Three-dimensional (3D)-image-based anatomical analysis of rotator cuff tear patients has been proposed as a way to improve repair prognosis analysis to reduce the incidence of postoperative retear. However, for application in clinics, an efficient and robust method for the segmentation of anatomy from MRI is required. We present the use of a deep learning network for automatic segmentation of the humerus, scapula, and rotator cuff muscles with integrated automatic result verification. Trained on N = 111 and tested on N = 60 diagnostic T1-weighted MRI of 76 rotator cuff tear patients acquired from 19 centers, a nnU-Net segmented the anatomy with an average Dice coefficient of 0.91 ± 0.06. For the automatic identification of inaccurate segmentations during the inference procedure, the nnU-Net framework was adapted to allow for the estimation of label-specific network uncertainty directly from its subnetworks. The average Dice coefficient of segmentation results from the subnetworks identified labels requiring segmentation correction with an average sensitivity of 1.0 and a specificity of 0.94. The presented automatic methods facilitate the use of 3D diagnosis in clinical routine by eliminating the need for time-consuming manual segmentation and slice-by-slice segmentation verification.

Purpose Preservation surgery can halt the progress of joint degradation, preserving the life of the hip; however, outcome depends on the existing cartilage quality. Biochemical analysis of the hip cartilage utilizing MRI sequences such as delayed gadolinium-enhanced MRI of cartilage (dGEMRIC), in addition to morphological analysis, can be used to detect early signs of cartilage degradation. However, a complete, accurate 3D analysis of the cartilage regions and layers is currently not possible due to a lack of diagnostic tools. Methods A system for the efficient automatic parametrization of the 3D hip cartilage was developed. 2D U-nets were trained on manually annotated dual-flip angle (DFA) dGEMRIC for femoral head localization and cartilage segmentation. A fully automated cartilage sectioning pipeline for analysis of central and peripheral regions, femoral-acetabular layers, and a variable number of section slices, was developed along with functionality for the automatic calculation of dGEMRIC index, thickness, surface area, and volume. Results The trained networks locate the femoral head and segment the cartilage with a Dice similarity coefficient of 88 ± 3 and 83 ± 4% on DFA and magnetization-prepared 2 rapid gradient-echo (MP2RAGE) dGEMRIC, respectively. A completely automatic cartilage analysis was performed in 18s, and no significant difference for average dGEMRIC index, volume, surface area, and thickness calculated on manual and automatic segmentation was observed. Conclusion An application for the 3D analysis of hip cartilage was developed for the automated detection of subtle morphological and biochemical signs of cartilage degradation in prognostic studies and clinical diagnosis. The segmentation network achieved a 4-time increase in processing speed without loss of segmentation accuracy on both normal and deformed anatomy, enabling accurate parametrization. Retraining of the networks with the promising MP2RAGE protocol would enable analysis without the need for B1 inhomogeneity correction in the future.

Background: Delayed gadolinium-enhanced magnetic resonance imaging of cartilage (dGEMRIC) allows objective and noninvasive assessment of cartilage quality. An interim analysis 1 year after correction of femoroacetabular impingement (FAI) previously showed that the dGEMRIC index decreased despite good clinical outcome. Purpose: To evaluate dGEMRIC indices longitudinally in patients who underwent FAI correction and in a control group undergoing nonoperative treatment for FAI. Study Design: Cohort study; Level of evidence, 3. Methods: This prospective, comparative longitudinal study included 39 patients (40 hips) who received either operative (n = 20 hips) or nonoperative (n = 20 hips) treatment. Baseline demographic characteristics and presence of osseous deformities did not differ between groups. All patients received indirect magnetic resonance arthrography at 3 time points (baseline, 1 and 3 years of follow-up). The 3-dimensional cartilage models were created using a custom-developed deep learning–based software. The dGEMRIC indices were determined separately for acetabular and femoral cartilage. A mixed-effects model was used for statistical analysis in repeated measures. Results: The operative group showed an initial (preoperative to 1-year follow-up) decrease of dGEMRIC indices: acetabular from 512 ± 174 to 392 ± 123 ms and femoral from 530 ± 173 to 411 ± 117 ms (both P < .001). From 1-year to 3-year follow-up, dGEMRIC indices improved again: acetabular from 392 ± 123 to 456 ± 163 ms and femoral from 411 ± 117 to 477 ± 169 ms (both P < .001). The nonoperative group showed no significant changes in dGEMRIC indices in acetabular and femoral cartilage from baseline to either follow-up point (all P > .05). Conclusion: This study showed that 3 years after FAI correction, the dGEMRIC indices improved compared with short-term 1-year follow-up. This may be due to normalized joint biomechanics or regressive postoperative activation of the inflammatory cascade after intra-articular surgery.

(1) Background: To evaluate the performance of a deep learning model to automatically segment femoral head necrosis (FHN) based on a standard 2D MRI sequence compared to manual segmentations for 3D quantification of FHN. (2) Methods: Twenty-six patients (thirty hips) with avascular necrosis underwent preoperative MR arthrography including a coronal 2D PD-w sequence and a 3D T1 VIBE sequence. Manual ground truth segmentations of the necrotic and unaffected bone were then performed by an expert reader to train a self-configuring nnU-Net model . Testing of the network performance was performed using a 5-fold cross-validation and Dice coefficients were calculated. In addition, performance across the three segmentations were compared using six parameters: volume of necrosis, volume of unaffected bone, percent of necrotic bone volume, surface of necrotic bone, unaffected femoral head surface, and percent of necrotic femoral head surface area. (3) Results: Comparison between the manual 3D and manual 2D segmentations as well as 2D with the automatic model yielded significant, strong correlations (Rp > 0.9) across all six parameters of necrosis. Dice coefficients between manual- and automated 2D segmentations of necrotic- and unaffected bone were 75 ± 15% and 91 ± 5%, respectively. None of the six parameters of FHN differed between the manual and automated 2D segmentations and showed strong correlations (Rp > 0.9). Necrotic volume and surface area showed significant differences (all p < 0.05) between early and advanced ARCO grading as opposed to the modified Kerboul angle, which was comparable between both groups (p > 0.05). (4) Conclusions: Our deep learning model to automatically segment femoral necrosis based on a routine hip MRI was highly accurate. Coupled with improved quantification for volume and surface area, as opposed to 2D angles, staging and course of treatment can become better tailored to patients with varying degrees of AVN.