Skip to search boxSkip to navigationSkip to main content

Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis

  • Livija Jakaite
    ,
  • Vitaly Schetinin
    ,
  • Jiří Hladůvka
    ,
  • Sergey Minaev
    ,
  • Aziz Ambia
    ,
  • Wojtek Krzanowski
  • TU Wien
    ,
  • Stavropol State Medical University
    ,
  • Fusion Radiology
    ,
  • University of Exeter
Research Output: Contribution to journal Article Peer-review

Open access

Abstract

Texture features are designed to quantitatively evaluate patterns of spatial distribution of image pixels for purposes of image analysis and interpretation. Unexplained variations in the texture patterns often lead to misinterpretation and undesirable consequences in medical image analysis. In this paper we explore the ability of machine learning (ML) methods to design a radiology test of Osteoarthritis (OA) at early stage when the number of patients’ cases is small. In our experiments we use high-resolution X-ray images of knees in patients which were identified with Kellgren–Lawrence scores progressing from 1. The existing ML methods have provided a limited diagnostic accuracy, whilst the proposed Group Method of Data Handling strategy of Deep Learning has significantly extended the diagnostic test. The comparative experiments demonstrate that the proposed framework using the Zernike-based texture features has significantly improved the diagnostic accuracy on average by 11%. This allows us to conclude that the designed model for early diagnostic of OA will provide more accurate radiology tests, although new study is required when a large number of patients’ cases will be available.

Publication Information

Output type

Research Output: Contribution to journal Article Peer-review

Original language

English

Article number

2294

Pages from-to (Number of pages)

Pages 2294

Journal (Volume, Issue Number)

Scientific Reports (Volume 11, Issue 1)

Publication milestones

  • Accepted/In press - 07/01/2021
  • Published - 27/01/2021

Publication status

Published - 27/01/2021

External Publication IDs

  • handle.net: 10547/624806
  • Scopus: 85099857273
  • PubMed: 33504863

Access to documents

Publication metrics

Metrics

Download statistics
Download count
6

PlumX, opens in new tab

54
Captures
58
Social media
20