Comparative analysis of machine learning and deep learning algorithms for knee arthritis detection using YOLOv8 models

Knee arthritis is a prevalent joint condition that affects many people worldwide. Early detection and appropriate treatment are essential to slow the disease's progression and enhance patients' quality of life. In this study, various machine learning and deep learning algorithms were used...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of X-ray science and technology Jg. 33; H. 3; S. 565
1. Verfasser: Cinar, Ilkay
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 01.05.2025
Schlagworte:
ISSN:1095-9114, 1095-9114
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Knee arthritis is a prevalent joint condition that affects many people worldwide. Early detection and appropriate treatment are essential to slow the disease's progression and enhance patients' quality of life. In this study, various machine learning and deep learning algorithms were used to detect knee arthritis. The machine learning models included k-NN, SVM, and GBM, while DenseNet, EfficientNet, and InceptionV3 were used as deep learning models. Additionally, YOLOv8 classification models (YOLOv8n-cls, YOLOv8s-cls, YOLOv8m-cls, YOLOv8l-cls, and YOLOv8x-cls) were employed. The "Annotated Dataset for Knee Arthritis Detection" with five classes (Normal, Doubtful, Mild, Moderate, Severe) and 1650 images were divided into 80% training, 10% validation, and 10% testing using the Hold-Out method. YOLOv8 models outperformed both machine learning and deep learning algorithms. k-NN, SVM, and GBM achieved success rates of 63.61%, 64.14%, and 67.36%, respectively. Among deep learning models, DenseNet, EfficientNet, and InceptionV3 achieved 62.35%, 70.59%, and 79.41%. The highest success was seen in the YOLOv8x-cls model at 86.96%, followed by YOLOv8l-cls at 86.79%, YOLOv8m-cls at 83.65%, YOLOv8s-cls at 80.37%, and YOLOv8n-cls at 77.91%.
AbstractList Knee arthritis is a prevalent joint condition that affects many people worldwide. Early detection and appropriate treatment are essential to slow the disease's progression and enhance patients' quality of life. In this study, various machine learning and deep learning algorithms were used to detect knee arthritis. The machine learning models included k-NN, SVM, and GBM, while DenseNet, EfficientNet, and InceptionV3 were used as deep learning models. Additionally, YOLOv8 classification models (YOLOv8n-cls, YOLOv8s-cls, YOLOv8m-cls, YOLOv8l-cls, and YOLOv8x-cls) were employed. The "Annotated Dataset for Knee Arthritis Detection" with five classes (Normal, Doubtful, Mild, Moderate, Severe) and 1650 images were divided into 80% training, 10% validation, and 10% testing using the Hold-Out method. YOLOv8 models outperformed both machine learning and deep learning algorithms. k-NN, SVM, and GBM achieved success rates of 63.61%, 64.14%, and 67.36%, respectively. Among deep learning models, DenseNet, EfficientNet, and InceptionV3 achieved 62.35%, 70.59%, and 79.41%. The highest success was seen in the YOLOv8x-cls model at 86.96%, followed by YOLOv8l-cls at 86.79%, YOLOv8m-cls at 83.65%, YOLOv8s-cls at 80.37%, and YOLOv8n-cls at 77.91%.
Knee arthritis is a prevalent joint condition that affects many people worldwide. Early detection and appropriate treatment are essential to slow the disease's progression and enhance patients' quality of life. In this study, various machine learning and deep learning algorithms were used to detect knee arthritis. The machine learning models included k-NN, SVM, and GBM, while DenseNet, EfficientNet, and InceptionV3 were used as deep learning models. Additionally, YOLOv8 classification models (YOLOv8n-cls, YOLOv8s-cls, YOLOv8m-cls, YOLOv8l-cls, and YOLOv8x-cls) were employed. The "Annotated Dataset for Knee Arthritis Detection" with five classes (Normal, Doubtful, Mild, Moderate, Severe) and 1650 images were divided into 80% training, 10% validation, and 10% testing using the Hold-Out method. YOLOv8 models outperformed both machine learning and deep learning algorithms. k-NN, SVM, and GBM achieved success rates of 63.61%, 64.14%, and 67.36%, respectively. Among deep learning models, DenseNet, EfficientNet, and InceptionV3 achieved 62.35%, 70.59%, and 79.41%. The highest success was seen in the YOLOv8x-cls model at 86.96%, followed by YOLOv8l-cls at 86.79%, YOLOv8m-cls at 83.65%, YOLOv8s-cls at 80.37%, and YOLOv8n-cls at 77.91%.Knee arthritis is a prevalent joint condition that affects many people worldwide. Early detection and appropriate treatment are essential to slow the disease's progression and enhance patients' quality of life. In this study, various machine learning and deep learning algorithms were used to detect knee arthritis. The machine learning models included k-NN, SVM, and GBM, while DenseNet, EfficientNet, and InceptionV3 were used as deep learning models. Additionally, YOLOv8 classification models (YOLOv8n-cls, YOLOv8s-cls, YOLOv8m-cls, YOLOv8l-cls, and YOLOv8x-cls) were employed. The "Annotated Dataset for Knee Arthritis Detection" with five classes (Normal, Doubtful, Mild, Moderate, Severe) and 1650 images were divided into 80% training, 10% validation, and 10% testing using the Hold-Out method. YOLOv8 models outperformed both machine learning and deep learning algorithms. k-NN, SVM, and GBM achieved success rates of 63.61%, 64.14%, and 67.36%, respectively. Among deep learning models, DenseNet, EfficientNet, and InceptionV3 achieved 62.35%, 70.59%, and 79.41%. The highest success was seen in the YOLOv8x-cls model at 86.96%, followed by YOLOv8l-cls at 86.79%, YOLOv8m-cls at 83.65%, YOLOv8s-cls at 80.37%, and YOLOv8n-cls at 77.91%.
Author Cinar, Ilkay
Author_xml – sequence: 1
  givenname: Ilkay
  orcidid: 0000-0003-0611-3316
  surname: Cinar
  fullname: Cinar, Ilkay
  organization: Department of Computer Engineering, Selcuk University, 42250 Selcuklu, Konya, Türkiye
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40012222$$D View this record in MEDLINE/PubMed
BookMark eNpNkD1PwzAQhi1URD_gB7AgjywBX2LH9ogqvqRKXWBgipz40gYSu9hJpf57gihSb7lX7z16hpuTifMOCbkGdgcg5T1TWmRa5ymHjCkp2RmZAdMi0QB8cpKnZB7jJ2MAQqkLMuVjTMeZkf3SdzsTTN_skRpn2kNsIvU17Uy1bRzSFk1wjduMR0st4u6kaTc-NP22i7T2gX45HBWh347d6LDYY9U33tEh_tIf69V6r2jnLbbxkpzXpo14ddwL8v70-LZ8SVbr59flwyqpskz2CeepKVklLXBQ1uoKuFFoa8ZBC1vXMhcZWm6YhlKULDfGaKEFq2pRlSbN0wW5_fPugv8eMPZF18QK29Y49EMsMpCgFHCRjujNER3KDm2xC01nwqH4_1X6A7Rab1E
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1177/08953996241308770
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Medicine
Engineering
Physics
EISSN 1095-9114
ExternalDocumentID 40012222
Genre Journal Article
Comparative Study
GroupedDBID ---
--K
0R~
1B1
1RT
1~5
29L
4.4
4G.
53G
5GY
5VS
7-5
AAEDT
AAEJI
AAGLT
AALRI
AAPII
AAQFI
AAQXI
AAQXK
AAXUO
AAYWO
ABDBF
ABEFU
ABJNI
ABJZC
ABMAC
ABUBZ
ABUJY
ABWVN
ACGFS
ACPQW
ACRPL
ACUHS
ADBBV
ADMUD
ADNMO
ADZMO
AEJQA
AENEX
AFFNX
AFRHK
AFYTF
AGIAB
AGQPQ
AHDMH
AHHHB
AITUG
AJGYC
AJNRN
AKRWK
ALIRC
ALMA_UNASSIGNED_HOLDINGS
APPIZ
ARTOV
CAG
CGR
COF
CS3
CUY
CVF
DM4
DU5
EAD
EAP
EBD
EBS
ECM
EIF
EJD
EMK
EMOBN
EPL
EST
ESX
F5P
FDB
FEDTE
FGOYB
FIRID
G-2
H13
HEI
HMK
HMO
HVGLF
HZ~
I-F
IHE
IL9
IOS
J8X
LG5
M29
MET
MIO
MV1
NGNOM
NPM
O-L
O9-
P2P
Q1R
R2-
ROL
RPZ
SAE
SAUOL
SCNPE
SFC
SSZ
SV3
TUS
UHS
WUQ
XPP
7X8
ACARO
ID FETCH-LOGICAL-c337t-442ab0c7d1418dd9c14a8edf04195dff7653ed4a091b5b06aaa95950cf5cba262
IEDL.DBID 7X8
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001464287500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1095-9114
IngestDate Sat Nov 01 15:06:44 EDT 2025
Thu Aug 28 04:47:12 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Keywords deep learning
knee arthritis detection
classification
machine learning
YOLOv8
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c337t-442ab0c7d1418dd9c14a8edf04195dff7653ed4a091b5b06aaa95950cf5cba262
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0003-0611-3316
OpenAccessLink https://journals.sagepub.com/doi/pdf/10.1177/08953996241308770
PMID 40012222
PQID 3171881452
PQPubID 23479
ParticipantIDs proquest_miscellaneous_3171881452
pubmed_primary_40012222
PublicationCentury 2000
PublicationDate 2025-05-00
20250501
PublicationDateYYYYMMDD 2025-05-01
PublicationDate_xml – month: 05
  year: 2025
  text: 2025-05-00
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of X-ray science and technology
PublicationTitleAlternate J Xray Sci Technol
PublicationYear 2025
SSID ssj0011588
Score 2.3746493
Snippet Knee arthritis is a prevalent joint condition that affects many people worldwide. Early detection and appropriate treatment are essential to slow the disease's...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 565
SubjectTerms Algorithms
Deep Learning
Humans
Image Interpretation, Computer-Assisted - methods
Knee Joint - diagnostic imaging
Machine Learning
Neural Networks, Computer
Osteoarthritis, Knee - diagnostic imaging
Title Comparative analysis of machine learning and deep learning algorithms for knee arthritis detection using YOLOv8 models
URI https://www.ncbi.nlm.nih.gov/pubmed/40012222
https://www.proquest.com/docview/3171881452
Volume 33
WOSCitedRecordID wos001464287500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3JTsMwEB2xCw4sZd9kJK4RsWMnzgkhBOIAhQNI5VQ5XloJSAsp_X7GrlG5ICFxySGLYs1M7Mm88XsAp8ZRm0pbJlmubcK19YWmjCVaZ-htQ41wPIhNFO227HTKh1hwa2Jb5fecGCZqM9C-Rn6G6xyVknLBzofviVeN8uhqlNCYhfkMUxkf1UVniiJQISdb4YIeIeUR1QyES7L0nKx5gJVkUaS_Z5hhpble--8Y12E15pjkYhIUGzBj6xas_GAebMHSXcTUW7AYmkB1swnjyykVOFGRrYQMHHkLHZeWRImJHl40xFg7_HHmtYcjGfXfGoJpMHnBNxGMyn7gTMJ7R6Hlqya-z75Hnu9v78eSBBmeZguerq8eL2-SqMuQ6CwrRgnnTFWpLgzlVBpTasqVtMalnJbCOFfkIrOGK0xFKlGluVKqFKVItRO6Uixn2zBXD2q7C0RqpWheMC9rhYGSl07iD6tEhzHjqpzuwcm3pbsY9x7MULUdfDbdqa33YGfiru5wQtDR5QEwZGz_D08fwDLzkr6hh_EQ5h1-9fYIFvQYzfNxHAIKj-2Huy-RltZP
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Comparative+analysis+of+machine+learning+and+deep+learning+algorithms+for+knee+arthritis+detection+using+YOLOv8+models&rft.jtitle=Journal+of+X-ray+science+and+technology&rft.au=Cinar%2C+Ilkay&rft.date=2025-05-01&rft.issn=1095-9114&rft.eissn=1095-9114&rft.volume=33&rft.issue=3&rft.spage=565&rft_id=info:doi/10.1177%2F08953996241308770&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1095-9114&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1095-9114&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1095-9114&client=summon