Simultaneous segmentation of the bone and cartilage surfaces of a knee joint in 3D

Abstract

We present a novel framework for the simultaneous segmentation of multiple interacting surfaces belonging to multiple mutually interacting objects. The method is a non-trivial extension of our previously reported optimal multi-surface segmentation. Considering an example application of knee-cartilage segmentation, the framework consists of the following main steps: 1) Shape model construction: Building a mean shape for each bone of the joint (femur, tibia, patella) from interactively segmented volumetric datasets. Using the resulting mean-shape model -identification of cartilage, non-cartilage, and transition areas on the mean-shape bone model surfaces. 2) Presegmentation: Employment of iterative optimal surface detection method to achieve approximate segmentation of individual bone surfaces. 3) Cross-object surface mapping: Detection of inter-bone equidistant separating sheets to help identify corresponding vertex pairs for all interacting surfaces. 4) Multi-object, multi-surface graph construction and final segmentation: Construction of a single multi-bone, multi-surface graph so that two surfaces (bone and cartilage) with zero and non-zero intervening distances can be detected for each bone of the joint, according to whether or not cartilage can be locally absent or present on the bone. To define inter-object relationships, corresponding vertex pairs identified using the separating sheets were interlinked in the graph. The graph optimization algorithm acted on the entire multiobject, multi-surface graph to yield a globally optimal solution.The segmentation framework was tested on 16 MR-DESS knee-joint datasets from the Osteoarthritis Initiative database. The average signed surface positioning error for the 6 detected surfaces ranged from 0.00 to 0.12 mm. When independently initialized, the signed reproducibility error of bone and cartilage segmentation ranged from 0.00 to 0.26 mm. The results showed that this framework provides robust, accurate, and reproducible segmentation of the knee joint bone and cartilage surfaces of the femur, tibia, and patella. As a general segmentation tool, the developed framework can be applied to a broad range of multi-object segmentation problems.Medical image segmentation is a continuously evolving field. Due to the anatomical complexity and possible presence of pathologies, segmentation tools for general purpose tasks are difficult to derive. The medical image analysis objects of interest are typically three-dimensional, and they frequently consist of 3D regions separated by interacting surfaces, e.g., inner and outer vascular walls, endo-and epicardial heart surfaces, multi-layer structure of human retina, etc. These are intra-object interactions. Similarly, organs typically occur in prespecified anatomical relationships and it seems advantageous to consider such relationships when segmenting the medical images, e.g., the mutual positions of cardiac ventricles and atria, of the prostate and bladder, etc. These are inter-object relationships. Yet, most of the contemporary metho...

Implementation of Discrete Element Analysis for Subject-Specific, Population-Wide Investigations of Habitual Contact Stress Exposure

“…The limit of practicality for manual segmentations (in 3D) is in the range of dozens of cases, reasonable for moderate-sized series. Continuing developments in automated segmentation (Yin et al, 2009) hold promise for studying hundreds or even thousands of subjects. Manual segmentations generate point clouds (x, y, z points) for the articulating bone surfaces, and in the case of MRI, for their overlying cartilage regions, and triangulated surfaces are fit to these point cloud data ( Figure 1b).…”

Femoral cartilage segmentation in Knee MRI scans using two stage voxel classification

“…al. proposed a method for simultaneous segmentation of bone and cartilage surfaces [9]. A fully automatic method was proposed by Seim et.…”

Electric field theory based approach to search-direction line definition in image segmentation: application to optimal femur-tibia cartilage segmentation in knee-joint 3-D MR

“…Therefore, the mapping procedure avoids surface regeneration and merging 12 (which is usually difficult) and enhances robustness regarding to local roughness of the surface when comparing with our previously introduced nearest point based mapping techniques. 8,11 In the following section, we will show how the properties of ELF can be used for bifurcation detection, inter-surface mapping and multiple surfaces on multiple coupled objects segmentation.…”

“…The correspondent pairs and their ELF direction connections are used for inter-object graph link construction. 8,11 For graph cost design, we use gradient information as surface cost at non-cartilage region and Random Forest output unlikeness as regional cost 18 at transitional and cartilage regions. The global minimum cost solution for this graph gives optimal bone-cartilage delineation for all bones simultaneously.…”

“…The results of our previous attempt to solve this task were reported in 2009. 8 We introduced a general framework to solve so-called multi-object multi-surface segmentation problem. This framework includes: 1) Model formation, 2) bone presegmentation, 3) cross-object surface mapping, and 4) final bone-cartilage segmentation.…”