Scribd
Upload
21 views

Skin Cancer Detection Using Tenserflow

The document outlines a project on skin cancer detection using TensorFlow, focusing on implementing a model with transfer learning and EfficientNet architecture. It discusses the importance of early detection of skin cancer, the necessary libraries for data handling, and the general approach for model development and deployment. Challenges such as variability in lesion appearance and ethical considerations are also highlighted, along with a conclusion suggesting exploration of other frameworks for improved results.

Uploaded by

krishanupal22
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
21 views

Skin Cancer Detection Using Tenserflow

The document outlines a project on skin cancer detection using TensorFlow, focusing on implementing a model with transfer learning and EfficientNet architecture. It discusses the importance of early detection of skin cancer, the necessary libraries for data handling, and the general approach for model development and deployment. Challenges such as variability in lesion appearance and ethical considerations are also highlighted, along with a conclusion suggesting exploration of other frameworks for improved results.

Uploaded by

krishanupal22
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/ 13

SKIN CANCER

DETECTION
USING TENSERFLOW
Under The Guidance Of

Mrs Bapita Roy,


HOD Of Electronics & Computer Science,
Guru Nanak Institute Of Technology
Presented By:
• Deepa Saha(501021020003)
• Md. Tarique Khan(501021010006)
• Shankha Deep
Manna(501021010013)
• Somdutta Banerjee(501021020016)
INTRODUCTION

We will learn how to implement a Skin Cancer Detection model


using Tensorflow. We will use a dataset that contains images
for the two categories that are malignant or benign. We will
use the transfer learning technique to achieve better results in
less amount of training. We will use EfficientNet architecture as
the backbone of our model along with the pre-trained weights
of the same obtained by training it on the image net dataset.

04/08/2025 1
WHAT IS SKIN CANCER

Skin cancer is an abnormal growth of skin cells. It is one of the


most common cancers and unfortunately, it can become
deadly. The good news though is when caught early, your
dermatologist can treat it and eliminate it entirely.

04/08/2025 2
LIBRARY FUNCTIONS
• Import Libraries-Python libraries make it very easy for us to handle the data and
perform typical and complex tasks with a single line of code.
• Pandas-This library helps to load the data frame in a 2D array format and has multiple
functions to perform analysis tasks in one go.
• Numpy- Numpy arrays are very fast and can perform large computations in a very short
time.
• Matplotlib- This library is used to draw visualizations.
• Sklearn- This module contains multiple libraries having pre-implemented functions to
perform tasks from data preprocessing to model development and evaluation.
• Tensorflow- This is an open-source library that is used for Machine Learning and Artificial
intelligence and provides a range of functions to achieve complex functionalities with
single lines of code.

04/08/2025 3
GENERAL APPROACH
• Data Acquisition and Preprocessing Dataset: Gather a diverse dataset of
skin lesion images, including both benign and malignant cases. Popular
datasets include the HAM10000 dataset.
• Data Augmentation: Apply techniques like rotation, flipping, and
zooming to increase the dataset's size and diversity, improving model
generalization .
• Image Preprocessing: Normalize pixel values, resize images to a
standard size, and convert them into a suitable format for model input.

04/08/2025 4
ALGORITHMS
• Step 1: Set Up Google Collab.
• Step 2: Import Necessary Libraries.
• Step 3: Load and Prepare the Dataset.
• Step 4: Preprocess Images.
• Step 5: Create the Model.
• Step 6: Train the Model.
• Step 7: Evaluate the Model.
• Step 8: Save the Model.
• Step 9: Predict on New Images. 04/08/2025 5
MODEL ARCHITECHTURE

• Convolutional Neural Network (CNN): A CNN is well-suited for


image classification tasks. It extracts relevant features from
the input images through convolutional layers, pooling layers,
and fully connected layers.
• Transfer Learning: Utilize pre-trained models like ResNet,
Inception, or VGG16 as the base architecture. Fine-tune these
models on the skin cancer dataset to adapt them to the
specific task.

04/08/2025 6
MODEL DEPLOYMENT

• Deployment Platform: Deploy the trained model on a suitable


platform, such as a web application, mobile app, or cloud-
based service.
• Interface: Design a user-friendly interface for users to upload
skin lesion images and receive predictions.

04/08/2025 7
CHALLENGES
• Variability in Lesion Appearance: Skin lesions can exhibit
significant variations in color, size, and shape, making
accurate classification challenging.
• Imbalanced Datasets: Real-world datasets often have an
imbalance between benign and malignant cases, which can
bias the model.
• Ethical Considerations: Deploying AI-powered skin cancer
detection systems requires careful consideration of ethical
implications, including potential biases and the impact on
patient care 04/08/2025 8
CONCLUSION
Although TensorFlow performs well enough in the skin cancer
detection model, it has its own disadvantages like the use of
high computational power or the use of large amounts of
memory. Thus, trying out other frameworks like PyTorch, Keras
and MXNet, etc would not be a bad idea in order to explore
even more possibilities in the field of skin cancer detection
using machine learning.

04/08/2025 9
THANK YOU

You might also like