Osteoarthritis imaging最新文献

INTRODUCTION

Non-invasive monitoring of VC using segmentation of MRI images has become vital part of clinical trials and longitudinal OA studies. Many parts of protocol such as MR sequence parameters, MR hardware or time between follow-ups are fixed to ensure that the observed change in VC caused by degenerative/regenerative processes and not by other confounders. Consistent patient positioning during follow-up visits improves the overall precision, however due to various reasons, such as pain, same positioning might not be possible.

OBJECTIVE

Objective of this study was to assess an effect of the patient positioning on the femoral VC.

METHODS

The left knees of eight healthy volunteers (4 male, 4 female, mean age: 35.5 ± 10.2 years) were scanned on 3T Siemens PrismaFit (Siemens Healthineers AG, Forchheim, Germany). The 3D DESS (TE=5ms, TR=14.1ms, 160 slices, 0.6x0.6x0.6mm3, flip angle=25°, acquisition=5:58min) was used. Each volunteer's patella center was marked with a black line, and two additional lines spaced 1cm apart were drawn on each side. A dedicated 15-channel knee coil was positioned to align these lines with the scanner laser, resulting in five different knee positions: neutral, two medial rotations, and two lateral rotations. Knee rotation angles were measured using RadiAnt DICOM Viewer (Medixant, Poznań, Poland) (Fig. 1). Images were segmented automatically using MR ChondralHealth version 3.1 research application software (Siemens Healthineers AG, Forchheim, Germany), then manually edited if needed. Voxel volume times number of voxels yielded the VC for nine femoral cartilage regions: medial anterior (MaF)/central (McF)/posterior (MpF); trochlear lateral (TL)/central (TC)/medial (TM) and lateral anterior (LaF)/central (LcF)/posterior (LpF). The correlation between knee rotation angle and VC was assessed using Spearman's correlation coefficient.

RESULTS

Observed correlations were as follows: MaF = -0.06, McF = -0.18, MpF = -0.3, TL = 0.07, TC = 0.05, TM = 0.01, LaF = 0.15, LcF = -0.12, LpF = -0.2.

CONCLUSION

While there are observable correlations between knee rotation angle and femoral VC in healthy individuals, these correlations are generally weak and vary across different cartilage regions. Volume of trochlear cartilage is essentially unaffected by knee positioning, while the posterior condyle region exhibit weak negative correlation, implying the false VC decrease. Further quantification of the effect using linear mixed effects models is planned in the future. While the impact of positioning on VC is negligible, if the anticipated change in VC is expected to be small in longitudinal studies, it's crucial to validate the intended segmentation method in comparable situations.

INTRODUCTION

Exploring ways to improve methodologies for model training in MRI-based segmentation tasks is important for enhancing segmentation accuracy. Accurate automated segmentations are essential for applications including the extraction of imaging biomarkers. Leveraging advanced deep learning techniques, such as nnU-Net, holds promise for achieving precise segmentations. Additionally, incorporating multiple image outputs from Dixon MRI into these methodologies could improve segmentation performance.

OBJECTIVE

The aim of the study was to investigate whether the accuracy of an automated deep learning segmentation model for the hip joint could be improved by combining information from multiple image outputs from a Dixon sequence.

METHODS

Manual segmentations of 20 participants (40 hips) of the Generation R study, comprising individuals who were 19 years old (11 males, 9 females), were used to train an nnU-Net. The segmented regions included the femoral bone, acetabular bone, femoral cartilage, and acetabular cartilage in both the left and right hip. The 2D and 3D configurations of the nnU-Net were trained using 5-fold cross-validation and an ensemble of the 2D-3D configurations was used in the analyses. The input consisted of 1) water-only images from the Lava Flex sequence, with an in-plane resolution of 0.89 × 0.89 mm² and a slice thickness of 1.2 mm, 2) a combination of in-phase and water-only images, as well as 3) a combination of water-only and fat-only images from the same sequence, allowing for comparison between the methodologies. The combination of water-only and in-phase images was chosen for potentially increasing segmentation accuracy, following visual inspection. Additionally, the water-only and fat-only combination aimed to assess if segmentation results could be enhanced by offering additional tissue contrast. Evaluation was performed on a hold-out test set consisting of 10 manually segmented hips, using the Dice similarity coefficient (DSC) and mean surface distance (MSD).

RESULTS

The mean ±SD DSC for the segmentation of bone and cartilage in the hip using the 1) water-only vs 2) in-phase and water-only combination vs. 3) combination of fat-only and water-only images were as follows: femoral bone 1) 0.961±0.013 vs. 2) 0.967±0.004 vs. 3) 0.950±0.036, acetabular bone 1) 0.886±0.027 vs. 2) 0.893±0.021 vs. 3) 0.896±0.016, femoral cartilage 1) 0.762±0.018 vs. 2) 0.763±0.020 vs. 3) 0.752±0.023, and acetabular cartilage 1) 0.760±0.028 vs. 2) 0.768±0.022 vs. 3) 0.768±0.022. The MSDs were: femoral bone 1) 0.412± 0.105 mm vs. 2) 0.341±0.047 mm vs. 3) 0.297±5.59 mm, acetabular bone 1) 0.602±0.109 mm vs. 2) 0.567±0.097 mm vs. 3) 0.651±0.077 mm, femoral cartilage 1) 0.276±0.033 mm vs. 2) 0.271±0.034 mm vs. 3) 0.295±0.033 mm, and acetabular cartilage 1) 0.313±0.078 mm vs. 2) 0.282±0.049 mm vs. 3) 0.281±0.046 mm.

CONCLUSION<