Inspiration
Lung cancer is a widespread and deadly disease that often goes undetected until its advanced stages, when treatment options become limited. Early detection is a critical factor in improving patient outcomes and increasing survival rates. By developing an accurate and efficient lung cancer detection system, the project aims to save lives and improve the quality of life for those diagnosed with the disease.
What it does
our project has 2 models , first model diagnosis lung cancer in early stages and the second model classifies it further into subtypes of lung cancer namely, adenocarcinoma, squamous cell carcinoma, large cell carcinoma by image processing(dataset used are CT scans ). The second model is also capable of distinguishing the CTscan of a normal person.
How we built it
We have built these models with the application of machine learning, deep learning (CNN-convolution neural networking) and image processing using tensorflow and keras
Challenges we ran into
Dataset for CT scans were limited , therefore it was a huge challenge to train a CNN model.
Accomplishments that we're proud of
Despite of challenges , we have successfully trained both the models with astonishing accuracies of 98.4% and 99.6% respectively
Built With
- ai
- cnn
- deep-learning
- google-colab
- kaggle
- machine-learning
- matplotlib
- model
- numpy
- pandas
- python
- seaborn
Log in or sign up for Devpost to join the conversation.