Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Feb 1;23(3):1565.
doi: 10.3390/s23031565.

Computer-Aided Ankle Ligament Injury Diagnosis from Magnetic Resonance Images Using Machine Learning Techniques

Rodrigo S Astolfi  1 , Daniel S da Silva  2 , Ingrid S Guedes  1 , Caio S Nascimento  2 , Robertas Damaševičius  3 , Senthil K Jagatheesaperumal  4 , Victor Hugo C de Albuquerque  2 , José Alberto D Leite  1
Affiliations

Computer-Aided Ankle Ligament Injury Diagnosis from Magnetic Resonance Images Using Machine Learning Techniques

Rodrigo S Astolfi et al. Sensors (Basel). .

Abstract

Ankle injuries caused by the Anterior Talofibular Ligament (ATFL) are the most common type of injury. Thus, finding new ways to analyze these injuries through novel technologies is critical for assisting medical diagnosis and, as a result, reducing the subjectivity of this process. As a result, the purpose of this study is to compare the ability of specialists to diagnose lateral tibial tuberosity advancement (LTTA) injury using computer vision analysis on magnetic resonance imaging (MRI). The experiments were carried out on a database obtained from the Vue PACS-Carestream software, which contained 132 images of ATFL and normal (healthy) ankles. Because there were only a few images, image augmentation techniques was used to increase the number of images in the database. Following that, various feature extraction algorithms (GLCM, LBP, and HU invariant moments) and classifiers such as Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Random Forest (RF) were used. Based on the results from this analysis, for cases that lack clear morphologies, the method delivers a hit rate of 85.03% with an increase of 22% over the human expert-based analysis.

Keywords: MRI; ankle ligament injury; data augmentation; feature extraction.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Sequence of stages involved in the clinical decision making of ankle ligament injury from the MRI images.
Figure 2
Figure 2
The confusion matrix highlights the validation metrics chosen for experimentation and analysis.
Figure 3
Figure 3
MRI of the ankle in a T2-weighted axial section at the height where the talus is most visible for ATFL analysis. (A): normal ligament (rectilinear and homogeneous); (B): abnormal ligament due to altered signal; (C): abnormal ligament due to altered contours; and (D): absent ligament.
Figure 4
Figure 4
Distribution of normal, abnormal, and absent ATFL and CAI.
Figure 5
Figure 5
Comparison of mean values of performance measures for various combinations of feature sets and classifiers.
Figure 6
Figure 6
Results of the statistical t-test (p-values) for various combinations of feature sets and classifiers.
Figure 7
Figure 7
Critical Distance diagrams for performance metrics of the machine learning methods.
Figure 7
Figure 7
Critical Distance diagrams for performance metrics of the machine learning methods.
Figure 8
Figure 8
Confusion matrix obtained for the RF classifier with Set 5 chosen for analysis.
Figure 9
Figure 9
Comparison of classifiers based on training and testing times.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Conlin F.D., Johnson P.G., Sinning J.E., Jr. The etiology and repair of rotary ankle instability. Foot Ankle. 1989;10:152–155. doi: 10.1177/107110078901000307. - DOI - PubMed
    1. Bajuri M.Y., Daun E., Raof M.H.A., Hassan M.R., Das S. Functional outcome of modified Brostrom-Gould procedure using the PopLok knotless suture anchor technique in lateral ankle instability. Cureus. 2019;11:e4971. doi: 10.7759/cureus.4971. - DOI - PMC - PubMed
    1. Milner C.E., Soames R.W. Anatomy of the collateral ligaments of the human ankle joint. Foot Ankle Int. 1998;19:757–760. doi: 10.1177/107110079801901109. - DOI - PubMed
    1. Renström A.F.H. and Scott A. Lynch Ankle ligament injuries. Rev. Bras. Med. Esporte. 1998;4:71–80. doi: 10.1590/S1517-86921998000300002. - DOI
    1. Tao H., Hu Y., Qiao Y., Ma K., Yan X., Hua Y., Chen S. T2-mapping evaluation of early cartilage alteration of talus for chronic lateral ankle instability with isolated anterior talofibular ligament tear or combined with calcaneofibular ligament tear. J. Magn. Reson. Imaging. 2018;47:69–77. doi: 10.1002/jmri.25745. - DOI - PubMed

MeSH terms