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.
Highlights
Abnormal torsion of the lower limbs may adversely affect joint health
Originating in the 1970s, torsional alignment has traditionally been measured by computed tomography (CT)[8]
To reduce radiation exposure to the paediatric patient population, Magnetic Resonance Imaging (MRI) techniques have e volved[9] to be diagnostically equivalent with traditional CT techniques while fitting into tight clinical s chedules[10,11]. For both CT and MRI, accuracy and reliability are challenged by substantial intra- and inter-reader variability that may be as high as 10.8° and 15.6°, r espectively[12], which may be largely attributed to inconsistent level, obliquity, and method of selecting the respective reference lines[8,10]
Summary
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. To reduce radiation exposure to the paediatric patient population, Magnetic Resonance Imaging (MRI) techniques have e volved[9] to be diagnostically equivalent with traditional CT techniques while fitting into tight clinical s chedules[10,11] For both CT and MRI, accuracy and reliability are challenged by substantial intra- and inter-reader variability that may be as high as 10.8° and 15.6°, r espectively[12], which may be largely attributed to inconsistent level, obliquity, and method of selecting the respective reference lines[8,10]. Even with à-priori selected axial or oblique images, the variability persisted[8,13], highlighting the difficulty of correctly and reliably identifying pertinent axes in 3D objects (such as bone) using 2D images In this era of much-sought standardization, there is a clear need for standardized, accurate, and reproducible evaluation of lower limb torsion that may be addressed by deep learning. Deep learning techniques refer to a subtype of machine learning that rely on computational networks to learn from image data by progressively
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
