search

lujian9328 / LungCancerDetection

This project presents the better Computer Aided Diagnosing (CAD) system for automatic detection of lung cancer. The initial process is lung region detection by applying basic image processing techniques such as Bit-Plane Slicing, Erosion, Median Filter, Dilation, Outlining, Lung Border Extraction and Flood-Fill algorithms to the CT scan images. After the lung region is detected, the segmentation is carried out with the help of Mean Shift clustering algorithm. With these, the features are extracted and the diagnosis rules are generated. These rules are then used for learning with the help of Random Forest. The experimentation is performed with 15, 000 images obtained from the kaggle contest. The experimental result shows that the proposed CAD system can able to tell the posterior probability of lung cancer for a patient based on the detection algorithm. Also the usage of Random Forest will increase the accuracy of detecting the cancer nodules.
18 stars 6 forks source link

Some question about the code #1

Open jimingabc opened 6 years ago

jimingabc commented 6 years ago

Hi, thank you for your sharing, I try to run your code ,but I find It cannot process the image in preprocess.m, thus I want to know that if the code can be run directly or some modify is needed.

Hukamar commented 5 years ago

Please, help me with Wireless capsule endoscopy database.

When I tried to download I had " Critical error The registration confirmation email can't be send!" Please, can you shares that dataset with me?

Hukamar commented 5 years ago

Hi, Please, help me with Wireless capsule endoscopy database (https://www.kaggle.com/kiddataset/kid-dataset-2).

When I tried to download I had " Critical error The registration confirmation email can't be send!" Please, can you shares that dataset with me?