LOGISMOS—Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces: Cartilage Segmentation in the Knee Joint

Abstract

A novel method for simultaneous segmentation of multiple interacting surfaces belonging to multiple interacting objects, called LOGISMOS (layered optimal graph image segmentation of multiple objects and surfaces), is reported. The approach is based on the algorithmic incorporation of multiple spatial inter-relationships in a single n-dimensional graph, followed by graph optimization that yields a globally optimal solution. The LOGISMOS method’s utility and performance are demonstrated on a bone and cartilage segmentation task in the human knee joint. Although trained on only a relatively small number of nine example images, this system achieved good performance. Judged by dice similarity coefficients (DSC) using a leave-one-out test, DSC values of 0.84 ± 0.04, 0.80 ± 0.04 and 0.80 ± 0.04 were obtained for the femoral, tibial, and patellar cartilage regions, respectively. These are excellent DSC values, considering the narrow-sheet character of the cartilage regions. Similarly, low signed mean cartilage thickness errors were obtained when compared to a manually-traced independent standard in 60 randomly selected 3-D MR image datasets from the Osteoarthritis Initiative database—0.11 ± 0.24, 0.05 ± 0.23, and 0.03 ± 0.17 mm for the femoral, tibial, and patellar cartilage thickness, respectively. The average signed surface positioning errors for the six detected surfaces ranged from 0.04 ± 0.12 mm to 0.16 ± 0.22 mm. The reported LOGISMOS framework provides robust and accurate 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 multiobject multisurface segmentation problems.

Automated segmentation and quantitative analysis of the hip joint from magnetic resonance images

“…The original multi-layered graph search framework (Yin et al 2010) has successfully applied to the knee joint for simultaneous segmentation of the cartilages. However, this approach is not readily applicable to the delineation of multiple surfaces with poor separation of boundaries, e.g., the femoral and acetabular plates.…”

“…The optimal graph search approach originally presented in (Li et al 2006;Wu and Chen 2002) has been used extensively in medical image analysis applications (Li et al 2005;Song et al 2013;2010;Yin et al 2010) for successful simultaneous segmentation of multiple object surfaces with mutually interacting surface constraints (e.g., no intersection) encoded.…”

“…To facilitate this, automated MR-based segmentation approaches are being developed to circumvent the need for extensive time-and expertise-intensive manual/semi-automated segmentation of osteochondral elements in the hip region (Kavanagh et al 2011;Naish et al 2006). In previous MR studies, advanced image analysis approaches such as SSM (Cootes et al 1995), atlas-based and graph search approaches have been successfully applied to automatic bone segmentation of the knee (Ababneh et al 2011;Fripp et al 2007;Shan et al 2012;Yin et al 2010), ankle (Li et al 2005) and spine ) and for use in subsequent segmentation of the cartilage Seim et al 2010).…”

“…Currently, due to anatomical and imaging challenges particularly for the hip joint (Section 1.3), MR-based quantitative analyses for hip joint cartilages have not paralleled advances in comparable work with the knee joint Tamez-Pena et al 2012;Yin et al 2010). Compared with the knee joint, the highly curved hip cartilages are much thinner with an average thickness of 1.4 and 1.2 mm for the femoral head and acetabular plates, respectively (Hodler et al 1992).…”

“…This developed scheme relies on the following processes: bone pre-segmentation using a 3D ASM algorithm introduced in Chapter 3, extraction of the BCI and segmentation of the hip joint cartilage using an improved multi-layered graph search algorithm (Yin et al 2010).…”