Skip to main navigation Skip to search Skip to main content

Classification and Recognition of Knee Coronal Femoral Edema Based on Nonnegative Matrix Factorization

  • Harbin Institute of Technology
  • The Second Affiliated Hospital of Harbin Medical University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

It’s a huge workload to label the edema area in the diagnosis of knee edema at present, based on the excellent ability of nonnegative matrix factorization to process high-dimensional data and the characteristics of less requirement for prior information, we combine nonnegative matrix factorization with the diagnosis of knee edema to determine whether there is edema and find the corresponding edema area. In this paper, we propose a new weakly-supervised method named FSNMF algorithm, by adjusting the corresponding eigenvalues based on different targets, so as to ensure the effectiveness of disease image classification and edema region feature extraction. In our paper, experiments have been carried out on the proposed algorithm to show the performance of our FSNMF algorithm. Through experiments on public data sets, we verify the classification accuracy of the proposed method is improved compared with the previous NMF classification algorithm and the accuracy of edema identification using FSNMF is also excellent.

Original languageEnglish
Title of host publicationIntelligent and Fuzzy Systems - Intelligent Industrial Informatics and Efficient Networks Proceedings of the INFUS 2024 Conference
EditorsCengiz Kahraman, Sezi Cevik Onar, Selcuk Cebi, Basar Oztaysi, Irem Ucal Sari, A. Cagrı Tolga
PublisherSpringer Science and Business Media Deutschland GmbH
Pages216-224
Number of pages9
ISBN (Print)9783031671913
DOIs
StatePublished - 2024
EventInternational Conference on Intelligent and Fuzzy Systems, INFUS 2024 - Canakkale, Turkey
Duration: 16 Jul 202418 Jul 2024

Publication series

NameLecture Notes in Networks and Systems
Volume1090 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

ConferenceInternational Conference on Intelligent and Fuzzy Systems, INFUS 2024
Country/TerritoryTurkey
CityCanakkale
Period16/07/2418/07/24

Keywords

  • Edema identification
  • Image classification
  • Nonnegative matrix factorization
  • Weakly-supervised method

Fingerprint

Dive into the research topics of 'Classification and Recognition of Knee Coronal Femoral Edema Based on Nonnegative Matrix Factorization'. Together they form a unique fingerprint.

Cite this