Intelligent localization and quantitative evaluation of anterior talofibular ligament injury using magnetic resonance imaging of ankle.
Anterior talofibular ligament
DRLSE
Intelligent localization of ATFL
Magnetic resonance imaging
Quantitative evaluation of ATFL injury
Journal
BMC medical imaging
ISSN: 1471-2342
Titre abrégé: BMC Med Imaging
Pays: England
ID NLM: 100968553
Informations de publication
Date de publication:
28 08 2021
28 08 2021
Historique:
received:
01
06
2021
accepted:
24
08
2021
entrez:
29
8
2021
pubmed:
30
8
2021
medline:
22
1
2022
Statut:
epublish
Résumé
There is a high incidence of injury to the lateral ligament of the ankle in daily living and sports activities. The anterior talofibular ligament (ATFL) is the most frequent types of ankle injuries. It is of great clinical significance to achieve intelligent localization and injury evaluation of ATFL due to its vulnerability. According to the specific characteristics of bones in different slices, the key slice was extracted by image segmentation and characteristic analysis. Then, the talus and fibula in the key slice were segmented by distance regularized level set evolution (DRLSE), and the curvature of their contour pixels was calculated to find useful feature points including the neck of talus, the inner edge of fibula, and the outer edge of fibula. ATFL area can be located using these feature points so as to quantify its first-order gray features and second-order texture features. Support vector machine (SVM) was performed for evaluation of ATFL injury. Data were collected retrospectively from 158 patients who underwent MRI, and were divided into normal (68) and tear (90) group. The positioning accuracy and Dice coefficient were used to measure the performance of ATFL localization, and the mean values are 87.7% and 77.1%, respectively, which is helpful for the following feature extraction. SVM gave a good prediction ability with accuracy of 93.8%, sensitivity of 88.9%, specificity of 100%, precision of 100%, and F1 score of 94.2% in the test set. Experimental results indicate that the proposed method is reliable in diagnosing ATFL injury. This study may provide a potentially viable method for aided clinical diagnoses of some ligament injury.
Sections du résumé
BACKGROUND
There is a high incidence of injury to the lateral ligament of the ankle in daily living and sports activities. The anterior talofibular ligament (ATFL) is the most frequent types of ankle injuries. It is of great clinical significance to achieve intelligent localization and injury evaluation of ATFL due to its vulnerability.
METHODS
According to the specific characteristics of bones in different slices, the key slice was extracted by image segmentation and characteristic analysis. Then, the talus and fibula in the key slice were segmented by distance regularized level set evolution (DRLSE), and the curvature of their contour pixels was calculated to find useful feature points including the neck of talus, the inner edge of fibula, and the outer edge of fibula. ATFL area can be located using these feature points so as to quantify its first-order gray features and second-order texture features. Support vector machine (SVM) was performed for evaluation of ATFL injury.
RESULTS
Data were collected retrospectively from 158 patients who underwent MRI, and were divided into normal (68) and tear (90) group. The positioning accuracy and Dice coefficient were used to measure the performance of ATFL localization, and the mean values are 87.7% and 77.1%, respectively, which is helpful for the following feature extraction. SVM gave a good prediction ability with accuracy of 93.8%, sensitivity of 88.9%, specificity of 100%, precision of 100%, and F1 score of 94.2% in the test set.
CONCLUSION
Experimental results indicate that the proposed method is reliable in diagnosing ATFL injury. This study may provide a potentially viable method for aided clinical diagnoses of some ligament injury.
Identifiants
pubmed: 34454471
doi: 10.1186/s12880-021-00660-x
pii: 10.1186/s12880-021-00660-x
pmc: PMC8403355
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
130Informations de copyright
© 2021. The Author(s).
Références
Eur Radiol. 2019 Nov;29(11):6336-6344
pubmed: 30937585
J Digit Imaging. 2017 Aug;30(4):427-441
pubmed: 28275919
Sports Med. 2014 Jan;44(1):123-40
pubmed: 24105612
Rozhl Chir. 2010 Aug;89(7):461-5
pubmed: 20925265
Foot Ankle Surg. 2010 Jun;16(2):78-80
pubmed: 20483139
Med Image Anal. 2019 Feb;52:109-118
pubmed: 30529224
J Orthop Sci. 2020 Jan;25(1):183-187
pubmed: 30885728
BMC Musculoskelet Disord. 2017 Sep 12;18(1):397
pubmed: 28899377
Clin Radiol. 2012 Apr;67(4):313-8
pubmed: 22078461
Am J Sports Med. 2014 Jul;42(7):1549-57
pubmed: 24753239
J Foot Ankle Surg. 2020 May - Jun;59(3):465-468
pubmed: 32354502
Comput Biol Med. 2021 Jul;134:104449
pubmed: 33993015
IEEE Trans Image Process. 2010 Dec;19(12):3243-54
pubmed: 20801742
Diagnostics (Basel). 2021 Jan 11;11(1):
pubmed: 33440798
Mayo Clin Proc. 1984 Mar;59(3):165-70
pubmed: 6708594
IEEE Trans Image Process. 2011 Jun;20(6):1485-94
pubmed: 21216713
J Orthop Res. 2021 Apr;39(4):831-840
pubmed: 33241856
Acad Radiol. 2021 Sep;28(9):e247-e257
pubmed: 32534965
AJR Am J Roentgenol. 2014 Jan;202(1):W87-94
pubmed: 24370169
IEEE Trans Pattern Anal Mach Intell. 2013 Jun;35(6):1397-409
pubmed: 23599054
J Orthop Sci. 2020 Mar;25(2):297-302
pubmed: 31104886
Foot Ankle Int. 2017 Jun;38(6):621-626
pubmed: 28552041
Foot Ankle Int. 1998 Nov;19(11):757-60
pubmed: 9840205
J Digit Imaging. 2019 Dec;32(6):980-986
pubmed: 30859341
Br J Radiol. 2012 Aug;85(1016):1157-72
pubmed: 22553301
Skeletal Radiol. 2010 Jan;39(1):41-7
pubmed: 19685050
Radiol Artif Intell. 2019 May 08;1(3):180091
pubmed: 32076658
IEEE Trans Neural Netw Learn Syst. 2015 Oct;26(10):2357-69
pubmed: 25576581
IEEE Trans Image Process. 2008 Dec;17(12):2324-33
pubmed: 19004705
Nat Med. 2018 Sep;24(9):1342-1350
pubmed: 30104768