Improving CNN Training using Disentanglement for Liver Lesion Classification in CT

Avi Ben-Cohen, Roey Mechrez, Noa Yedidia, Hayit Greenspan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Training data is the key component in designing algorithms for medical image analysis and in many cases it is the main bottleneck in achieving good results. Recent progress in image generation has enabled the training of neural network based solutions using synthetic data. A key factor in the generation of new samples is controlling the important appearance features and potentially being able to generate a new sample of a specific class with different variants. In this work we suggest the synthesis of new data by mixing the class specified and unspecified representation of different factors in the training data which are separated using a disentanglement based scheme. Our experiments on liver lesion classification in CT show an average improvement of 7.4% in accuracy over the baseline training scheme.

Original languageEnglish
Title of host publication2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages886-889
Number of pages4
ISBN (Electronic)9781538613115
DOIs
StatePublished - Jul 2019
Event41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 - Berlin, Germany
Duration: 23 Jul 201927 Jul 2019

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Conference

Conference41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
Country/TerritoryGermany
CityBerlin
Period23/07/1927/07/19

Keywords

  • Disentanglement
  • Liver lesions
  • Medical
  • Synthesis

Fingerprint

Dive into the research topics of 'Improving CNN Training using Disentanglement for Liver Lesion Classification in CT'. Together they form a unique fingerprint.

Cite this