Learning numerical observers using unsupervised domain adaptation

Shenghua He, Weimin Zhou, Hua Li, Mark A. Anastasio

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

Abstract

Medical imaging systems are commonly assessed by use of objective image quality measures. Supervised deep learning methods have been investigated to implement numerical observers for task-based image quality assessment. However, labeling large amounts of experimental data to train deep neural networks is tedious, expensive, and prone to subjective errors. Computer-simulated image data can potentially be employed to circumvent these issues; however, it is often difficult to computationally model complicated anatomical structures, noise sources, and the response of real-world imaging systems. Hence, simulated image data will generally possess physical and statistical differences from the experimental image data they seek to emulate. Within the context of machine learning, these differences between the sets of two images is referred to as domain shift. In this study, we propose and investigate the use of an adversarial domain adaptation method to mitigate the deleterious effects of domain shift between simulated and experimental image data for deep learning-based numerical observers (DL-NOs) that are trained on simulated images but applied to experimental ones. In the proposed method, a DL-NO will initially be trained on computer-simulated image data and subsequently adapted for use with experimental image data, without the need for any labeled experimental images. As a proof of concept, a binary signal detection task is considered. The success of this strategy as a function of the degree of domain shift present between the simulated and experimental image data is investigated.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2020
Subtitle of host publicationImage Perception, Observer Performance, and Technology Assessment
EditorsFrank W. Samuelson, Sian Taylor-Phillips
PublisherSPIE
ISBN (Electronic)9781510633995
DOIs
StatePublished - Jan 1 2020
EventMedical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment - Houston, United States
Duration: Feb 19 2020Feb 20 2020

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume11316
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment
CountryUnited States
CityHouston
Period2/19/202/20/20

Keywords

  • Adversarial learning
  • Image quality assessment
  • Numerical observers
  • Unsupervised domain adaptation

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'Learning numerical observers using unsupervised domain adaptation'. Together they form a unique fingerprint.

  • Cite this

    He, S., Zhou, W., Li, H., & Anastasio, M. A. (2020). Learning numerical observers using unsupervised domain adaptation. In F. W. Samuelson, & S. Taylor-Phillips (Eds.), Medical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment [113160W] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 11316). SPIE. https://doi.org/10.1117/12.2549812