A Logarithmic Opinion Pool Based STAPLE Algorithm for the Fusion of Segmentations With Associated Reliability Weights

Abstract

Pelvic floor dysfunction is very common in women after childbirth and precise segmentation of magnetic resonance images (MRI) of the pelvic floor may facilitate diagnosis and treatment of patients. However, because of the complexity of the structures of pelvic floor, manual segmentation of the pelvic floor is challenging and suffers from high inter and intra-rater variability of expert raters. Multiple template fusion algorithms are promising techniques for segmentation of MRI in these types of applications, but these algorithms have been limited by imperfections in the alignment of each template to the target, and by template segmentation errors. In this class of segmentation techniques, a collection of templates is aligned to a target, and a new segmentation of the target is inferred. A number of algorithms sought to improve segmentation performance by combining image intensities and template labels as two independent sources of information, carrying out decision fusion through local intensity weighted voting schemes. This class of approach is a form of linear opinion pooling, and achieves unsatisfactory performance for this application. We hypothesized that better decision fusion could be achieved by assessing the contribution of each template in comparison to a reference standard segmentation of the target image and developed a novel segmentation algorithm to enable automatic segmentation of MRI of the female pelvic floor. The algorithm achieves high performance by estimating and compensating for both imperfect registration of the templates to the target image and template segmentation inaccuracies. The algorithm is a generalization of the STAPLE algorithm in which a reference segmentation is estimated and used to infer an optimal weighting for fusion of templates. A local image similarity measure is used to infer a local reliability weight, which contributes to the fusion through a novel logarithmic opinion pooling. We evaluated our new algorithm in comparison to nine state-of-the-art segmentation methods by comparison to a reference standard derived from repeated manual segmentations of each subject image and demonstrate our algorithm achieves the highest performance. This automated segmentation algorithm is expected to enable widespread evaluation of the female pelvic floor for diagnosis and prognosis in the future.

Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure

“…For each MS patient case, an unprecedented number of seven manual delineations was gathered, from trained experts split over the three sites providing MR images. From these segmentations, a consensus “ground truth” segmentation was built for evaluation with the LOP STAPLE algorithm 10 . We present in Fig.…”

“…This method gathered the other thirteen teams segmentations in a consensus through label fusion using the LOP STAPLE algorithm 10 . The goal of this fourteenth method was to evaluate the capability of such a label fusion method to overpass the individual difficulties of each method and thus obtain results closer to the ground truth.…”

“…To cope with this problem, we computed for each patient a consensus segmentation by using the Logarithmic Opinion Pool Based STAPLE (LOP STAPLE) algorithm proposed by 10 . This algorithm computes iteratively, using an Expectation-Maximization approach, a consensus segmentation based on penalties for individual deviations from agreement between manual experts segmentations.…”

Multi-atlas segmentation of biomedical images: A survey

“…The original STAPLE algorithm only supported binary segmentations (Warfield et al, 2004), but was soon after extended to the multi-class setting (Rohlfing et al, 2003b,c,d). Many extensions of STAPLE correspond (or can be shown to correspond) to modifications of the original probabilistic model, for example placing a Beta prior on the parameters of the confusion matrix (Commowick and Warfield, 2010), replacing the hard atlas segmentations with probabilistic maps (Weisenfeld and Warfield, 2011b), dealing with missing atlas label data (Landman et al, 2012b), altering the confusion matrix to account for self-assessed uncertainty (Asman and Landman, 2011; Bryan et al, 2014), employing a hierarchical noise model (Asman and Landman, 2014), introducing and estimating unknown reliability weight maps (Akhondi-Asl et al, 2014), and learning and exploiting the relationship between performance parameters and intensity similarities (Gorthi et al, 2014). …”

“…Finally, there are many other applications that have benefited from MAS within human medical imaging, including: segmentation of pelvic bones in MRI (Weisenfeld and Warfield, 2011b; Akhondi-Asl et al, 2014); lungs in CT scans (van Rikxoort et al, 2009) and chest X-rays (Candemir et al, 2014); heart and its ventricles in CT (van Rikxoort et al, 2010; Dey et al, 2010), MRI (Zhuang et al, 2010; Zuluaga et al, 2014), MR angiography (Wachinger and Golland, 2012), ultrasound (Wang et al, 2014a), and CT angiography (Kirişli et al, 2010; Yang et al, 2014a); breast tissues and lesions in X-ray mammography (Iglesias and Karssemeijer, 2009) and MRI (Gubern-Mérida et al, 2012; Lee et al, 2013); cartilage and bone in knee MRI (Tamez-Pena et al, 2012; Lee et al, 2014b; Shan et al, 2014); the vertebrae in spinal MRI (Asman et al, 2014); scar tissue in intravascular coronary optical coherence tomography (OCT) (Tung et al, 2013); the mitral valve in transesophageal echocardiography (Wang et al, 2013a; Pouch et al, 2014); skeletal muscle in whole-body MRI (Karlsson et al, 2014); kidneys in CT images (Yang et al, 2014b); and bone in dental cone-beam CT images (Wang et al, 2014c). …”