Literature DB >> 34133034

Deep Learning Pitfall: Impact of Novel Ultrasound Equipment Introduction on Algorithm Performance and the Realities of Domain Adaptation.

Michael Blaivas1,2, Laura N Blaivas3, James W Tsung4.   

Abstract

OBJECTIVES: To test deep learning (DL) algorithm performance repercussions by introducing novel ultrasound equipment into a clinical setting.
METHODS: Researchers introduced prospectively obtained inferior vena cava (IVC) videos from a similar patient population using novel ultrasound equipment to challenge a previously validated DL algorithm (trained on a common point of care ultrasound [POCUS] machine) to assess IVC collapse. Twenty-one new videos were obtained for each novel ultrasound machine. The videos were analyzed for complete collapse by the algorithm and by 2 blinded POCUS experts. Cohen's kappa was calculated for agreement between the 2 POCUS experts and DL algorithm. Previous testing showed substantial agreement between algorithm and experts with Cohen's kappa of 0.78 (95% CI 0.49-1.0) and 0.66 (95% CI 0.31-1.0) on new patient data using, the same ultrasound equipment.
RESULTS: Challenged with higher image quality (IQ) POCUS cart ultrasound videos, algorithm performance declined with kappa values of 0.31 (95% CI 0.19-0.81) and 0.39 (95% CI 0.11-0.89), showing fair agreement. Algorithm performance plummeted on a lower IQ, smartphone device with a kappa value of -0.09 (95% CI -0.95 to 0.76) and 0.09 (95% CI -0.65 to 0.82), respectively, showing less agreement than would be expected by chance. Two POCUS experts had near perfect agreement with a kappa value of 0.88 (95% CI 0.64-1.0) regarding IVC collapse.
CONCLUSIONS: Performance of this previously validated DL algorithm worsened when faced with ultrasound studies from 2 novel ultrasound machines. Performance was much worse on images from a lower IQ hand-held device than from a superior cart-based device.
© 2021 American Institute of Ultrasound in Medicine.

Entities:  

Keywords:  artificial intelligence; deep learning; domain shift; inferior vena cava; pediatrics; point of care ultrasound

Mesh:

Year:  2021        PMID: 34133034     DOI: 10.1002/jum.15765

Source DB:  PubMed          Journal:  J Ultrasound Med        ISSN: 0278-4297            Impact factor:   2.153


  2 in total

1.  Machine learning algorithm using publicly available echo database for simplified "visual estimation" of left ventricular ejection fraction.

Authors:  Michael Blaivas; Laura Blaivas
Journal:  World J Exp Med       Date:  2022-03-20

Review 2.  Review of Machine Learning in Lung Ultrasound in COVID-19 Pandemic.

Authors:  Jing Wang; Xiaofeng Yang; Boran Zhou; James J Sohn; Jun Zhou; Jesse T Jacob; Kristin A Higgins; Jeffrey D Bradley; Tian Liu
Journal:  J Imaging       Date:  2022-03-05
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.