Observer variation-aware medical image segmentation by combining deep learning and surrogate-assisted genetic algorithms

Arkadiy Dushatskiy*, Adriënne M. Mendrik, Peter A.N. Bosman, Tanja Alderliesten

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Citations (Scopus)

Abstract

There has recently been great progress in automatic segmentation of medical images with deep learning algorithms. In most works observer variation is acknowledged to be a problem as it makes training data heterogeneous but so far no attempts have been made to explicitly capture this variation. Here, we propose an approach capable of mimicking different styles of segmentation, which potentially can improve quality and clinical acceptance of automatic segmentation methods. In this work, instead of training one neural network on all available data, we train several neural networks on subgroups of data belonging to different segmentation variations separately. Because a priori it may be unclear what styles of segmentation exist in the data and because different styles do not necessarily map one-on-one to different observers, the subgroups should be automatically determined. We achieve this by searching for the best data partition with a genetic algorithm. Therefore, each network can learn a specific style of segmentation from grouped training data. We provide proof of principle results for open-sourced prostate segmentation MRI data with simulated observer variations. Our approach provides an improvement of up to 23% (depending on simulated variations) in terms of Dice and surface Dice coefficients compared to one network trained on all data.

Original languageEnglish
Title of host publicationMedical Imaging 2020
Subtitle of host publicationImage Processing
EditorsIvana Isgum, Bennett A. Landman
PublisherSPIE
Number of pages12
Volume11313
ISBN (Electronic)9781510633933
DOIs
Publication statusPublished - 2020
EventMedical Imaging 2020: Image Processing - Houston, United States
Duration: 17 Feb 202020 Feb 2020

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume11313
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2020: Image Processing
Country/TerritoryUnited States
CityHouston
Period17/02/2020/02/20

Keywords

  • Deep learning
  • Medical image segmentation
  • Observer variation
  • Surrogate-assisted genetic algorithm

Fingerprint

Dive into the research topics of 'Observer variation-aware medical image segmentation by combining deep learning and surrogate-assisted genetic algorithms'. Together they form a unique fingerprint.

Cite this