Efficient multi-atlas abdominal segmentation on clinically acquired CT with SIMPLE context learning

https://doi.org/10.1016/j.media.2015.05.009Get rights and content

Highlights

  • Represent the SIMPLE atlas selection criteria with principled likelihood models.

  • Augment the SIMPLE framework with exogenous information learned from image context.

  • Integrate SIMPLE context learning with joint label fusion and graph cut.

  • Efficiently segment 12 abdominal organs on clinical CT of liver cancer patients.

Abstract

Abdominal segmentation on clinically acquired computed tomography (CT) has been a challenging problem given the inter-subject variance of human abdomens and complex 3-D relationships among organs. Multi-atlas segmentation (MAS) provides a potentially robust solution by leveraging label atlases via image registration and statistical fusion. We posit that the efficiency of atlas selection requires further exploration in the context of substantial registration errors. The selective and iterative method for performance level estimation (SIMPLE) method is a MAS technique integrating atlas selection and label fusion that has proven effective for prostate radiotherapy planning. Herein, we revisit atlas selection and fusion techniques for segmenting 12 abdominal structures using clinically acquired CT. Using a re-derived SIMPLE algorithm, we show that performance on multi-organ classification can be improved by accounting for exogenous information through Bayesian priors (so called context learning). These innovations are integrated with the joint label fusion (JLF) approach to reduce the impact of correlated errors among selected atlases for each organ, and a graph cut technique is used to regularize the combined segmentation. In a study of 100 subjects, the proposed method outperformed other comparable MAS approaches, including majority vote, SIMPLE, JLF, and the Wolz locally weighted vote technique. The proposed technique provides consistent improvement over state-of-the-art approaches (median improvement of 7.0% and 16.2% in DSC over JLF and Wolz, respectively) and moves toward efficient segmentation of large-scale clinically acquired CT data for biomarker screening, surgical navigation, and data mining.

Introduction

The human abdomen is an essential, yet complex body space. Computed tomography (CT) scans are routinely obtained for the diagnosis and prognosis of abdomen-related disease. Automated segmentation of abdominal anatomy may improve patient care by decreasing or eliminating the subjectivity inherent in traditional qualitative assessment. In large-scale clinical studies, efficient segmentation of multiple abdominal organs can also be used for biomarker screening, surgical navigation, and data mining.

Atlas-based segmentation provides a general-purpose approach to segment target images by transferring information from canonical atlases via registration. When adapting to abdomen, the variable abdominal anatomy between individuals (e.g., weight, stature, age, disease status) and within individuals (e.g., pose, respiratory cycle, clothing) can lead to substantial registration errors (Figs. 1 and 2). Previous abdominal segmentation approaches have used single probabilistic atlases constructed by co-registering atlases to characterize the spatial variations of abdominal organs (Park et al., 2003, Shimizu et al., 2007); statistical shape models (Okada et al., 2013, 2008) and/or graph theories (Bagci et al., 2012, Linguraru et al., 2012) have been integrated to refine the segmentation using probabilistic atlases. Multi-atlas segmentation (MAS), on the other hand, is a technique that has been proven effective and robust in neuroimaging by registering multiple atlases to the target image separately, and combining voxel-wise observations among the registered labels through label fusion (Sabuncu et al., 2010). Recently, Wolz et al. applied MAS to the abdomen using locally weighted subject-specific atlas (Wolz et al., 2013); yet the segmentation accuracies were inconsistent. We posit that the efficiency of atlas selection for abdominal MAS requires further exploration in the context of substantial registration errors, especially on clinically acquired CT.

The selective and iterative method for performance level estimation (Langerak et al., 2010) (SIMPLE) algorithm raised effective atlas selection criteria based on the Dice similarity coefficient (Dice, 1945) overlap with intermediate voting-based fusion result, and addressed extensive variation in prostate anatomy to reduce the impact of outlier atlases. In Xu et al. (2014), we generalized a SIMPLE theoretical framework to account for exogenous information through Bayesian priors – referred to as context learning; the newly presented model selected atlases more effectively for segmenting spleens in metastatic liver cancer patients. A further integration with joint label fusion (JLF) (Wang et al., 2012) addressed the label determination by reducing the correlated errors among the selected atlases, and yielded a median DSC of 0.93 for spleen segmentation.

Herein, we propose an efficient approach for segmenting 12 abdominal organs of interest (Fig. 1) in 75 metastatic liver cancer patients and 25 ventral hernia patients on clinically acquired CT. Based on the re-derived SIMPLE framework (Xu et al., 2014), we construct context priors, select atlases, and fuse estimated segmentation using JLF for each organ individually, and combine the fusion estimates of all organs into a regularized multi-organ segmentation using graph cut (Boykov et al., 2001) (Fig. 3). The segmentation performances are validated with other MAS approaches, including majority vote (MV), SIMPLE, JLF, and the Wolz approach. This work is an extension of previous theoretical (Xu et al., 2014) and empirical (Xu et al., 2015) conference papers and presents new analyses of algorithm performance and parameter sensitivity.

Section snippets

Theory

We re-formulate the SIMPLE algorithm from the perspective of expectation–maximization (EM) while focusing on the atlas selection step. In this principled likelihood model, the Bayesian prior learning from context features (e.g., intensity, gradient) is considered as exogenous information to regularize the atlas selection.

Data

Under Institutional Review Board (IRB) supervision, the first-session of abdomen CT scans of 75 metastatic liver cancer patients were randomly selected from an ongoing colorectal cancer chemotherapy trial, and an additional 25 retrospective scans were acquired clinically from post-operative patients with suspected ventral hernias. The 100 scans were captured during portal venous contrast phase with variable volume sizes (512 × 512 × 33– 512 × 512 × 158) and field of views (approx. 300 × 300 ×

Discussion

The proposed method provides a fully automated approach to segment 12 abdominal organs on clinically acquired CT. The SIMPLE context learning reduces the impact of the vastly problematic registrations with appropriate atlas selection considering exogenous contexts in addition to intermediate fusion estimate, and thus enables more efficient abdominal segmentations. We note that proposed generative model naturally leads to an iterative atlas selection, which differs from the STEPS approach (Jorge

Acknowledgments

This research was supported by NIH 1R03EB012461, NIH 2R01EB006136, NIH R01EB006193, ViSE/VICTR VR3029, NIH UL1 RR024975-01, NIH UL1 TR000445-06, NIH P30 CA068485, and AUR GE Radiology Research Academic Fellowship. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH. This work was conducted in part using the resources of the Advanced Computing Center for Research and Education at Vanderbilt University, Nashville, TN.

References (29)

  • GassT. et al.

    Multi-atlas segmentation and landmark localization in images with large field of view

    Medical Computer Vision: Algorithms for Big Data

    (2014)
  • HeimannT. et al.

    Comparison and evaluation of methods for liver segmentation from CT datasets

    IEEE Trans. Med. Imag.

    (2009)
  • KéchichianR. et al.

    Shortest-path constraints for 3d multiobject semiautomatic segmentation via clustering and graph cut

    IEEE Trans. Image Process.

    (2013)
  • LangerakT.R. et al.

    Label fusion in atlas-based segmentation using a selective and iterative method for performance level estimation (SIMPLE)

    IEEE Trans. Med. Imag.

    (2010)
  • Cited by (0)

    View full text