Convolutional neural networks for histopathology image classification: Training vs. Using pre-trained networks

Brady Kieffer, Morteza Babaie, Shivam Kalra, H. R. Tizhoosh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We explore the problem of classification within a medical image data-set based on a feature vector extracted from the deepest layer of pre-trained Convolution Neural Networks. We have used feature vectors from several pre-trained structures, including networks with/without transfer learning to evaluate the performance of pre-trained deep features versus CNNs which have been trained by that specific dataset as well as the impact of transfer learning with a small number of samples. All experiments are done on Kimia Path24 dataset which consists of 27,055 histopathology training patches in 24 tissue texture classes along with 1,325 test patches for evaluation. The result shows that pre-trained networks are quite competitive against training from scratch. As well, fine-tuning does not seem to add any tangible improvement for VGG16 to justify additional training while we observed considerable improvement in retrieval and classification accuracy when we fine-tuned the Inception structure.

Original languageEnglish (US)
Title of host publicationProceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
ISBN (Electronic)9781538618417
DOIs
StatePublished - Mar 8 2018
Event7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017 - Montreal, Canada
Duration: Nov 28 2017Dec 1 2017

Publication series

NameProceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017
Volume2018-January

Conference

Conference7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017
Country/TerritoryCanada
CityMontreal
Period11/28/1712/1/17

Keywords

  • CNNs
  • deep features
  • deep learning
  • digital pathology
  • image classification
  • Image retrieval
  • Inception
  • medical imaging
  • VGG

ASJC Scopus subject areas

  • Signal Processing
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Convolutional neural networks for histopathology image classification: Training vs. Using pre-trained networks'. Together they form a unique fingerprint.

Cite this