Medical Image Analysis - Articles in Press

Combining Spatial Priors and Anatomical Information for fMRI Detection - Accepted Manuscript

Wanmei Ou, William M. Wells III, Polina Golland — 2010-03-08

Abstract: In this paper, we analyze Markov Random Field (MRF) as a spatial regularizer in fMRI detection. The low signal-to-noise ratio (SNR) in fMRI images presents a serious challenge for detection algorithms, making regularization necessary to achieve good detection accuracy. Gaussian smoothing, traditionally employed to boost SNR, often produces over-smoothed activation maps. Recently, the use of MRF priors has been suggested as an alternative regularization approach. However, solving for an optimal configuration of the MRF is NP-hard in general. In this work, we investigate fast inference algorithms based on the Mean Field approximation in application to MRF priors for fMRI detection. Furthermore, we propose a novel way to incorporate anatomical information into the MRF-based detection framework and into the traditional smoothing methods. Intuitively speaking, the anatomical evidence increases the likelihood of activation in the gray matter and improves spatial coherency of the resulting activation maps within each tissue type. Validation using the receiver operating characteristic (ROC) analysis and the confusion matrix analysis on simulated data illustrates substantial improvement in detection accuracy using the anatomically guided MRF spatial regularizer. We further demonstrate the potential benefits of the proposed method in real fMRI signals of reduced length. The anatomically guided MRF regularizer enables significant reduction of the scan length while maintaining the quality of the resulting activation maps.

Musculoskeletal MRI segmentation using multi-resolution simplex meshes with medial representations - Accepted Manuscript

Benjamin Gilles, Nadia Magnenat-Thalmann — 2010-03-02

Abstract: The automatic segmentation of the musculoskeletal system from medical images is a particularly challenging task, due to its morphological complexity, its large variability in the population and its potentially large deformations. In this paper we propose a novel approach for musculoskeletal segmentation and registration based on simplex meshes. Such discrete models have already proven to be efficient and versatile for medical image segmentation. We extend the current framework by introducing a multi-resolution approach and a reversible medial representation, in order to reduce the complexity of geometric and non-penetration constraints computation. Our framework allows both inter and intra patient registration (involving both rigid and elastic matching). We also show that the introduced representations facilitate morphological analysis. As a case study, we demonstrate that muscles, bones, ligaments and cartilages of the hip and the thigh can be registered at an interactive frame rate, in a time-efficient way (<30 min), with a satisfactory accuracy ∼(1.5mm), and with a minimal amount of manual tasks.

A New Computationally Efficient CAD System for Pulmonary Nodule Detection in CT Imagery - Accepted Manuscript

Temesguen Messay, Russell C. Hardie, Steven K. Rogers — 2010-02-22

Abstract: Early detection of lung nodules is extremely important for the diagnosis and clinical management of lung cancer. In this paper, a novel computer aided detection (CAD) system for the detection of pulmonary nodules in thoracic computed tomography (CT) imagery is presented. The paper describes the architecture of the CAD system and assesses its performance on a publicly available database to serve as a benchmark for future research efforts. Training and tuning of all modules in our CAD system is done using a separate and independent dataset provided courtesy of the University of Texas Medical Branch (UTMB).The publicly available testing dataset is that created by the Lung Image Database Consortium (LIDC). The LIDC data used here is comprised of 84 CT scans containing 143 nodules ranging from 3-30 mm in effective size that are manually segmented at least by one of the four radiologists. The CAD system uses a fully automated lung segmentation algorithm to define the boundaries of the lung regions. It combines intensity thresholding with morphological processing to detect and segment nodule candidates simultaneously. A set of 245 features is computed for each segmented nodule candidate. A sequential forward selection process is used to determine the optimum subset of features for two distinct classifiers, a Fisher Linear Discriminant (FLD) classifier and a quadratic classifier. A performance comparison between the two classifiers is presented, and based on this, the FLD classifier is selected for the CAD system. With an average of 517.5 nodule candidates per case/scan (517.5 ± 72.9), the proposed front-end detector/segmentor is able to detect 92.8% of all the nodules in the LIDC/testing dataset (based on merged ground truth). The mean overlap between the nodule regions delineated by three or more radiologists and the ones segmented by the proposed segmentation algorithm is approximately 63%. Overall, with a specificity of 3 false positives (FPs) per case/patient on average, the CAD system is able to correctly identify 80.4% of the nodules (115/143) using 40 selected features. A 7-fold cross-validation performance analysis using the LIDC database only shows CAD sensitivity of 82.66% with an average of 3 FPs per CT scan/case.

Evaluation of Brain Atrophy Estimation Algorithms using Simulated Ground-Truth Data - Accepted Manuscript

S. Sharma, V. Noblet, F. Rousseau, F. Heitz, L. Rumbach, J.-P. Armspach — 2010-02-18

Abstract: A number of analysis tools have been developed for the estimation of brain atrophy using MRI. Since brain atrophy is being increasingly used as a marker of disease progression in many neuro-degenerative diseases such as Multiple Sclerosis and Alzheimer’s Disease, the validation of these tools is an important task. However, this is complex, in the real scenario, due to the absence of gold standards for comparison. In order to create gold standards, we first propose an approach for the realistic simulation of brain tissue loss that relies on the estimation of a topology preserving B-spline based deformation fields. Using these gold standards, an evaluation of the performance of three standard brain atrophy estimation methods (SIENA, SIENAX and BSI-UCD), on the basis of their robustness to various sources of error (bias-field inhomogeneity, noise, geometrical distortions, interpolation artefacts and presence of lesions), is presented. Our evaluation shows that, in general, bias-field inhomogeneity and noise lead to larger errors in the estimated atrophy than geometrical distortions and interpolation artefacts. Experiments on 18 different anatomical models of the brain after simulating whole brain atrophies in the range of 0.2-1.5% indicate that, in the presence of bias-field inhomogeneity and noise, a mean error of 0.64%±0.53, 4.00%±2.41 and 1.79%±0.97 may be expected in the atrophy estimated by SIENA, SIENAX and BSI-UCD, respectively.

A Fast and Robust Patient Specific Finite Element Mesh Registration Technique: Application to 60 Clinical Cases - Accepted Manuscript

Marek Bucki, Claudio Lobos, Yohan Payan — 2010-02-16

Abstract: Finite Element mesh generation remains an important issue for patient specific biomechanical modeling. While some techniques make automatic mesh generation possible, in most cases, manual mesh generation is preferred for better control over the sub-domain representation, element type, layout and refinement that it provides. Yet, this option is time consuming and not suited for intraoperative situations where model generation and computation time is critical. To overcome this problem we propose a fast and automatic mesh generation technique based on the elastic registration of a generic mesh to the specific target organ in conjunction with element regularity and quality correction. This Mesh-Match-and-Repair (MMRep) approach combines control over the mesh structure along with fast and robust meshing capabilities, even in situations where only partial organ geometry is available. The technique was successfully tested on a database of 5 pre-operatively acquired complete femora CT scans, 5 femoral heads partially digitized at intraoperative stage, and 50 CT volumes of patients’ heads. In the latter case, both skin and bone surfaces were taken into account by the mesh registration process in order to model the face muscles and fat layers. The MMRep algorithm succeeded in all 60 cases, yielding for each patient a hex-dominant, Atlas based, Finite Element mesh with submillimetric surface representation accuracy, directly exploitable within a commercial FE software.

Automatic cerebral and cerebellar hemisphere segmentation in 3D MRI: adaptive disconnection algorithm - Accepted Manuscript

Lu Zhao, Ulla Ruotsalainen, Jussi Hirvonen, Jarmo Hietala, Jussi Tohka — 2010-02-11

Abstract: This paper describes the automatic Adaptive Disconnection method to segment cerebral and cerebellar hemispheres of human brain in three-dimensional magnetic resonance imaging (MRI). Using the partial differential equations based shape bottlenecks algorithm cooperating with an information potential value clustering process, it detects and cuts, first, the compartmental connections between the cerebrum, the cerebellum and the brainstem in the white matter domain, and then, the interhemispheric connections of the extracted cerebrum and cerebellum volumes. As long as the subject orientation in the scanner is given, the variations in subject location and normal brain morphology in different images is adapted automatically, thus no stereotaxic image registration is required. The modeling of partial volume effect is used to locate cerebrum, cerebellum and brainstem boundaries, and make the interhemispheric connections detectable. The Adaptive Disconnection method was tested with 10 simulated images from the BrainWeb database and 39 clinical images from the LONI Probabilistic Brain Atlas database. It obtained lower error rates than a traditional shape bottlenecks algorithm based segmentation technique (BrainVisa) and linear and nonlinear registration based brain hemisphere segmentation methods. Segmentation accuracies were evaluated against manual segmentations. The Adaptive Disconnection method was also confirmed not to be sensitive to the noise and intensity non-uniformity in the images. We also applied the Adaptive Disconnection method to clinical images of 22 healthy controls and 18 patients with schizophrenia. A preliminary cerebral volumetric asymmetry analysis based on these images demonstrated that the Adaptive Disconnection method is applicable to study abnormal brain asymmetry in schizophrenia.

An Automated Pipeline for Cortical Sulcal Fundi Extraction - Accepted Manuscript

Gang Li, Lei Guo, Jingxin Nie, Tianming Liu — 2010-02-08

Abstract: In this paper, we propose a novel automated pipeline for extraction of sulcal fundi from triangulated cortical surfaces. This method consists of four consecutive steps. Firstly, we adopt a finite difference method to estimate principal curvatures, principal directions and curvature derivatives, along the principal directions, for each vertex. Then, we detect the sulcal fundi segment in each triangle of the cortical surface based on curvatures and curvature derivatives. Afterwards, we link the sulcal fundi segments into continuous curves. Finally, we connect breaking sulcal fundi and smooth bumping sulcal fundi by using the fast marching method on the cortical surface. The proposed method can find the accurate sulcal fundi using curvatures and curvature derivatives without any manual interaction. The method was applied to ten normal brain MR images on inner cortical surfaces. We quantitatively evaluated the accuracy of the sulcal fundi extraction method using manually labeled sulcal fundi by experts. The average difference between automatically extracted major sulcal fundi and the expert labeled results is consistently around 1.0 mm on ten subject images, indicating the good performance of the proposed method.

Spherical wavelet transform for ODF sharpening - Corrected Proof

I. Kezele, M. Descoteaux, C. Poupon, F. Poupon, J.-F. Mangin — 2010-02-01

Abstract: The choice of local HARDI reconstruction technique is crucial for discerning multiple fiber orientations, which is itself of substantial importance for tractography, and reliable and accurate assessment of white matter fiber geometry. Due to the complexity of the diffusion process and its milieu, distinct diffusion compartments can have different frequency signatures, making the HARDI signal spread over multiple frequency bands. Therefore, we put forth the idea of multiscale analysis with localized basis functions, ensuring that different frequency ranges are probed. With the aim of truthful recovery of fiber orientations, we reconstruct the orientation distribution function (ODF), by incorporating a spherical wavelet transform (SWT) into the Funk–Radon transform. First, we apply and validate our proposed SWT method on real physical phantoms emulating fiber bundle crossings. Then, we apply the SWT method to a real brain data set. The analysis of the real data set suggests that different angular frequencies may capture different information, thus stressing the importance of multiscale analysis. For both phantom and real data, we compare the SWT reconstruction with state-of-the-art q-ball imaging and spherical deconvolution reconstruction methods. We demonstrate the algorithm efficiency in diffusion ODF denoising and sharpening that is of particular importance for applications to fiber tracking (especially for probabilistic approaches), and brain connectome mapping. Also, the algorithm results in considerable data compression that could prove beneficial in applications to fiber bundle segmentation, and for HARDI based white matter morphometry methods.

A framework for optimizing measurement weight maps to minimize the required sample size - Corrected Proof

2010-02-01

Abstract: We propose a fully automatic statistical framework for identifying the non-negative, real-valued weight map that best discriminate between two groups of objects. Given measurements on a spatially defined grid, a numerical optimization scheme is used to find the weight map that minimizes the sample size required to discriminate the two groups. The weight map produced by the method reflects the relative importance of the different areas in the objects, and the resulting sample size reduction is an important end goal in situations where data collection is difficult or expensive. An example is in clinical studies where the cost and the patient burden are directly related to the number of participants needed for the study. In addition, inspection of the weight map might provide clues that can lead to a better clinical understanding of the objects and pathologies being studied. The method is evaluated on synthetic data and on clinical data from knee cartilage MRI. The clinical data contain a total of 159 subjects aged 21–81 years and ranked from zero to four on the Kellgren–Lawrence osteoarthritis severity scale. Compared to a uniform weight map, we achieve sample size reductions up to 58% for cartilage thickness measurements. Based on quantifications from both morphometric and textural based imaging features, we also identify the most pathological areas in the articular cartilage.

High resolution cortical bone thickness measurement from clinical CT data - Corrected Proof

G.M. Treece, A.H. Gee, P.M. Mayhew, K.E.S. Poole — 2010-01-25

Abstract: The distribution of cortical bone in the proximal femur is believed to be a critical component in determining fracture resistance. Current CT technology is limited in its ability to measure cortical thickness, especially in the sub-millimetre range which lies within the point spread function of today’s clinical scanners. In this paper, we present a novel technique that is capable of producing unbiased thickness estimates down to 0.3mm. The technique relies on a mathematical model of the anatomy and the imaging system, which is fitted to the data at a large number of sites around the proximal femur, producing around 17,000 independent thickness estimates per specimen. In a series of experiments on 16 cadaveric femurs, estimation errors were measured as −0.01±0.58mm (mean±1std.dev.) for cortical thicknesses in the range 0.3–4mm. This compares with 0.25±0.69mm for simple thresholding and 0.90±0.92mm for a variant of the 50% relative threshold method. In the clinically relevant sub-millimetre range, thresholding increasingly fails to detect the cortex at all, whereas the new technique continues to perform well. The many cortical thickness estimates can be displayed as a colour map painted onto the femoral surface. Computation of the surfaces and colour maps is largely automatic, requiring around 15min on a modest laptop computer.

Optimal embedding for shape indexing in medical image databases - Corrected Proof

Xiaoning Qian, Hemant D. Tagare, Robert K. Fulbright, Rodney Long, Sameer Antani — 2010-01-20

Abstract: This paper addresses the problem of indexing shapes in medical image databases. Shapes of organs are often indicative of disease, making shape similarity queries important in medical image databases. Mathematically, shapes with landmarks belong to shape spaces which are curved manifolds with a well defined metric. The challenge in shape indexing is to index data in such curved spaces. One natural indexing scheme is to use metric trees, but metric trees are prone to inefficiency. This paper proposes a more efficient alternative.We show that it is possible to optimally embed finite sets of shapes in shape space into a Euclidean space. After embedding, classical coordinate-based trees can be used for efficient shape retrieval. The embedding proposed in the paper is optimal in the sense that it least distorts the partial Procrustes shape distance.The proposed indexing technique is used to retrieve images by vertebral shape from the NHANES II database of cervical and lumbar spine X-ray images maintained at the National Library of Medicine. Vertebral shape strongly correlates with the presence of osteophytes, and shape similarity retrieval is proposed as a tool for retrieval by osteophyte presence and severity.Experimental results included in the paper evaluate (1) the usefulness of shape similarity as a proxy for osteophytes, (2) the computational and disk access efficiency of the new indexing scheme, (3) the relative performance of indexing with embedding to the performance of indexing without embedding, and (4) the computational cost of indexing using the proposed embedding versus the cost of an alternate embedding. The experimental results clearly show the relevance of shape indexing and the advantage of using the proposed embedding.

Automatic detection of informative frames from wireless capsule endoscopy images - Corrected Proof

M.K. Bashar, T. Kitasaka, Y. Suenaga, Y. Mekada, K. Mori — 2010-01-04

Abstract: Wireless capsule endoscopy (WCE) is a new clinical technology permitting visualization of the small bowel, the most difficult segment of the digestive tract. The major drawback of this technology is the excessive amount of time required for video diagnosis. We therefore propose a method for generating smaller videos by detecting informative frames from original WCE videos. This method isolates useless frames that are highly contaminated by turbid fluids, faecal materials and/or residual foods. These materials and fluids are presented in a wide range of colors, from brown to yellow, and/or have bubble-like texture patterns. The detection scheme therefore consists of two steps: isolating (Step-1) highly contaminated non-bubbled (HCN) frames and (Step-2) significantly bubbled (SB) frames. Two color representations, viz., local color moments in Ohta space and the HSV color histogram, are attempted to characterize HCN frames, which are isolated by a support vector machine (SVM) classifier in Step-1. The rest of the frames go to Step-2, where a Gauss Laguerre transform (GLT) based multiresolution texture feature is used to characterize the bubble structures in WCE frames. GLT uses Laguerre Gauss circular harmonic functions (LG-CHFs) to decompose WCE images into multiresolution components. An automatic method of segmentation was designed to extract bubbled regions from grayscale versions of the color images based on the local absolute energies of their CHF responses. The final informative frames were detected by using a threshold on the segmented regions. An automatic procedure for selecting features based on analyzing the consistency of the energy-contrast map is also proposed. Three experiments, two of which use 14,841 and 37,100 frames from three videos and the rest uses 66,582 frames from six videos, were conducted for justifying the proposed method. The two combinations of the proposed color and texture features showed excellent average detection accuracies (86.42% and 84.45%) with the final experiment, when compared with the same color features followed by conventional Gabor-based (78.18% and 76.29%) and discrete wavelet-based (65.43% and 63.83%) texture features. Although intra-video training–testing cases are typical choices for supervised classification in Step-1, combining a suitable number of training sets using a subset of the input videos was shown to be possible. This mixing not only reduced computation costs but also produced better detection accuracies by minimizing visual-selection errors, especially when processing large numbers of WCE videos.

Glaucoma risk index:Automated glaucoma detection from color fundus images - Corrected Proof

Rüdiger Bock, Jörg Meier, László G. Nyúl, Joachim Hornegger, Georg Michelson — 2010-01-04

Abstract: Glaucoma as a neurodegeneration of the optic nerve is one of the most common causes of blindness. Because revitalization of the degenerated nerve fibers of the optic nerve is impossible early detection of the disease is essential. This can be supported by a robust and automated mass-screening. We propose a novel automated glaucoma detection system that operates on inexpensive to acquire and widely used digital color fundus images. After a glaucoma specific preprocessing, different generic feature types are compressed by an appearance-based dimension reduction technique. Subsequently, a probabilistic two-stage classification scheme combines these features types to extract the novel Glaucoma Risk Index (GRI) that shows a reasonable glaucoma detection performance. On a sample set of 575 fundus images a classification accuracy of 80% has been achieved in a 5-fold cross-validation setup. The GRI gains a competitive area under ROC (AUC) of 88% compared to the established topography-based glaucoma probability score of scanning laser tomography with AUC of 87%. The proposed color fundus image-based GRI achieves a competitive and reliable detection performance on a low-priced modality by the statistical analysis of entire images of the optic nerve head.