Adaptive Few-Shot Learning PoC Ultrasound COVID-19 Diagnostic System

Michael Karnes, Shehan Perera, Srikar Adhikari, Alper Yilmaz

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

7 Scopus citations

Abstract

This paper presents a novel ultrasound imaging point-of-care (PoC) COVID-19 diagnostic system. The adaptive visual diagnostics utilize few-shot learning (FSL) to generate encoded disease state models that are stored and classified using a dictionary of knowns. The novel vocabulary based feature processing of the pipeline adapts the knowledge of a pretrained deep neural network to compress the ultrasound images into discrimative descriptions. The computational efficiency of the FSL approach enables high diagnostic deep learning performance in PoC settings, where training data is limited and the annotation process is not strictly controlled. The algorithm performance is evaluated on the open source COVID-19 POCUS Dataset to validate the system's ability to distinguish COVID-19, pneumonia, and healthy disease states. The results of the empirical analyses demonstrate the appropriate efficiency and accuracy for scalable PoC use. The code for this work will be made publicly available on GitHub upon acceptance.

Original languageEnglish (US)
Title of host publicationBioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728172040
DOIs
StatePublished - 2021
Event2021 IEEE Biomedical Circuits and Systems Conference, BioCAS 2021 - Virtual, Online, Germany
Duration: Oct 6 2021Oct 9 2021

Publication series

NameBioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings

Conference

Conference2021 IEEE Biomedical Circuits and Systems Conference, BioCAS 2021
Country/TerritoryGermany
CityVirtual, Online
Period10/6/2110/9/21

Keywords

  • COVID-19
  • Deep Neural Networks
  • Few-Shot Learning
  • POC Ultrasound

ASJC Scopus subject areas

  • Hardware and Architecture
  • Biomedical Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Adaptive Few-Shot Learning PoC Ultrasound COVID-19 Diagnostic System'. Together they form a unique fingerprint.

Cite this