Retrospective 4D MR image construction from free-breathing slice Acquisitions: A novel graph-based approach.

PURPOSE: Dynamic or 4D imaging of the thorax has many applications. Both prospective and retrospective respiratory gating and tracking techniques have been developed for 4D imaging via CT and MRI. For pediatric imaging, due to radiation concerns, MRI becomes the de facto modality of choice. In thoracic insufficiency syndrome (TIS), patients often suffer from extreme malformations of the chest wall, diaphragm, and/or spine with inability of the thorax to support normal respiration or lung growth (Campbell et al., 2003, Campbell and Smith, 2007), as such patient cooperation needed by some of the gating and tracking techniques are difficult to realize without causing patient discomfort and interference with the breathing mechanism itself. Therefore (ventilator-supported) free-breathing MRI acquisition is currently the best choice for imaging these patients. This, however, raises a question of how to create a consistent 4D image from such acquisitions. This paper presents a novel graph-based technique for compiling the best 4D image volume representing the thorax over one respiratory cycle from slice images acquired during unencumbered natural tidal-breathing of pediatric TIS patients. METHODS: In our approach, for each coronal (or sagittal) slice position, images are acquired at a rate of about 200-300ms/slice over several natural breathing cycles which yields over 2000 slices. A weighted graph is formed where each acquired slice constitutes a node and the weight of the arc between two nodes defines the degree of contiguity in space and time of the two slices. For each respiratory phase, an optimal 3D spatial image is constructed by finding the best path in the graph in the spatial direction. The set of all such 3D images for a given respiratory cycle constitutes a 4D image. Subsequently, the best 4D image among all such constructed images is found over all imaged respiratory cycles. Two types of evaluation studies are carried out to understand the behavior of this algorithm and in comparison to a method called Random Stacking - a 4D phantom study and 10 4D MRI acquisitions from TIS patients and normal subjects. The 4D phantom was constructed by 3D printing the pleural spaces of an adult thorax, which were segmented in a breath-held MRI acquisition. RESULTS: Qualitative visual inspection via cine display of the slices in space and time and in 3D rendered form showed smooth variation for all data sets constructed by the proposed method. Quantitative evaluation was carried out to measure spatial and temporal contiguity of the slices via segmented pleural spaces. The optimal method showed smooth variation of the pleural space as compared to Random Stacking whose behavior was erratic. The volumes of the pleural spaces at the respiratory phase corresponding to end inspiration and end expiration were compared to volumes obtained from breath-hold acquisitions at roughly the same phase. The mean difference was found to be roughly 3%. CONCLUSIONS: The proposed method is purely image-based and post-hoc and does not need breath holding or external surrogates or instruments to record respiratory motion or tidal volume. This is important and practically warranted for pediatric patients. The constructed 4D images portray spatial and temporal smoothness that should be expected in a consistent 4D volume. We believe that the method can be routinely used for thoracic 4D imaging.

Differential and relaxed image foresting transform for graph-cut segmentation of multiple 3D objects.

Graph-cut algorithms have been extensively investigated for interactive binary segmentation, when the simultaneous delineation of multiple objects can save considerable user's time. We present an algorithm (named DRIFT) for 3D multiple object segmentation based on seed voxels and Differential Image Foresting Transforms (DIFTs) with relaxation. DRIFT stands behind efficient implementations of some state-of-the-art methods. The user can add/remove markers (seed voxels) along a sequence of executions of the DRIFT algorithm to improve segmentation. Its first execution takes linear time with the image's size, while the subsequent executions for corrections take sublinear time in practice. At each execution, DRIFT first runs the DIFT algorithm, then it applies diffusion filtering to smooth boundaries between objects (and background) and, finally, it corrects possible objects' disconnection occurrences with respect to their seeds. We evaluate DRIFT in 3D CT-images of the thorax for segmenting the arterial system, esophagus, left pleural cavity, right pleural cavity, trachea and bronchi, and the venous system.

Body-wide hierarchical fuzzy modeling, recognition, and delineation of anatomy in medical images.

To make Quantitative Radiology (QR) a reality in radiological practice, computerized body-wide Automatic Anatomy Recognition (AAR) becomes essential. With the goal of building a general AAR system that is not tied to any specific organ system, body region, or image modality, this paper presents an AAR methodology for localizing and delineating all major organs in different body regions based on fuzzy modeling ideas and a tight integration of fuzzy models with an Iterative Relative Fuzzy Connectedness (IRFC) delineation algorithm. The methodology consists of five main steps: (a) gathering image data for both building models and testing the AAR algorithms from patient image sets existing in our health system; (b) formulating precise definitions of each body region and organ and delineating them following these definitions; (c) building hierarchical fuzzy anatomy models of organs for each body region; (d) recognizing and locating organs in given images by employing the hierarchical models; and (e) delineating the organs following the hierarchy. In Step (c), we explicitly encode object size and positional relationships into the hierarchy and subsequently exploit this information in object recognition in Step (d) and delineation in Step (e). Modality-independent and dependent aspects are carefully separated in model encoding. At the model building stage, a learning process is carried out for rehearsing an optimal threshold-based object recognition method. The recognition process in Step (d) starts from large, well-defined objects and proceeds down the hierarchy in a global to local manner. A fuzzy model-based version of the IRFC algorithm is created by naturally integrating the fuzzy model constraints into the delineation algorithm. The AAR system is tested on three body regions - thorax (on CT), abdomen (on CT and MRI), and neck (on MRI and CT) - involving a total of over 35 organs and 130 data sets (the total used for model building and testing). The training and testing data sets are divided into equal size in all cases except for the neck. Overall the AAR method achieves a mean accuracy of about 2 voxels in localizing non-sparse blob-like objects and most sparse tubular objects. The delineation accuracy in terms of mean false positive and negative volume fractions is 2% and 8%, respectively, for non-sparse objects, and 5% and 15%, respectively, for sparse objects. The two object groups achieve mean boundary distance relative to ground truth of 0.9 and 1.5 voxels, respectively. Some sparse objects - venous system (in the thorax on CT), inferior vena cava (in the abdomen on CT), and mandible and naso-pharynx (in neck on MRI, but not on CT) - pose challenges at all levels, leading to poor recognition and/or delineation results. The AAR method fares quite favorably when compared with methods from the recent literature for liver, kidneys, and spleen on CT images. We conclude that separation of modality-independent from dependent aspects, organization of objects in a hierarchy, encoding of object relationship information explicitly into the hierarchy, optimal threshold-based recognition learning, and fuzzy model-based IRFC are effective concepts which allowed us to demonstrate the feasibility of a general AAR system that works in different body regions on a variety of organs and on different modalities.

GPU-based relative fuzzy connectedness image segmentation.

PURPOSE: Recently, clinical radiological research and practice are becoming increasingly quantitative. Further, images continue to increase in size and volume. For quantitative radiology to become practical, it is crucial that image segmentation algorithms and their implementations are rapid and yield practical run time on very large data sets. The purpose of this paper is to present a parallel version of an algorithm that belongs to the family of fuzzy connectedness (FC) algorithms, to achieve an interactive speed for segmenting large medical image data sets. METHODS: The most common FC segmentations, optimizing an [script-l](∞)-based energy, are known as relative fuzzy connectedness (RFC) and iterative relative fuzzy connectedness (IRFC). Both RFC and IRFC objects (of which IRFC contains RFC) can be found via linear time algorithms, linear with respect to the image size. The new algorithm, P-ORFC (for parallel optimal RFC), which is implemented by using NVIDIA's Compute Unified Device Architecture (CUDA) platform, considerably improves the computational speed of the above mentioned CPU based IRFC algorithm. RESULTS: Experiments based on four data sets of small, medium, large, and super data size, achieved speedup factors of 32.8×, 22.9×, 20.9×, and 17.5×, correspondingly, on the NVIDIA Tesla C1060 platform. Although the output of P-ORFC need not precisely match that of IRFC output, it is very close to it and, as the authors prove, always lies between the RFC and IRFC objects. CONCLUSIONS: A parallel version of a top-of-the-line algorithm in the family of FC has been developed on the NVIDIA GPUs. An interactive speed of segmentation has been achieved, even for the largest medical image data set. Such GPU implementations may play a crucial role in automatic anatomy recognition in clinical radiology.