Characterizing Osteophyte Formation in Knee Osteoarthritis: Application of Machine Learning Quantification of a Computerized Tomography Cohort: Implications for Treatment.

BACKGROUND: Osteophytes are commonly used to diagnose and guide knee osteoarthritis (OA) treatment, but their causes are unclear. Although they are not typically the focus of knee arthroplasty surgeons, they can predict case difficulty and length. Furthermore, their extent and location may yield much information about the knee joint status. The aims of this computed tomography-based study in patients awaiting total or partial knee arthroplasty were to: (1) measure osteophyte volume in anatomical subregions and relative change as total volume increases; (2) determine whether medial and/or lateral OA affects osteophyte distribution; and (3) explore relationships between osteophytes and OA severity. METHODS: Data were obtained from 4,928 computed tomography scans. Machine-learning-based imaging analyses enabled osteophyte segmentation and quantification, divided into anatomical regions. Mean three-dimensional joint space narrowing was assessed in medial and lateral compartments. A Bayesian model assessed the uniformity of osteophyte distribution. We correlated femoral osteophyte volumes with B-scores, a validated OA status measure. RESULTS: Total tibial (25%) and femoral osteophyte volumes (75%) within each knee correlated strongly (R2 = 0.85). Medial osteophytes (65.3%) were larger than lateral osteophytes (34.6%), with similar proportions in both the femur and tibia. Osteophyte growth was found in all compartments, and as total osteophyte volume increased, the relative distribution of osteophytes between compartments did not markedly change. No evidence of variation was found in the regional distribution of osteophyte volume between knees with medial, lateral, both, or no three-dimensional joint space narrowing in the femur or tibia. There was a direct relationship between osteophyte volume and OA severity. CONCLUSIONS: Osteophyte volume increased in both medial and lateral compartments proportionally with total osteophyte volume, regardless of OA location. The peripheral position of femoral osteophytes does not appear to contribute to load-bearing. This suggests that osteophytic growth represents a 'whole-knee'/global response. This work may have broad applications for knee OA, both surgically and nonoperatively.

Predicting robotic-assisted total knee arthroplasty operating time : benefits of machine-learning and 3D patient-specific data.

AIMS: No predictive model has been published to forecast operating time for total knee arthroplasty (TKA). The aims of this study were to design and validate a predictive model to estimate operating time for robotic-assisted TKA based on demographic data, and evaluate the added predictive power of CT scan-based predictors and their impact on the accuracy of the predictive model. METHODS: A retrospective study was conducted on 1,061 TKAs performed from January 2016 to December 2019 with an image-based robotic-assisted system. Demographic data included age, sex, height, and weight. The femoral and tibial mechanical axis and the osteophyte volume were calculated from CT scans. These inputs were used to develop a predictive model aimed to predict operating time based on demographic data only, and demographic and 3D patient anatomy data. RESULTS: The key factors for predicting operating time were the surgeon and patient weight, followed by 12 anatomical parameters derived from CT scans. The predictive model based only on demographic data showed that 90% of predictions were within 15 minutes of actual operating time, with 73% within ten minutes. The predictive model including demographic data and CT scans showed that 94% of predictions were within 15 minutes of actual operating time and 88% within ten minutes. CONCLUSION: The primary factors for predicting robotic-assisted TKA operating time were surgeon, patient weight, and osteophyte volume. This study demonstrates that incorporating 3D patient-specific data can improve operating time predictions models, which may lead to improved operating room planning and efficiency. Cite this article: Bone Jt Open 2022;3(5):383-389.

Precision, Reliability, and Responsiveness of a Novel Automated Quantification Tool for Cartilage Thickness: Data from the Osteoarthritis Initiative.

OBJECTIVE: Accurate automated segmentation of cartilage should provide rapid reliable outcomes for both epidemiological studies and clinical trials. We aimed to assess the precision and responsiveness of cartilage thickness measured with careful manual segmentation or a novel automated technique. METHODS: Agreement of automated segmentation was assessed against 2 manual segmentation datasets: 379 magnetic resonance images manually segmented in-house (training set), and 582 from the Osteoarthritis Initiative with data available at 0, 1, and 2 years (biomarkers set). Agreement of mean thickness was assessed using Bland-Altman plots, and change with pairwise Student t test in the central medial femur (cMF) and tibia regions (cMT). Repeatability was assessed on a set of 19 knees imaged twice on the same day. Responsiveness was assessed using standardized response means (SRM). RESULTS: Agreement of manual versus automated methods was excellent with no meaningful systematic bias (training set: cMF bias 0.1 mm, 95% CI ± 0.35; biomarkers set: bias 0.1 mm ± 0.4). The smallest detectable difference for cMF was 0.13 mm (coefficient of variation 3.1%), and for cMT 0.16 mm(2.65%). Reported change using manual segmentations in the cMF region at 1 year was -0.031 mm (95% CI -0.022, -0.039), p < 10-4, SRM -0.31 (-0.23, -0.38); and at 2 years was -0.071 (-0.058, -0.085), p < 10-4, SRM -0.43 (-0.36, -0.49). Reported change using automated segmentations in the cMF at 1 year was -0.059 (-0.047, -0.071), p < 10-4, SRM -0.41 (-0.34, -0.48); and at 2 years was -0.14 (-0.123, -0.157, p < 10-4, SRM -0.67 (-0.6, -0.72). CONCLUSION: A novel cartilage segmentation method provides highly accurate and repeatable measures with cartilage thickness measurements comparable to those of careful manual segmentation, but with improved responsiveness.

Evaluation of segmentation methods on head and neck CT: Auto-segmentation challenge 2015.

PURPOSE: Automated delineation of structures and organs is a key step in medical imaging. However, due to the large number and diversity of structures and the large variety of segmentation algorithms, a consensus is lacking as to which automated segmentation method works best for certain applications. Segmentation challenges are a good approach for unbiased evaluation and comparison of segmentation algorithms. METHODS: In this work, we describe and present the results of the Head and Neck Auto-Segmentation Challenge 2015, a satellite event at the Medical Image Computing and Computer Assisted Interventions (MICCAI) 2015 conference. Six teams participated in a challenge to segment nine structures in the head and neck region of CT images: brainstem, mandible, chiasm, bilateral optic nerves, bilateral parotid glands, and bilateral submandibular glands. RESULTS: This paper presents the quantitative results of this challenge using multiple established error metrics and a well-defined ranking system. The strengths and weaknesses of the different auto-segmentation approaches are analyzed and discussed. CONCLUSIONS: The Head and Neck Auto-Segmentation Challenge 2015 was a good opportunity to assess the current state-of-the-art in segmentation of organs at risk for radiotherapy treatment. Participating teams had the possibility to compare their approaches to other methods under unbiased and standardized circumstances. The results demonstrate a clear tendency toward more general purpose and fewer structure-specific segmentation algorithms.

Cloud-Based Evaluation of Anatomical Structure Segmentation and Landmark Detection Algorithms: VISCERAL Anatomy Benchmarks.

Variations in the shape and appearance of anatomical structures in medical images are often relevant radiological signs of disease. Automatic tools can help automate parts of this manual process. A cloud-based evaluation framework is presented in this paper including results of benchmarking current state-of-the-art medical imaging algorithms for anatomical structure segmentation and landmark detection: the VISCERAL Anatomy benchmarks. The algorithms are implemented in virtual machines in the cloud where participants can only access the training data and can be run privately by the benchmark administrators to objectively compare their performance in an unseen common test set. Overall, 120 computed tomography and magnetic resonance patient volumes were manually annotated to create a standard Gold Corpus containing a total of 1295 structures and 1760 landmarks. Ten participants contributed with automatic algorithms for the organ segmentation task, and three for the landmark localization task. Different algorithms obtained the best scores in the four available imaging modalities and for subsets of anatomical structures. The annotation framework, resulting data set, evaluation setup, results and performance analysis from the three VISCERAL Anatomy benchmarks are presented in this article. Both the VISCERAL data set and Silver Corpus generated with the fusion of the participant algorithms on a larger set of non-manually-annotated medical images are available to the research community.

Osteoarthritic bone marrow lesions almost exclusively colocate with denuded cartilage: a 3D study using data from the Osteoarthritis Initiative.

OBJECTIVES: The aetiology of bone marrow lesions (BMLs) in knee osteoarthritis (OA) is poorly understood. We employed three-dimensional (3D) active appearance modelling (AAM) to study the spatial distribution of BMLs in an OA cohort and compare this with the distribution of denuded cartilage. METHODS: Participants were selected from the Osteoarthritis Initiative progressor cohort with Kellgren-Lawrence scores ≥2, medial joint space narrowing and osteophytes. OA and ligamentous BMLs and articular cartilage were manually segmented. Bone surfaces were automatically segmented by AAM. Cartilage thickness of <0.5 mm was defined as denuded and ≥0.5-1.5 mm as severely damaged. Non-quantitative assessment and 3D population maps were used for analysing the comparative position of BMLs and damaged cartilage. RESULTS: 88 participants were included, 45 men, mean age (SD) was 61.3 (9.9) years and mean body mass index was 31.1 (4.6) kg/m(2). 227 OA and 107 ligamentous BMLs were identified in 86.4% and 73.8% of participants; OA BMLs were larger. Denuded cartilage was predominantly confined to a central region on the medial femur and tibia, and the lateral facet of the trochlear femur. 67% of BMLs were colocated with denuded cartilage and a further 21% with severe cartilage damage. In the remaining 12%, 25/28 were associated with cartilage defects. 74% of all BMLs were directly opposing (kissing) another BML across the joint. CONCLUSIONS: There was an almost exclusive relationship between the location of OA BML and cartilage denudation, which itself had a clear spatial pattern. We propose that OA, ligamentous and traumatic BMLs represent a bone response to abnormal loading.

A novel method for bone area measurement provides new insights into osteoarthritis and its progression.

BACKGROUND: Modern image analysis enables the accurate quantification of knee osteoarthritis (OA) bone using MRI. We hypothesised that three-dimensional changes in bone would be characteristic of OA and provide a responsive measure of progression. METHODS: 1312 participants with radiographic knee OA, and 885 non-OA controls with MRIs at baseline, 1, 2 and 4 years were selected from the NIH Osteoarthritis Initiative. Automated segmentation of all knee bones and calculation of bone area was performed using active appearance models. In a subset of 352 participants, responsiveness of bone area change was compared with change in radiographic joint space width (JSW) and MRI cartilage thickness over a 2-year period. RESULTS: All OA knee compartments showed increased bone area over time compared with non-OA participants: for example, the 4-year percentage change from baseline in medial femur area for OA (95% CI) was 1.87(0.13), non-OA 0.43 (0.07); p<0.0001. Bone area change was more responsive than cartilage thickness or JSW; 2-year SRM for bone area in the medial femur was 0.83, for the most responsive cartilage thickness measure central medial femorotibial composite (cMFTC): 0.38, JSW: 0.35. Almost half of all knees had change greater than smallest detectable difference at 2 years. Body mass index, gender and alignment had only a small effect on the rate of change of bone area. CONCLUSIONS: Changes in bone area discriminated people with OA from controls and was more responsive than the current and impending standards for assessing OA progression. The shape change in OA bone provides a new window on OA pathogenesis and a focus for clinical trials.

Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge.

Prostate MRI image segmentation has been an area of intense research due to the increased use of MRI as a modality for the clinical workup of prostate cancer. Segmentation is useful for various tasks, e.g. to accurately localize prostate boundaries for radiotherapy or to initialize multi-modal registration algorithms. In the past, it has been difficult for research groups to evaluate prostate segmentation algorithms on multi-center, multi-vendor and multi-protocol data. Especially because we are dealing with MR images, image appearance, resolution and the presence of artifacts are affected by differences in scanners and/or protocols, which in turn can have a large influence on algorithm accuracy. The Prostate MR Image Segmentation (PROMISE12) challenge was setup to allow a fair and meaningful comparison of segmentation methods on the basis of performance and robustness. In this work we will discuss the initial results of the online PROMISE12 challenge, and the results obtained in the live challenge workshop hosted by the MICCAI2012 conference. In the challenge, 100 prostate MR cases from 4 different centers were included, with differences in scanner manufacturer, field strength and protocol. A total of 11 teams from academic research groups and industry participated. Algorithms showed a wide variety in methods and implementation, including active appearance models, atlas registration and level sets. Evaluation was performed using boundary and volume based metrics which were combined into a single score relating the metrics to human expert performance. The winners of the challenge where the algorithms by teams Imorphics and ScrAutoProstate, with scores of 85.72 and 84.29 overall. Both algorithms where significantly better than all other algorithms in the challenge (p<0.05) and had an efficient implementation with a run time of 8min and 3s per case respectively. Overall, active appearance model based approaches seemed to outperform other approaches like multi-atlas registration, both on accuracy and computation time. Although average algorithm performance was good to excellent and the Imorphics algorithm outperformed the second observer on average, we showed that algorithm combination might lead to further improvement, indicating that optimal performance for prostate segmentation is not yet obtained. All results are available online at http://promise12.grand-challenge.org/.

Magnetic resonance imaging-based three-dimensional bone shape of the knee predicts onset of knee osteoarthritis: data from the osteoarthritis initiative.

OBJECTIVE: To examine whether magnetic resonance imaging (MRI)-based 3-dimensional (3-D) bone shape predicts the onset of radiographic knee osteoarthritis (OA). METHODS: We conducted a case-control study using data from the Osteoarthritis Initiative by identifying knees that developed incident tibiofemoral radiographic knee OA (case knees) during followup, and matching them each to 2 random control knees. Using knee MRIs, we performed active appearance modeling of the femur, tibia, and patella and linear discriminant analysis to identify vectors that best classified knees with OA versus those without OA. Vectors were scaled such that -1 and +1 represented the mean non-OA and mean OA shapes, respectively. We examined the relation of 3-D bone shape to incident OA (new-onset Kellgren and Lawrence [K/L] grade ≥2) occurring 12 months later using conditional logistic regression. RESULTS: A total of 178 case knees (incident OA) were matched to 353 control knees. The whole joint (i.e., tibia, femur, and patella) 3-D bone shape vector had the strongest magnitude of effect, with knees in the highest tertile having a 3.0 times higher likelihood of developing incident radiographic knee OA 12 months later compared with those in the lowest tertile (95% confidence interval [95% CI] 1.8-5.0, P < 0.0001). The associations were even stronger among knees that had completely normal radiographs before incidence (K/L grade of 0) (odds ratio 12.5 [95% CI 4.0-39.3]). Bone shape at baseline, often several years before incidence, predicted later OA. CONCLUSION: MRI-based 3-D bone shape predicted the later onset of radiographic OA. Further study is warranted to determine whether such methods can detect treatment effects in trials and provide insight into the pathophysiology of OA development.