A fully automated knee magnetic resonance imaging (MRI) segmentation method to study osteoarthritis (OA) was developed using a novel hierarchical set of random forests (RF) classifiers to learn the appearance of cartilage regions and their boundaries. A neighborhood approximation forest is used first to provide contextual feature to the second-level RF classifier that also considers local features and produces location-specific costs for the layered optimal graph image segmentation of multiple objects and surfaces (LOGISMOS) framework. Double-echo steady state MRIs used in this paper originated from the OA Initiative study. Trained on 34 MRIs with varying degrees of OA, the performance of the learning-based method tested on 108 MRIs showed significant reduction in segmentation errors ( ) compared with the conventional gradient-based and single-stage RF-learned costs. The 3-D LOGISMOS was extended to longitudinal-3-D (4-D) to simultaneously segment multiple follow-up visits of the same patient. As such, data from all time-points of the temporal sequence contribute information to a single optimal solution that utilizes both spatial 3-D and temporal contexts. 4-D LOGISMOS validation on 108 MRIs from baseline, and 12 month follow-up scans of 54 patients showed significant reduction in segmentation errors ( ) compared with 3-D. Finally, the potential of 4-D LOGISMOS was further explored on the same 54 patients using five annual follow-up scans demonstrating a significant improvement of measuring cartilage thickness ( ) compared with the sequential 3-D approach.

Background: Posttraumatic osteoarthritis (PTOA) of the subtalar joint is a serious, disabling, and frequent complication following intra-articular calcaneal fractures (IACFs). Using plain radiographs to assess the subtalar joint for PTOA is imprecise and insensitive, hindering progress toward improving treatment and assessing outcomes. This study explored how low-dose weightbearing computed tomography (WBCT) can be used to provide reliable, quantitative 3D measures of subtalar joint space width (JSW) following IACF and correlated the 3D JSW with clinical outcomes. Methods: After institutional review board approval, 21 patients (15 male; age, 28-70 years) who sustained IACFs and were treated with percutaneous surgical reduction underwent WBCT scans at follow-up visits 2 to 15 years (average, 7.8 years) after surgical treatment. Subtalar joint 3D JSW was computed after a semiautomated protocol was used to segment the talus and calcaneus from the WBCT data. Mean and minimum 3D JSW measurements were calculated and compared with Kellgren-Lawrence (KL) radiographic osteoarthritis grade, RAND-36 Physical (PCS) and Mental (MCS) Component Scores, and visual analog scale (VAS) pain scores. Spearman’s rank correlation was used to detect the strength of association between variables, with significance set at P < .05. Results: Mean 3D JSW values measured from WBCT for patients with IACFs ranged from 0.9 to 2.5 mm (1.7 ± 0.4 mm) over the entire subtalar joint. Intra- and interrater reliabilities for the WBCT-based JSW measurement technique were 0.95 (95% CI, 0.91-0.97) and 0.97 (95% CI, 0.95-0.98), respectively. Mean and minimum 3D JSW values correlated inversely with VAS pain scores and KL grade ( P < .05), particularly in central and posterior subtalar regions. Conclusion: WBCT-based methods were used to quantify the preservation/loss of JSW in patients with IACFs, enabling more accurate, definitive measurement of subtalar PTOA. The results of this study demonstrate that WBCT can be utilized to objectively assess subtalar PTOA and help us to better understand how arthritic changes affect actual patient experience. Level of Evidence: Level III, prognostic comparative study.

A vector force model systematically accounts for the multiple determinants of upper eyelid position in the setting of a trabeculectomy bleb. This model provides a framework for the evaluation of bleb-induced upper eyelid malposition and offers a logical, mathematical explanation for the occurrence of bleb-induced upper eyelid retraction and the usefulness of previously reported treatment modalities for this clinical entity.

Objectives: To quantify fracture severity for a series of displaced intra-articular calcaneal fractures (DIACFs) and correlate it with Sanders classification, post traumatic osteoarthritis (PTOA), and patient outcomes.

No abstract