Scribd
Upload
14 views

Batch_7

The document outlines a project focused on developing a deep learning-based system for skin cancer detection using dermoscopic images. It aims to improve diagnostic accuracy and reduce manual effort in identifying melanoma, which is responsible for a significant percentage of skin cancer deaths. The implementation includes data preprocessing, model training with CNNs, and deployment as a web application for real-time diagnosis.

Uploaded by

priyasenthilsivanisenthil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
14 views

Batch_7

The document outlines a project focused on developing a deep learning-based system for skin cancer detection using dermoscopic images. It aims to improve diagnostic accuracy and reduce manual effort in identifying melanoma, which is responsible for a significant percentage of skin cancer deaths. The implementation includes data preprocessing, model training with CNNs, and deployment as a web application for real-time diagnosis.

Uploaded by

priyasenthilsivanisenthil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

SKIN CANCER

DETECTION

Under the Guidance of, PRESENTED BY,

Mrs. R.Narmatha, JANANI K S 613521104009


Department of Computer PRIYA S 613521104030
Science and Engineering RAMPRIYAA R 613521104034
AMSAVENI K 613521104301
INTRODUCTION
 Skin cancer is one of the most common cancers worldwide. Using
deep learning, we aim to automate and improve the accuracy of
diagnosis.

OBJECTIVE
 To develop an deep learning-based system that can detect skin
cancer from dermoscopic images with high accuracy.
DOMAIN AREA
 Healthcare Technology (Medical Imaging and Artificial
Intelligence)

PROBLEM
STATEMENT
 Melanoma is a type of cancer that can be deadly if not
detected early.
 It accounts for 75% of skin cancer deaths.
 A solution which can evaluate images and alert the
dermatologists about the presence of melanoma has the
potential to reduce a lot of manual effort needed in diagnosis.
EXISTING SYSTEM
The existing skin cancer detection system is evolving from manual
diagnosis to AI-driven automated systems. While machine learning
models (GLCM) model .

Limitations of the Existing System:


 Limited Features – Captures only texture-based features, missing
complex patterns.
 No Deep Learning – Cannot learn hierarchical features like CNNs.
 Image Sensitivity – Affected by lighting, angle, and skin tone
variations.
 Manual Feature Selection – Requires predefined texture features,
reducing adaptability.
 Struggles with Large Data – Less effective on high-dimensional
datasets compared to deep learning.
PROPOSED IDEA
 The project involves developing a Deep learning model that
classifies skin lesions as benign or malignant based on image
analysis.

The Ideas include :


 For higher accuracy and robustness, CNN-based deep learning
models (like ResNet, VGG, or EfficientNet) are used for skin cancer
detection.
IMPLEMENTATION
Implementation involves:
 Perform data preprocessing, including missing value handling,
feature extraction, and data augmentation.
 Use a Convolutional Neural Network (CNN) or a pre-trained
model (ResNet/VGG16) for classification.
 Evaluate performance using accuracy, precision, recall, and
AUC-ROC.
 Finally, deploy the model as a web app (Flask/Streamlit) for
real-time skin lesion diagnosis.
REQUIREMENTS
SOFTWARE REQUIREMENT
 Programming language : Python
 Library : Flask
 Programming platform :Google Colab

HARDWARE
REQUIREMENT
 Processor - AMD Ryzen 5/7
 RAM - Minimum 4GB
 Storage – 512 GB SSD
BUDGET & COST ESTIMATION

Estimated costs include:


 Cloud computing resources
 Data acquisition
 Model training and storage
 Deployment and maintenance
PROJECT TIMELINE
 Week 1-2: Data Collection
 Week 3-4: Model Training
 Week 5-6: Model Evaluation
 Week 7-8: Deployment and Testing
 Week 9: Final Report and Presentation
REFERENCE

Dataset link :
Skin_cancer_dataset

References:
 MohdAnas, Ram Kailash Gupta, Dr. Shafeeq Ahmad, ”Skin Cancer

Classification Using K-Means Clustering”, International Journal of Technical

Research and Applications, Volume 5, Issue 1, 2017.

 R.S. Shiyam Sundar, M. Vadivel, ‘‘Performance Analysis of Melanoma Early

Detection using Skin Lession Classification System”, International Conference

on Circuit, Power and Computing Technologies [ICCPCT], 2016.

 S. Mohan Kumar, J. Ram Kumar, K. Gopalakrishnan, Skin cancer diagnostic

using machine learning techniques – shearlet transform and naïve bayes

classifier, Int. J. Eng. Adv. Technol. (IJEAT) 9 (2) (2019) 2249–8958.


THANK YOU

You might also like