You are on page 1of 8

1 DEEP LEARNING BASED LUNG CANCER DETECTION SYSTEM

RAJKIYA ENGINEERING COLLEGE , KANNAUJ


DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

Project Guide – Submitted by-


Dr. B.D.K Patro Anuj Kumar
H.O.D of C.S.E. Department 1908390100019
REC Kannauj
2 INDEX
1. Introduction
2. Methodology
3. Dataset
4. Implementati
on
5. Future work
3 INTRODUCTION
 Today, Lung Cancer is considered to be most serious disease in consideration for death rates.
 Cancer which begin to grow uncontrollably in the lungs is known as lung cancer.
 CT imaging are reliable for lung cancer diagnosis because it can suspected lung cancer nodules .
 Image Processing and deep learning techniques has been implemented to detect and classify the lung cancer.
 Lung cancer research can help develop better treatments, increasing the survival and quality of life for
patients.

NON- CANCEROUS CANCEROUS


4 PROJECT OVERVIEW
Create a system that
detects and classify
Lung Cancer using CT
Scan images.

By Using
CNN (Convolutional Neural
Network) model with the
help of Deep Learning.
5
METHODOLOGY

Image Pre- Feature


from processing extraction
database

Lung cancer YES


detected
Lung
Classify by
cancer
CNN
No lung detection
cancer
detected
model
NO
6 DATASET
❑ Data has been collected from this https://www.kaggle.com/datasets/mohamedhanyyy/chest-
ctscanimages/website.[3]
❑ This dataset used for training and testing CNN (convolutional neural network) model for lung cancer
detection .
❑ For preprocessing dataset is further split into 70% training set to train our model and 20 % testing set
to evaluate performance and 10% for validation.
❑ Data contain 3 lung cancer types which are Adenocarcinoma, Large cell carcinoma, Squamous cell
carcinoma , and 1 folder for the normal cell.
7 IMPLEMENTATION
 Import python libraries make it very easy for us to handle the data and perform typical and
complex tasks with a single line of code.
such as Numpy, Pandas, Tensorflow, matplotlib etc.
 Apply Data Augmentation technique for preprocessing the data.
 Use the TensorFlow library to build CNN model and Keras framework of the tensor flow
library contains all the functionalities that one may need to define the architecture of a CNN
and train it on the data.
 While compiling a model we provide these three essential parameters:
 In the future we try to train and test the module by using the above purposed methodology .

FUTURE PLAN
 The main aim of this project is to create web based application for
detection of lung cancer correctly using CT scan images.
8

THANK
YOU

You might also like