A method for labelling lesions for machine learning and some new observations on osteochondrosis in computed tomographic scans of four pig joints.
Articular osteochondrosis
Breeding selection
Helical computed tomography
Lesion number
Lesion volume
Machine learning
Swine
Journal
BMC veterinary research
ISSN: 1746-6148
Titre abrégé: BMC Vet Res
Pays: England
ID NLM: 101249759
Informations de publication
Date de publication:
31 Aug 2022
31 Aug 2022
Historique:
received:
18
05
2022
accepted:
24
08
2022
entrez:
31
8
2022
pubmed:
1
9
2022
medline:
8
9
2022
Statut:
epublish
Résumé
Osteochondrosis is a major cause of leg weakness in pigs. Selection against osteochondrosis is currently based on manual scoring of computed tomographic (CT) scans for the presence of osteochondrosis manifesta lesions. It would be advantageous if osteochondrosis could be diagnosed automatically, through artificial intelligence methods using machine learning. The aim of this study was to describe a method for labelling articular osteochondrosis lesions in CT scans of four pig joints to guide development of future machine learning algorithms, and to report new observations made during the labelling process. The shoulder, elbow, stifle and hock joints were evaluated in CT scans of 201 pigs. Six thousand two hundred fifty osteochondrosis manifesta and cyst-like lesions were labelled in 201 pigs representing a total volume of 211,721.83 mm The described labelling method is an important step towards developing a machine learning algorithm that will enable automated diagnosis of osteochondrosis manifesta and cyst-like lesions. Both lesion number and volume should be considered during breeding selection. The apparent inverse relationship between lesion number and volume warrants further investigation.
Sections du résumé
BACKGROUND
BACKGROUND
Osteochondrosis is a major cause of leg weakness in pigs. Selection against osteochondrosis is currently based on manual scoring of computed tomographic (CT) scans for the presence of osteochondrosis manifesta lesions. It would be advantageous if osteochondrosis could be diagnosed automatically, through artificial intelligence methods using machine learning. The aim of this study was to describe a method for labelling articular osteochondrosis lesions in CT scans of four pig joints to guide development of future machine learning algorithms, and to report new observations made during the labelling process. The shoulder, elbow, stifle and hock joints were evaluated in CT scans of 201 pigs.
RESULTS
RESULTS
Six thousand two hundred fifty osteochondrosis manifesta and cyst-like lesions were labelled in 201 pigs representing a total volume of 211,721.83 mm
CONCLUSIONS
CONCLUSIONS
The described labelling method is an important step towards developing a machine learning algorithm that will enable automated diagnosis of osteochondrosis manifesta and cyst-like lesions. Both lesion number and volume should be considered during breeding selection. The apparent inverse relationship between lesion number and volume warrants further investigation.
Identifiants
pubmed: 36045350
doi: 10.1186/s12917-022-03426-x
pii: 10.1186/s12917-022-03426-x
pmc: PMC9429582
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
328Subventions
Organisme : Norges Forskningsråd
ID : 295083
Organisme : Norges Forskningsråd
ID : 295083
Organisme : Norges Forskningsråd
ID : 295083
Informations de copyright
© 2022. The Author(s).
Références
J Anim Sci. 2020 Apr 1;98(4):
pubmed: 32249288
Osteoarthritis Cartilage. 2009 Jun;17(6):705-13
pubmed: 19101179
Vet Pathol. 2015 Sep;52(5):785-802
pubmed: 26080832
Fukuoka Igaku Zasshi. 1996 Jun;87(6):133-41
pubmed: 8753020
Vet Pathol. 2019 Sep;56(5):732-742
pubmed: 31060473
Vet Pathol. 2018 Sep;55(5):693-702
pubmed: 29807507
Acta Radiol Suppl. 1978;358:45-90
pubmed: 233602
Equine Vet J. 2008 Jul;40(5):433-9
pubmed: 18487109
BMC Vet Res. 2014 Sep 09;10:212
pubmed: 25199991
Am J Sports Med. 2019 Jun;47(7):1601-1612
pubmed: 31072116
Animal. 2012 Jan;6(1):9-18
pubmed: 22436149
BMC Vet Res. 2018 Dec 10;14(1):390
pubmed: 30526583
J Orthop Res. 2014 Aug;32(8):1014-23
pubmed: 24740876
Can J Vet Res. 1988 Jan;52(1):154-5
pubmed: 3349396
Zentralbl Veterinarmed A. 1994 Jun;41(5):377-84
pubmed: 7817640
Animal. 2013 Oct;7(10):1576-82
pubmed: 23806321
Vet Pathol. 1987 Mar;24(2):109-17
pubmed: 3576905
J Orthop Res. 2004 Nov;22(6):1201-9
pubmed: 15475198
Osteoarthritis Cartilage. 2013 May;21(5):730-8
pubmed: 23428601
Rheumatol Int. 1986;6(6):239-43
pubmed: 3809886
Vet Pathol. 2017 May;54(3):445-456
pubmed: 28129094
BMC Vet Res. 2019 Dec 17;15(1):454
pubmed: 31847840
Acta Vet Scand. 1974;15(1):1-25
pubmed: 4830068
Equine Vet J. 1982 Jan;14(1):40-6
pubmed: 7084177
J Orthop Res. 1991 May;9(3):317-29
pubmed: 2010836
Equine Vet J. 2015 May;47(3):326-32
pubmed: 24750226
Vet Pathol. 2007 Jul;44(4):429-48
pubmed: 17606505
J Orthop Res. 2013 Dec;31(12):2006-12
pubmed: 23939946
Infect Immun. 1985 Aug;49(2):443-6
pubmed: 4018875
Vet Rec. 2006 Sep 16;159(12):383-7
pubmed: 16980524
Equine Vet J. 2008 Jan;40(1):30-9
pubmed: 18083657
Acta Radiol Suppl. 1978;358:23-44
pubmed: 233599
Bone. 2004 Mar;34(3):454-65
pubmed: 15003793
Dev Biol. 1988 Oct;129(2):372-9
pubmed: 3417044
BMC Vet Res. 2014 Sep 11;10:208
pubmed: 25208481
Bone. 2004 Dec;35(6):1294-306
pubmed: 15589210
Vet Pathol. 2015 Sep;52(5):862-72
pubmed: 25428408
Front Bioeng Biotechnol. 2020 Feb 28;8:93
pubmed: 32185167
BMC Vet Res. 2017 Aug 22;13(1):270
pubmed: 28830435
J Anim Sci. 2014 Aug;92(8):3338-47
pubmed: 24987085
Osteoarthritis Cartilage. 2020 Sep;28(9):1235-1244
pubmed: 32278071
Transl Anim Sci. 2018 May 24;2(3):324-335
pubmed: 32704716