Zhoubing Xu

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

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.

Evaluation of Six Registration Methods for the Human Abdomen on Clinically Acquired CT

Objective: This work evaluates current 3-D image registration tools on clinically acquired abdominal computed tomography (CT) scans. Methods: Thirteen abdominal organs were manually labeled on a set of 100 CT images, and the 100 labeled images (i.e., atlases) were pairwise registered based on intensity information with six registration tools (FSL, ANTS-CC, ANTS-QUICK-MI, IRTK, NIFTYREG, and DEEDS). The Dice similarity coefficient (DSC), mean surface distance, and Hausdorff distance were calculated on the registered organs individually. Permutation tests and indifference-zone ranking were performed to examine the statistical and practical significance, respectively. Results: The results suggest that DEEDS yielded the best registration performance. However, due to the overall low DSC values, and substantial portion of low-performing outliers, great care must be taken when image registration is used for local interpretation of abdominal CT. Conclusion: There is substantial room for improvement in image registration for abdominal CT. Significance: All data and source code are available so that innovations in registration can be directly compared with the current generation of tools without excessive duplication of effort.

Shape-constrained multi-atlas segmentation of spleen in CT

Spleen segmentation on clinically acquired CT data is a challenging problem given the complicity and variability of abdominal anatomy. Multi-atlas segmentation is a potential method for robust estimation of spleen segmentations, but can be negatively impacted by registration errors. Although labeled atlases explicitly capture information related to feasible organ shapes, multi-atlas methods have largely used this information implicitly through registration. We propose to integrate a level set shape model into the traditional label fusion framework to create a shape-constrained multi-atlas segmentation framework. Briefly, we (1) adapt two alternative atlas-to-target registrations to obtain the loose bounds on the inner and outer boundaries of the spleen shape, (2) project the fusion estimate to registered shape models, and (3) convert the projected shape into shape priors. With the constraint of the shape prior, our proposed method offers a statistically significant improvement in spleen labeling accuracy with an increase in DSC by 0.06, a decrease in symmetric mean surface distance by 4.01 mm, and a decrease in symmetric Hausdorff surface distance by 23.21 mm when compared to a locally weighted vote (LWV) method.

SIMPLE Is a Good Idea (and Better with Context Learning)

Selective and iterative method for performance level estimation (SIMPLE) is a multi-atlas segmentation technique that integrates atlas selection and label fusion that has proven effective for radiotherapy planning. Herein, we revisit atlas selection and fusion techniques in the context of segmenting the spleen in metastatic liver cancer patients with possible splenomegaly using clinically acquired computed tomography (CT). We re-derive the SIMPLE algorithm in the context of the statistical literature, and show that the atlas selection criteria rest on newly presented principled likelihood models. We show that SIMPLE performance can be improved by accounting for exogenous information through Bayesian priors (so called context learning). These innovations are integrated with the joint label fusion approach to reduce the impact of correlated errors among selected atlases. In a study of 65 subjects, the spleen was segmented with median Dice similarity coefficient of 0.93 and a mean surface distance error of 2.2 mm.

Immersive Virtual Reality for Visualization of Abdominal CT.

Immersive virtual environments use a stereoscopic head-mounted display and data glove to create high fidelity virtual experiences in which users can interact with three-dimensional models and perceive relationships at their true scale. This stands in stark contrast to traditional PACS-based infrastructure in which images are viewed as stacks of two dimensional slices, or, at best, disembodied renderings. Although there has substantial innovation in immersive virtual environments for entertainment and consumer media, these technologies have not been widely applied in clinical applications. Here, we consider potential applications of immersive virtual environments for ventral hernia patients with abdominal computed tomography imaging data. Nearly a half million ventral hernias occur in the United States each year, and hernia repair is the most commonly performed general surgery operation worldwide. A significant problem in these conditions is communicating the urgency, degree of severity, and impact of a hernia (and potential repair) on patient quality of life. Hernias are defined by ruptures in the abdominal wall (i.e., the absence of healthy tissues) rather than a growth (e.g., cancer); therefore, understanding a hernia necessitates understanding the entire abdomen. Our environment allows surgeons and patients to view body scans at scale and interact with these virtual models using a data glove. This visualization and interaction allows users to perceive the relationship between physical structures and medical imaging data. The system provides close integration of PACS-based CT data with immersive virtual environments and creates opportunities to study and optimize interfaces for patient communication, operative planning, and medical education.

Multi-Atlas Segmentation for Abdominal Organs with Gaussian Mixture Models.

Abdominal organ segmentation with clinically acquired computed tomography (CT) is drawing increasing interest in the medical imaging community. Gaussian mixture models (GMM) have been extensively used through medical segmentation, most notably in the brain for cerebrospinal fluid / gray matter / white matter differentiation. Because abdominal CT exhibit strong localized intensity characteristics, GMM have recently been incorporated in multi-stage abdominal segmentation algorithms. In the context of variable abdominal anatomy and rich algorithms, it is difficult to assess the marginal contribution of GMM. Herein, we characterize the efficacy of an a posteriori framework that integrates GMM of organ-wise intensity likelihood with spatial priors from multiple target-specific registered labels. In our study, we first manually labeled 100 CT images. Then, we assigned 40 images to use as training data for constructing target-specific spatial priors and intensity likelihoods. The remaining 60 images were evaluated as test targets for segmenting 12 abdominal organs. The overlap between the true and the automatic segmentations was measured by Dice similarity coefficient (DSC). A median improvement of 145% was achieved by integrating the GMM intensity likelihood against the specific spatial prior. The proposed framework opens the opportunities for abdominal organ segmentation by efficiently using both the spatial and appearance information from the atlases, and creates a benchmark for large-scale automatic abdominal segmentation.

Abdomen and spinal cord segmentation with augmented active shape models

Abstract. Active shape models (ASMs) have been widely used for extracting human anatomies in medical images given their capability for shape regularization of topology preservation. However, sensitivity to model initialization and local correspondence search often undermines their performances, especially around highly variable contexts in computed-tomography (CT) and magnetic resonance (MR) images. In this study, we propose an augmented ASM (AASM) by integrating the multiatlas label fusion (MALF) and level set (LS) techniques into the traditional ASM framework. Using AASM, landmark updates are optimized globally via a region-based LS evolution applied on the probability map generated from MALF. This augmentation effectively extends the searching range of correspondent landmarks while reducing sensitivity to the image contexts and improves the segmentation robustness. We propose the AASM framework as a two-dimensional segmentation technique targeting structures with one axis of regularity. We apply AASM approach to abdomen CT and spinal cord (SC) MR segmentation challenges. On 20 CT scans, the AASM segmentation of the whole abdominal wall enables the subcutaneous/visceral fat measurement, with high correlation to the measurement derived from manual segmentation. On 28 3T MR scans, AASM yields better performances than other state-of-the-art approaches in segmenting white/gray matter in SC.

Quantitative anatomical labeling of the anterior abdominal wall

Ventral hernias (VHs) are abnormal openings in the anterior abdominal wall that are common side effects of surgical intervention. Repair of VHs is the most commonly performed procedure by general surgeons worldwide, but VH repair outcomes are not particularly encouraging (with recurrence rates up to 43%). A variety of open and laparoscopic techniques are available for hernia repair, and the specific technique used is ultimately driven by surgeon preference and experience. Despite routine acquisition of computed tomography (CT) for VH patients, little quantitative information is available on which to guide selection of a particular approach and/or optimize patient-specific treatment. From anecdotal interviews, the success of VH repair procedures correlates with hernia size, location, and involvement of secondary structures. Herein, we propose an image labeling protocol to segment the anterior abdominal area to provide a geometric basis with which to derive biomarkers and evaluate treatment efficacy. Based on routine clinical CT data, we are able to identify inner and outer surfaces of the abdominal walls and the herniated volume. This is the first formal presentation of a protocol to quantify these structures on abdominal CT. The intra- and inter rater reproducibilities of this protocol are evaluated on 4 patients with suspected VH (3 patients were ultimately diagnosed with VH while 1 was not). Mean surfaces distances of less than 2mm were achieved for all structures.

Splenomegaly segmentation using global convolutional kernels and conditional generative adversarial networks.

Spleen volume estimation using automated image segmentation technique may be used to detect splenomegaly (abnormally enlarged spleen) on Magnetic Resonance Imaging (MRI) scans. In recent years, Deep Convolutional Neural Networks (DCNN) segmentation methods have demonstrated advantages for abdominal organ segmentation. However, variations in both size and shape of the spleen on MRI images may result in large false positive and false negative labeling when deploying DCNN based methods. In this paper, we propose the Splenomegaly Segmentation Network (SSNet) to address spatial variations when segmenting extraordinarily large spleens. SSNet was designed based on the framework of image-to-image conditional generative adversarial networks (cGAN). Specifically, the Global Convolutional Network (GCN) was used as the generator to reduce false negatives, while the Markovian discriminator (PatchGAN) was used to alleviate false positives. A cohort of clinically acquired 3D MRI scans (both T1 weighted and T2 weighted) from patients with splenomegaly were used to train and test the networks. The experimental results demonstrated that a mean Dice coefficient of 0.9260 and a median Dice coefficient of 0.9262 using SSNet on independently tested MRI volumes of patients with splenomegaly.

Evaluation of body-wise and organ-wise registrations for abdominal organs

Identifying cross-sectional and longitudinal correspondence in the abdomen on computed tomography (CT) scans is necessary for quantitatively tracking change and understanding population characteristics, yet abdominal image registration is a challenging problem. The key difficulty in solving this problem is huge variations in organ dimensions and shapes across subjects. The current standard registration method uses the global or body-wise registration technique, which is based on the global topology for alignment. This method (although producing decent results) has substantial influence of outliers, thus leaving room for significant improvement. Here, we study a new image registration approach using local (organ-wise registration) by first creating organ-specific bounding boxes and then using these regions of interest (ROIs) for aligning references to target. Based on Dice Similarity Coefficient (DSC), Mean Surface Distance (MSD) and Hausdorff Distance (HD), the organ-wise approach is demonstrated to have significantly better results by minimizing the distorting effects of organ variations. This paper compares exclusively the two registration methods by providing novel quantitative and qualitative comparison data and is a subset of the more comprehensive problem of improving the multi-atlas segmentation by using organ normalization.