Android Based Lung Cancer Detection Using Machine Learning

Lung cancer is one of the dangerous and life taking disease in the world. However, early diagnosis and treatment can save life. Although, CT scan imaging is best imaging technique in medical field but it is difficult for doctors to interpret and identify the cancer from CT scan images. Therefore com

Project Title

Android Based Lung Cancer Detection Using Machine Learning

Project Area of Specialization

Artificial Intelligence

Project Summary

Lung cancer is one of the dangerous and life taking disease in the world. However, early diagnosis and treatment can save life. Although, CT scan imaging is best imaging technique in medical field but it is difficult for doctors to interpret and identify the cancer from CT scan images. Therefore computer aided diagnosis can be helpful for doctors to identify the cancerous cells accurately.

Hence, in this study an android base lung cancer detection system using machine learning with various image processing technique such as image pre-processing, segmentation and feature extraction, will be used to detect and classify the presence of lung cancer in a CT- images. A CT scan image will be captured or can be uploaded into a proposed system and it will detect a cancer and classify it into different stages.

Project Objectives

The objective of project is to give user a graphical user interface in which a CT scan image is captured or uploaded. Then various image procesing techniques and machine learning will be applied on it. It display the features and cancer stage. This system can help in early detection of lung cancer more accurately.

Project Implementation Method

Our proposed model is android base which classifies a lung cancer into its different stages like Stage I, II, III, IV. For implementation of our proposed model, CT images will be captured or uploaded in a system and it will detect a cancer and classify it into different stages. The process involves

1.Image Acquiring:

CT images of patient will be obtained from Lung Image Database Consortium (LIDC), a database of lung cancer screening CT images. We will also visit the hospitals to obtain CT images.

2. Preprocessing: - Some noises are embedded on CT scan image which causes false detection of nodules. So, to remove this we use two methods in this step

Median Filter: Median Filter is a non-linear digital filter use to remove salt and pepper noise from an image without ruining the edges of an image by blurring it.

Gaussian Filter: Median filter removes only salt and pepper from the image but cannot remove speckle noise so to remove speckle noise and smooth the image we use Gaussian filter.

3. Segmentation: - In this process image is partitioned into different segments to make extracted2.image easier to analyze. In our system it segments the cancer nodule from CT scan images. For this purpose we implement Watershed Algorithm, used to identify and separate the touching object of an image which helps to segment the cancer nodules properly if it is touching the false nodule.

4. Feature Extraction: - Feature extraction is an essential stage that represents the final results to determine the normality or abnormality of an image. In this stage, features like area, perimeter, centroid, diameter, eccentricity and Mean intensity are extracted. These features later on are used as training features to develop classifier.

5. Classification: This stage evaluates the nodule size and divides the classified nodule into different stages like Stage I, II, III, IV.  Support vector machine (SVM) is used as classifier. It is supervised machine learning method 

Benefits of the Project

•  Assist radiologists and doctors detect the cancer accurately.
• Eliminate lenghty detection procedures.
• Assists patient to read their CT scan images.
• Saves time of doctors and radiologist.
• Help medical students.

Technical Details of Final Deliverable

User capture or upload a picture of CT scan image  into a system's graphical user interface. Various image processing technique such as image pre-processing, segmentation and feature extraction, will be used to detect the presence of lung cancer in a CT- images. The detected lung cancer nodule will then be classified into different stages i.e Stage I, Stage II, Stage III & Stage IV  and display the features and cancer stage. This system can help in early detection of lung cancer more accurately. 

Final Deliverable of the Project

Software System

Core Industry

Medical

Other Industries

IT , Health

Core Technology

Artificial Intelligence(AI)

Other Technologies

Others

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com