BackgroundOsteophytes 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 (CT)-based study in patients awaiting total or partial knee arthroplasty were to: (1) measure osteophyte volume in anatomical sub-regions 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.MethodsData were obtained from 4,928 CT scans. Machine-learning-based imaging analyses enabled osteophyte segmentation and quantification, divided into anatomical regions. Mean three-dimensional joint space narrowing (3D-JSN) 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.ResultsTotal 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 3D-JSN in the femur or tibia. There was a direct relationship between osteophyte volume and OA severity.ConclusionsOsteophyte 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 osteoarthritis, both surgically and non-operatively.

PurposeAutomated 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.MethodsIn 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.ResultsThis 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.ConclusionsThe 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.

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.

We present a fully automatic model based system for segmenting the mandible, parotid and submandibular glands, brainstem, optic nerves and the optic chiasm in CT images, which won the MICCAI 2015 Head and Neck Auto Segmentation Grand Challenge. The method is based on Active Appearance Models (AAM) built from manually segmented examples via a cancer imaging archive provided by the challenge organisers. High quality anatomical correspondences for the models are generated using a Minimum Description Length (MDL) Groupwise Image Registration method. A multi start optimisation scheme is used to robustly match the model to new images. The model has been cross validated on the training data to a good degree of accuracy, and successfully segmented all the test data.

Purpose: An ACL tear is a common knee injury with an increased risk of developing knee OA in the longer term. The driving mechanisms behind this increased risk are not known but close monitoring of the early phase after injury may shed light on processes indicative of OA onset. In this study, we used a novel technique to monitor shape changes of bone occurring in the ACL injured knee over the first 5 years after injury. We explored changes during the first 2 years (BL→Y2), and during a subsequent three-year period (Y2→Y5) after an acute ACL tear. Methods: 121 young (32 women, mean age 26.1 years) active adults with an acute ACL tear in a previously un-injured knee were included in a treatment RCT (the KANON-trial). Patients were randomized to either rehabilitation plus early ACL reconstruction (ACLR, n=62) or rehabilitation plus the option of having a delayed ACLR if needed (n=59). During the 5 year follow up period, 30 (51%) of those randomized to the latter group had a delayed ACLR. 111 participants had MR images available for BL and 2 year FUP; 108 had 2 and 5 year MR images available. Femur, tibia and patella bone surfaces were automatically segmented from the MR images using active appearance models1 (Imorphics, UK). Bone area regions were calculated from the segmentations for the medial and lateral femur, tibia and patella. MR images from the right knee of a group of 167 participants (younger than 49 years) with no signs of radiographic OA at baseline and at 2 years were identified from the Osteoarthritis Initiative and were used as a reference. Change was expressed in percent difference over time with positive values indicating increasing bone area and was compared using the paired T-test. Results: For all regions of the knee and for both investigated time intervals, statistically significant changes of bone shape occurred with increased areas over time (p≤0.002). This change mainly occurred over the first 2 years after injury with the smallest increase in the lateral trochlea femur (mean increase 1%, 95% CI 0.7-1.2%) and the largest increase in medial femur (2.8%, 2.4-3.2%). Over the subsequent three year period smaller, albeit still significant, changes occurred with the smallest increase in bone area occurring in the lateral trochlea femur (0.4%, 0.1-0.6%) and the largest increase occurring in medial (1.4%, 0.9-1.9%) and lateral (1.4%, 0.9-1.9%) patella. The latter regions also showed the largest increase in bone area over the full 5 year period (4.1%, 3.2-4.9% respectively). The reference group without radiographic OA showed small or no significant change over a two year period (Table). Conclusion: Our results show that the shape of all bones in the ACL injured knee joint undergoes rapid change during the first 2 years after an ACL tear. These changes could be measured as an increase of bone area and continue at a lower rate during the following three years after injury. Possibly, these changes are early measures of osteophyte formation but such relations, and the relation to treatment of the initial ACL injury, need to be further explored.

Methods—We conducted a case-control study within the Osteoarthritis Initiative by identifying knees that developed incident tibiofemoral radiographic knee OA (case knees) over follow-up, and matching them to two random control knees. Using knee MRI's, we used active appearance modeling of the femur, tibia and patella and linear discriminant analysis to identify vectors that best classified knees having OA vs. not. Vectors were scaled such that -1 and +1 represented the mean non-OA and mean OA shapes, respectively. We examined the relation of 3D bone shape to incident OA (new onset Kellgren and Lawrence (KL) grade ≥2) occurring 12 months later using conditional logistic regression.

We present a fully automatic model based system for segmenting the prostate in magnetic resonance (MR) images. The segmentation method is based on Active Appearance Models (AAM) built from manually segmented examples provided by the MICCAI 2012 Promise12 team. High quality correspondences for the model are generated using a Minimum Description Length (MDL) Groupwise Image Registration method. A multi start optimisation scheme is used to robustly match the model to new images. The model has been cross validated on the training data to a good degree of accuracy, and successfully segmented all the test data.

The detection of cartilage loss due to disease progression in Osteoarthritis remains a challenging problem. We have shown previously that the sensitivity of detection from 3D MR images can be improved significantly by focusing on regions of `at risk' cartilage defined consistently across subjects and time-points. We define these regions in a frame of reference based on the bones, which requires that the bone surfaces are segmented in each image, and that anatomical correspondence is established between these surfaces. Previous results has shown that this can be achieved automatically using surface-based Active Appearance Models (AAMs) of the bones. In this paper we describe a method of refining the segmentations and correspondences by building a volumetric appearance model using the minimum message length principle. We present results from a study of 12 subjects which show that the new approach achieves a significant improvement in segmentation accuracy compared to the surface AAM approach, and reduce the variance in cartilage thickness measurements for key regions of interest. The study makes use of images of the same subjects obtained using different vendors' scanners, and also demonstrates the feasibility of multi-centre trials.

We describe the application of a novel analysis method that provides detailed maps of changes in cartilage thickness measured from MRI scans for individuals and cohorts of patients together with regional measures. A cohort of osteoarthritis patients was imaged using a 1.0 T MR scanner over a 36-month period. Hyaline cartilage was manually segmented from a three-dimensional (3D) spoiled gradient-echo sequence with fat suppression. Representative outlines of the bone surfaces of the distal femur and proximal tibia were automatically generated from T₂ weighted images using statistical models of the shape and appearance of the bones. Cartilage thickness was measured from a dense set of points representing the bony surface. The models of the bones provided a common frame of reference, relative to which change maps were generated and aggregated across the cohort and anatomically corresponding subregions of the joint to be identified. In the reproducibility arm involving six patients, the thickness of cartilage had coefficients of variation of 2.66% within the tibiofemoral joint and 2.94% within the medial femoral condyle region. In the 9 patients (6 female, 3 male) who completed the 36-month study, the most striking observation was that lack of change in global measures of cartilage thickness concealed substantial focal changes. Specifically, the cartilage thickness within the tibiofemoral joint decreased by 0.85% per annum (95% CI -2.13% to 0.45%) with the medial femoral condyle as the region with the most significant change, decreasing by 2.43% per annum (uncorrected 95% CI -4.31% to 0.51%).

Osteoarthritis (OA) involves changes in the composition and ultimately the loss of cartilage from articulating joints. MRI has the ability to non-invasively probe the compositional integrity of cartilage, thereby potentially identifying diseased cartilage before loss occurs. In this study we have developed a technique to compare local changes in signal intensity over time in fat suppressed 3D gradient echo MR images of articular cartilage in patients with OA. We have used an Active Appearance Model (AAM) based image registration to correspond locations within the cartilage in the same individual at different times. We have applied the technique to data taken over periods of 1 and 3 years in two groups of patients with established OA of the knee. In both these studies, no significant change in total cartilage volume could be detected but we were able to observe some significant changes in signal intensity. We conclude that in a study of cartilage structure the technique can provide additional information without the overhead of extra scans.

In this study we have developed techniques to compare local changes in signal intensity over time in fat suppressed 3D gradient echo MR images of articular cartilage in patients with osteoarthritis. We have applied these techniques to data taken over a periods of 1 and 3 years in two groups of patients with established OA of the knee. In both these studies, no significant change in total cartilage volume could be detected but we were able to observe some significant changes in signal intensity. We conclude that in a study of cartilage structure this technique can provide additional information without the overhead of extra scans.