Artificial intelligence-based automatic assessment of lower limb torsion on MRI
Abstract Abnormal torsion of the lower limbs may adversely affect joint health. This study developed and validated a deep learning-based method for automatic measurement of femoral and tibial torsion on MRI. Axial T2-weighted sequences acquired of the hips, knees, and ankles of 93 patients (mean age...
Guardado en:
Autores principales: | , , , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/c14e2bbef8674f8eba836f6d678546f7 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:c14e2bbef8674f8eba836f6d678546f7 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:c14e2bbef8674f8eba836f6d678546f72021-12-05T12:15:28ZArtificial intelligence-based automatic assessment of lower limb torsion on MRI10.1038/s41598-021-02708-y2045-2322https://doaj.org/article/c14e2bbef8674f8eba836f6d678546f72021-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-02708-yhttps://doaj.org/toc/2045-2322Abstract Abnormal torsion of the lower limbs may adversely affect joint health. This study developed and validated a deep learning-based method for automatic measurement of femoral and tibial torsion on MRI. Axial T2-weighted sequences acquired of the hips, knees, and ankles of 93 patients (mean age, 13 ± 5 years; 52 males) were included and allocated to training (n = 60), validation (n = 9), and test sets (n = 24). A U-net convolutional neural network was trained to segment both femur and tibia, identify osseous anatomic landmarks, define pertinent reference lines, and quantify femoral and tibial torsion. Manual measurements by two radiologists provided the reference standard. Inter-reader comparisons were performed using repeated-measures ANOVA, Pearson’s r, and the intraclass correlation coefficient (ICC). Mean Sørensen-Dice coefficients for segmentation accuracy ranged between 0.89 and 0.93 and erroneous segmentations were scarce. Ranges of torsion as measured by both readers and the algorithm on the same axial image were 15.8°–18.0° (femur) and 33.9°–35.2° (tibia). Correlation coefficients (ranges, .968 ≤ r ≤ .984 [femur]; .867 ≤ r ≤ .904 [tibia]) and ICCs (ranges, .963 ≤ ICC ≤ .974 [femur]; .867 ≤ ICC ≤ .894 [tibia]) indicated excellent inter-reader agreement. Algorithm-based analysis was faster than manual analysis (7 vs 207 vs 230 s, p < .001). In conclusion, fully automatic measurement of torsional alignment is accurate, reliable, and sufficiently fast for clinical workflows.Justus SchockDaniel TruhnDarius NürnbergerStefan ConradMarc Sebastian HuppertzSebastian KeilChristiane KuhlDorit MerhofSven NebelungNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Justus Schock Daniel Truhn Darius Nürnberger Stefan Conrad Marc Sebastian Huppertz Sebastian Keil Christiane Kuhl Dorit Merhof Sven Nebelung Artificial intelligence-based automatic assessment of lower limb torsion on MRI |
description |
Abstract Abnormal torsion of the lower limbs may adversely affect joint health. This study developed and validated a deep learning-based method for automatic measurement of femoral and tibial torsion on MRI. Axial T2-weighted sequences acquired of the hips, knees, and ankles of 93 patients (mean age, 13 ± 5 years; 52 males) were included and allocated to training (n = 60), validation (n = 9), and test sets (n = 24). A U-net convolutional neural network was trained to segment both femur and tibia, identify osseous anatomic landmarks, define pertinent reference lines, and quantify femoral and tibial torsion. Manual measurements by two radiologists provided the reference standard. Inter-reader comparisons were performed using repeated-measures ANOVA, Pearson’s r, and the intraclass correlation coefficient (ICC). Mean Sørensen-Dice coefficients for segmentation accuracy ranged between 0.89 and 0.93 and erroneous segmentations were scarce. Ranges of torsion as measured by both readers and the algorithm on the same axial image were 15.8°–18.0° (femur) and 33.9°–35.2° (tibia). Correlation coefficients (ranges, .968 ≤ r ≤ .984 [femur]; .867 ≤ r ≤ .904 [tibia]) and ICCs (ranges, .963 ≤ ICC ≤ .974 [femur]; .867 ≤ ICC ≤ .894 [tibia]) indicated excellent inter-reader agreement. Algorithm-based analysis was faster than manual analysis (7 vs 207 vs 230 s, p < .001). In conclusion, fully automatic measurement of torsional alignment is accurate, reliable, and sufficiently fast for clinical workflows. |
format |
article |
author |
Justus Schock Daniel Truhn Darius Nürnberger Stefan Conrad Marc Sebastian Huppertz Sebastian Keil Christiane Kuhl Dorit Merhof Sven Nebelung |
author_facet |
Justus Schock Daniel Truhn Darius Nürnberger Stefan Conrad Marc Sebastian Huppertz Sebastian Keil Christiane Kuhl Dorit Merhof Sven Nebelung |
author_sort |
Justus Schock |
title |
Artificial intelligence-based automatic assessment of lower limb torsion on MRI |
title_short |
Artificial intelligence-based automatic assessment of lower limb torsion on MRI |
title_full |
Artificial intelligence-based automatic assessment of lower limb torsion on MRI |
title_fullStr |
Artificial intelligence-based automatic assessment of lower limb torsion on MRI |
title_full_unstemmed |
Artificial intelligence-based automatic assessment of lower limb torsion on MRI |
title_sort |
artificial intelligence-based automatic assessment of lower limb torsion on mri |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/c14e2bbef8674f8eba836f6d678546f7 |
work_keys_str_mv |
AT justusschock artificialintelligencebasedautomaticassessmentoflowerlimbtorsiononmri AT danieltruhn artificialintelligencebasedautomaticassessmentoflowerlimbtorsiononmri AT dariusnurnberger artificialintelligencebasedautomaticassessmentoflowerlimbtorsiononmri AT stefanconrad artificialintelligencebasedautomaticassessmentoflowerlimbtorsiononmri AT marcsebastianhuppertz artificialintelligencebasedautomaticassessmentoflowerlimbtorsiononmri AT sebastiankeil artificialintelligencebasedautomaticassessmentoflowerlimbtorsiononmri AT christianekuhl artificialintelligencebasedautomaticassessmentoflowerlimbtorsiononmri AT doritmerhof artificialintelligencebasedautomaticassessmentoflowerlimbtorsiononmri AT svennebelung artificialintelligencebasedautomaticassessmentoflowerlimbtorsiononmri |
_version_ |
1718372101587468288 |