• Home
  • Search
  • Knee Osteoarthritis Classification Using 3D CNN and MRI
  • Cite Icon65
  • https://doi.org/10.3390/app11115196Copy DOI Icon

Knee Osteoarthritis Classification Using 3D CNN and MRI

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Osteoarthritis (OA) is the most common form of arthritis and can often occur in the knee. While convolutional neural networks (CNNs) have been widely used to study medical images, the application of a 3-dimensional (3D) CNN in knee OA diagnosis is limited. This study utilizes a 3D CNN model to analyze sequences of knee magnetic resonance (MR) images to perform knee OA classification. An advantage of using 3D CNNs is the ability to analyze the whole sequence of 3D MR images as a single unit as opposed to a traditional 2D CNN, which examines one image at a time. Therefore, 3D features could be extracted from adjacent slices, which may not be detectable from a single 2D image. The input data for each knee were a sequence of double-echo steady-state (DESS) MR images, and each knee was labeled by the Kellgren and Lawrence (KL) grade of severity at levels 0–4. In addition to the 5-category KL grade classification, we further examined a 2-category classification that distinguishes non-OA (KL ≤ 1) from OA (KL ≥ 2) knees. Clinically, diagnosing a patient with knee OA is the ultimate goal of assigning a KL grade. On a dataset with 1100 knees, the 3D CNN model that classifies knees with and without OA achieved an accuracy of 86.5% on the validation set and 83.0% on the testing set. We further conducted a comparative study between MRI and X-ray. Compared with a CNN model using X-ray images trained from the same group of patients, the proposed 3D model with MR images achieved higher accuracy in both the 5-category classification (54.0% vs. 50.0%) and the 2-category classification (83.0% vs. 77.0%). The result indicates that MRI, with the application of a 3D CNN model, has greater potential to improve diagnosis accuracy for knee OA clinically than the currently used X-ray methods.

Loading PDF

Similar Papers
  • Research Article
  • Citations58

Identification of slightly sprouted wheat kernels using hyperspectral imaging technology and different deep convolutional neural networks

  • Aug 04, 2022
  • Food Control
  • Jingwu Zhu +3
  • Research Article
  • Citations25

Ultrasonographic assessment of pes anserinus tendon and pes anserinus tendinitis bursitis syndrome in patients with knee osteoarthritis

  • Jul 18, 2014
  • Modern Rheumatology
  • Hasan Toktas +4
  • Research Article
  • Citations107

Deep learning approaches using 2D and 3D convolutional neural networks for generating male pelvic synthetic computed tomography from magnetic resonance imaging.

  • Jul 26, 2019
  • Medical Physics
  • Jie Fu +6
  • Research Article
  • Citations11

Multislice input for 2D and 3D residual convolutional neural network noise reduction in CT.

  • Jan 31, 2023
  • Journal of Medical Imaging
  • Zhongxing Zhou +4
  • Abstract

POS0787 DYSLIPIDEMIC STATUS OF SYNOVIAL FLUID SHOWS A STRONG ASSOCIATION WITH SUSTAINED SYNOVIAL INFLAMMATION AND CARTILAGE DEGRADATION IN OSTEOARTHRITIS

  • Jun 01, 2024
  • Annals of the Rheumatic Diseases
  • A Harsulkar +3
  • Research Article
  • Citations40

3D convolutional neural network model from contrast-enhanced CT to predict spread through air spaces in non-small cell lung cancer

  • Jun 27, 2022
  • Diagnostic and Interventional Imaging
  • Junli Tao +7
  • Abstract

Serum vitamin D and knee osteoarthritis: is its role over-emphasized?

  • Apr 01, 2019
  • Osteoarthritis and Cartilage
  • S.R Srivastava +3
  • Research Article
  • Citations17

Radiographic features of knee and hip osteoarthritis represent characteristics of an individual, in addition to severity of osteoarthritis

  • Dec 16, 2011
  • Scandinavian Journal of Rheumatology
  • Mb Kinds +7
  • Research Article
  • Citations1

Enabling Early Identification of Malignant Vertebral Compression Fractures Through 2.5D Convolutional Neural Network Model With CT Image Analysis.

  • Jun 23, 2025
  • Spine
  • Chengbin Huang +7
  • Research Article
  • Citations34

Segmentation of focal cortical dysplasia lesions from magnetic resonance images using 3D convolutional neural networks

  • Jul 12, 2021
  • Biomedical Signal Processing and Control
  • S Niyas +6
  • Research Article

Self-reported physical activity and risk of primary knee replacement for osteoarthritis: a competing risks cohort analysis

  • Oct 27, 2025
  • BMC Musculoskeletal Disorders
  • Hao Peng +8
  • Abstract

OP0034 The association between radiographic hand osteoarthritis and meniscal damage on MRI in the general population

  • Jun 01, 2013
  • Annals of the Rheumatic Diseases
  • M Englund +8
  • Research Article
  • Citations16

Defects recognition of pine nuts using hyperspectral imaging and deep learning approaches

  • Apr 10, 2024
  • Microchemical Journal
  • Dongdong Peng +7
  • Research Article
  • Citations8

The Relationship between HIF-2α and VEGF with Radiographic Severity in the Primary Osteoarthritic Knee

  • Mar 15, 2016
  • Yonsei Medical Journal
  • Zhou Jian-Lin +8
  • Research Article
  • Citations29

Can urinary CTX-II be a biomarker for knee osteoarthritis?

  • Feb 10, 2020
  • Arthroplasty
  • Piti Arunrukthavon +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.