Skip to content

This project aims to perform binary classification to detect presence of cancerous cells in histopathological scans. The images are taken from the histopathological scans of lymph node sections from Kaggle Histopathological cancer detection challenge and provide tumor visualizations of tumor tissues.

Notifications You must be signed in to change notification settings

rutup1595/Breast-cancer-classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

64 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Breast Cancer Classifications

The proposed methods include Deep Learning based approaches to create classifier frameworks which perform end to end data set manipulation, training, test augmentation and detection.Transfer learning using Resnet and Densenet architectures was performed.Specifically, ResNet50, ResNet152 and DenseNet169 models were tried.

We aim to deal with the various discrepancies in the images and the dataset by taking various data pre processing and augmentation methods. The aim is to perform the classification with high degree of confidence.

These are the histopathological scanned images from the dataset with augmentations.

picture_git

Following are the pictures of the sample images from the dataset with ROI boundaries for negative and positve tumor samples.

roi_sample

About

This project aims to perform binary classification to detect presence of cancerous cells in histopathological scans. The images are taken from the histopathological scans of lymph node sections from Kaggle Histopathological cancer detection challenge and provide tumor visualizations of tumor tissues.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published