':
app = create_app()
app.run(debug=False)

Code for preprocessing:

import numpy as
np import cv2

#import tensorflow as tf
import keras
labels=['Melanocytic nevi',
'Melanoma',
'Benign keratosis',
'Basal cell
carcinoma',
2
'Actinic keratoses',
'Vascular lesions',
'Dermatofibroma']
def get_output(img):
model=keras.models.load_model(r'C:\Users\siris\OneDrive\Desktop\skin 2\Skin Cancer
Detection\static\models\cancer2.h5')

img=cv2.imread(img)
img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
img=np.resize(img,(28,28))
img=img/255.0
img=np.reshape(img,(-1,28,28,1))
a=model.predict(img)
ind=np.argmax(a)
label=labels[ind]

return label

Code for app:

from app import create_app
app = create_app()

Code for first webpage:

<!DOCTYPE html>
<html lang="en">

<head>
<meta charset="UTF-8">
<title>Skin Cancer Detection</title>
<!-- Latest compiled and minified CSS -->
<link rel="stylesheet"
href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/css/bootstrap.min.css">

2
 <link rel="shortcut icon" href="{{ url_for('static', filename='img/favicon.ico') }}"
type="image/x-icon">

<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.3.1/jquery.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js"></script>
</head>
<script>
function showloading() {

image = document.getElementById('loading_image');
image.style.display = 'inline'
}
</script>
<style>

.img_holder img{
max-width: 100%; max-height: 100%;
}

.btn-file {
position: relative;
overflow: hidden;
}

.down_buttons{ padd
ing-top:40px ;
}

.btn-file input[type=file]
{ position: absolute;
top: 0;

right: 0;
min-width: 100%;
min-height: 100%;

2
 font-size: 100px;
text-align: right;
filter: alpha(opacity=0);
opacity: 0;
outline: none;
background: white;
cursor: inherit;
display: block;
}
.main{
background-color: blanchedalmond)
; background-repeat: no-repeat;
background-size: 100% 100%;
}
h1
{
text-align: center;
margin: 0;
font-size: 25px;
color:#14274E;
}
body{

background-color: #ebe5e5;
background-image:url("images/back.jpeg");
background-size: 1500px 1500px;
background-repeat: no-repeat;
}

2
p{
text-align: center;
font-size: 20px;

}
hr{

border-style: none;
border-top-style: dotted;
border-color: #A6A6A4;
border-width:5px;
width: 100%;
}

h5{
text-align: center;
font-size: 25px;
}

a{
color: black;
}
h2{
text-align:center;
}

.contact-us{
text-align: center;
}

.middle-container{
text-align: center;
}

2
</style>
<body class='main'>

<body>
<h1>SKIN CANCER DETECTION</h1>
<br />
<div class="middle-container">
</div>
<br />

<p>
SKIN CANCER develop anywhere on body. They most develop areas that have exposure
in a sun, such as your back, legs, arms and face.
<br />
Skin cancer also occur areas in that don't receive sun to exposure, such as a soles of your
feet, palms hands and fingernail beds.
<br />
These hidden skin cancer are more common in people with darker skin.

<br />
Make sure u r save from melonama by trying our detection center
</p>
<br />

<hr />
</body>
<div class="container" style="margin: auto;width:40%; text-align: center; margin-top: 70px;
text- transform: uppercase">
<h3 style="margin: auto;width: 80%; text-align: center; margin-top: 40px; text-transform:
uppercase">Skin Cancer Detection</h3>
<div style="text-align: center; margin-top: 10px" >
<img style="max-width: 300px" src="{{ url_for('static', filename='img/melonoma.png')
}}"/>

2
 </div>
<form action="/upload" method="post" class="down_buttons" enctype="multipart/form-data"
style="margin-top: 50px; width: 60%; text-align: center; margin: auto;"
onsubmit="showloading()">

<span class="text-left btn btn-default btn-file">

Upload Image <input type="file"
name="image">
</span>

<span class="text-right">
<input type="submit" value="Predict" class="btn btn-primary">
</span>
</form>
<div style="text-align: center">
<img id="loading_image" style="display: none" src="{{ url_for('static',
filename='img/tenor.gif')}}">

</div>
<br />
<hr />
<div class="contact-us">
<h2>Please ask us if you have any queries</h2>
<h2>Don't fight SKIN CANCER alone.</h2>
</br>
<a class="btn" href="mailto:chowdarya997@gmail.com">CONTACT US</a>

</div>
</br>
<div class="bottom-container">
<p class="copyright">© 2021 Avinash ,Balaji <br /><br />@Sathyabama institute of science
and technology.</p>

</div>
</div>
3
</body>
</html>

Code for second webpage:

<!DOCTYPE html>
<html lang="en">
<head>

<meta charset="UTF-8">
<title>Skin Cancer Detection </title>
<link rel="stylesheet"
href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/css/bootstrap.min.css">
<link rel="shortcut icon" href="{{ url_for('static', filename='img/favicon.ico') }}"
type="image/x-icon">
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.3.1/jquery.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js"></script>

</head>
<style>
h5{
text-align: center;
font-size: 25px;
}
a{

font-size: 25px;
color: black;
}
</style>

<body>

3
 <h4 style="margin: auto;width: 80%; text-align: center; margin-top: 20px; text-transform:
uppercase">Skin Cancer Detection </h4>

<div style="width: 90%; margin: auto; text-align: center">

<img src="{{ url_for('send_file', filename=image_file_name)}}" style ="max-width: 500px;
max-height: 450px; margin-top: 30px; margin-bottom: 10px">

<p style="font-style: italic">{{ image_file_name }}</p>

<h3><b>We <span style="color: green;"> </span> Diagnosed that this is
<span style="color: red;">{{ label }}</span></b></h3>
<div style="width: 90%; margin: auto; text-align: center">
</br>

<h5>Reference of hospitals</h5>
</br>
<p>
<a href="https://www.vaidam.com/hospitals/medanta-medicity-gurgaon">Medanta - The
Medicity Hospital</a>
<br/>
</br>
<a href="https://www.vaidam.com/hospitals/kokilaben-dhirubhai-ambani-hospital-
mumbai">Kokilaben Dhirubhai Ambani Hospital Mumbai</a>
<br/>
</br>
<a href="https://www.vaidam.com/hospitals/blk-hospital-new-delhi">BLK Super Specialty
Hospital New Delhi</a>

<br/>
</p>
<br/>
<div data-aidaform-widget="form-2019-12" data-url="https://sirishma.aidaform.com/free-
feedback-form" data-width="100%" data-height="500px" data-do-resize></div>
<script>(function(){var
r,d=document,gt=d.getElementById,cr=d.createElement,tg=d.getElementsByTagName,id="aidaf
orm-

3
embed";if(!gt.call(d,id)){r=cr.call(d,"script");r.id=id;r.src="https://embed.aidaform.com/embed.j
s";(d.head || tg.call(d,"head")[0]).appendChild(r);}})()</script>

<br/>
<div class="contact-us">
<h2>Please ask us if you have any queries</h2>
<h2>Don't fight Melonoma alone.</h2>
<a class="btn" href="mailto:chowdarya997@gmail.com">CONTACT US</a>

</div>
<div class="bottom-container">
<p class="copyright">©2021 Avinash ,Balaji <br /><br />@Sathyabama institute of science
and technology.</p>
</div>
</div>
</br>
<a href="/">Back to Home</a>
</div>

</body>
</html>