Back
Mitosis detection in breast cancer histology images with deep neural networks.
Journal article

Mitosis detection in breast cancer histology images with deep neural networks.

  • Cireşan DC IDSIA, Dalle Molle Institute for Artificial Intelligence, USI-SUPSI, Lugano, Switzerland. dan@idsia.ch
  • Giusti A IDSIA, Dalle Molle Institute for Artificial Intelligence, USI-SUPSI, Lugano, Switzerland.
  • Gambardella LM IDSIA, Dalle Molle Institute for Artificial Intelligence, USI-SUPSI, Lugano, Switzerland.
  • Schmidhuber J IDSIA, Dalle Molle Institute for Artificial Intelligence, USI-SUPSI, Lugano, Switzerland.
  • 2014-03-01
Published in:
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. - 2013
Algorithms
Biopsy
Breast Neoplasms
Cell Nucleus
Female
Humans
Image Enhancement
Image Interpretation, Computer-Assisted
Microscopy
Mitosis
Neural Networks, Computer
Pattern Recognition, Automated
Reproducibility of Results
Sensitivity and Specificity
English We use deep max-pooling convolutional neural networks to detect mitosis in breast histology images. The networks are trained to classify each pixel in the images, using as context a patch centered on the pixel. Simple postprocessing is then applied to the network output. Our approach won the ICPR 2012 mitosis detection competition, outperforming other contestants by a significant margin.
Language
  • English
Open access status
green
Identifiers
Persistent URL
https://sonar.ch/global/documents/112380
Statistics
Document views: 42 File downloads: