DeepMammo

DeepMammo

Rashik Kotwal

Rashik Kotwal

Phoenix, Arizona

Convolutional Neural Network and It's Application in Breast tumor Classification

Artificial Intelligence

  • 0 Collaborators

  • 1 Followers

    Follow

Description

  • Rectangle patches that contains the whole tumor region (plus 10% surrounding region) is extracted from each modality and view image
  • All the patches are resized to the same size (224*224) Each patient, 4 images are fed into GoogLeNet, and get 4096 features (1024 for each image) at the last layer
  • Random forest (RF) is implemented to select important features from all 4096 features (based on Gini impurity)
  • 137 features are kept and fed into another RF for final classification into Benign (-) or Malignant (+)
Medium 0 06zzrkrwcvdegvuodn5v2vvft4kxhmhiyfkyear71ew3mvhqjnkrunv7 4de7jdfjv5yoyuokgekoesidsdc2wrwfgexoeaddsdsmkfdtbjdo088ddju0r2pwy

Rashik K. created project DeepMammo

Medium d8823bfd b515 4349 a28e 48cf5336e089

DeepMammo

  • Rectangle patches that contains the whole tumor region (plus 10% surrounding region) is extracted from each modality and view image
  • All the patches are resized to the same size (224*224) Each patient, 4 images are fed into GoogLeNet, and get 4096 features (1024 for each image) at the last layer
  • Random forest (RF) is implemented to select important features from all 4096 features (based on Gini impurity)
  • 137 features are kept and fed into another RF for final classification into Benign (-) or Malignant (+)

No users to show at the moment.