Multiatlas segmentation of thoracic and abdominal anatomy with level set‐based local search

Abstract

Segmentation of organs at risk (OARs) remains one of the most time‐consuming tasks in radiotherapy treatment planning. Atlas‐based segmentation methods using single templates have emerged as a practical approach to automate the process for brain or head and neck anatomy, but pose significant challenges in regions where large interpatient variations are present. We show that significant changes are needed to autosegment thoracic and abdominal datasets by combining multi‐atlas deformable registration with a level set‐based local search. Segmentation is hierarchical, with a first stage detecting bulk organ location, and a second step adapting the segmentation to fine details present in the patient scan. The first stage is based on warping multiple presegmented templates to the new patient anatomy using a multimodality deformable registration algorithm able to cope with changes in scanning conditions and artifacts. These segmentations are compacted in a probabilistic map of organ shape using the STAPLE algorithm. Final segmentation is obtained by adjusting the probability map for each organ type, using customized combinations of delineation filters exploiting prior knowledge of organ characteristics. Validation is performed by comparing automated and manual segmentation using the Dice coefficient, measured at an average of 0.971 for the aorta, 0.869 for the trachea, 0.958 for the lungs, 0.788 for the heart, 0.912 for the liver, 0.884 for the kidneys, 0.888 for the vertebrae, 0.863 for the spleen, and 0.740 for the spinal cord. Accurate atlas segmentation for abdominal and thoracic regions can be achieved with the usage of a multi‐atlas and perstructure refinement strategy. To improve clinical workflow and efficiency, the algorithm was embedded in a software service, applying the algorithm automatically on acquired scans without any user interaction.PACS numbers: 87.57.nm, 87.57.N‐, 87.57.Q‐

Multi-atlas segmentation of biomedical images: A survey

“…Other MAS algorithms rely on applying heavy post-processing to the label fusion output, for example by employing an error detection and correction classifier (Yushkevich et al 2010, who use AdaBoost), deriving features to drive a subsequent voxel-wise segmentation method, based for example on level sets (Gholipour et al, 2012; Schreibmann et al, 2014), random forests (Han, 2013), support vector machines (Hao et al, 2014), patch-based techniques (Wang et al, 2014e), or a graph-cut-based method (Candemir et al, 2014; Lee et al, 2014b). Along a similar direction, one can apply a refinement to the MAS results, for example, by comparing the observed intensities in the novel image to tissue-based expected intensity profiles (Ledig et al, 2014).…”

“…MAS has also been used in abdominal imaging, despite the relatively poor performance of image registration in this domain (e.g., compared with brain MRI) due to the shifting of organs within the abdominal cavity. Nonetheless, MAS has been successful in liver (van Rikxoort et al, 2007a; Platero and Tobar, 2014), spleen (Li et al, 2013; Xu et al, 2014b) and multi-organ segmentation (Wolz et al, 2013; Schreibmann et al, 2014) in CT scans.…”

Fully automated esophagus segmentation with a hierarchical deep learning approach

“…Another strategy is to segment multiple organs at the same time. For example a recent work was presented in [8] where the authors proposed to combine multi-atlas deformable registration with a level set-based local search to segment several organs, i.e., aorta, esophagus, trachea, heart. The results for the esophagus were not good enough for clinical usage with Dice ratio (DR) as low as 0.01.…”

MRI Sagittal Image Segmentation from Patients with Abdominal Aortic Aneurysms

“…Multi-atlas segmentation method for thoracic and abdominal anatomy from the CT images has done automatically. This method uses the level set approach based on local search [11]. Another segmentation approach is the method with connected component labeling.…”