Jeffrey W. Prescott

Automatic graph-cut based segmentation of bones from knee magnetic resonance images for osteoarthritis research

In this paper, a new, fully automated, content-based system is proposed for knee bone segmentation from magnetic resonance images (MRI). The purpose of the bone segmentation is to support the discovery and characterization of imaging biomarkers for the incidence and progression of osteoarthritis, a debilitating joint disease, which affects a large portion of the aging population. The segmentation algorithm includes a novel content-based, two-pass disjoint block discovery mechanism, which is designed to support automation, segmentation initialization, and post-processing. The block discovery is achieved by classifying the image content to bone and background blocks according to their similarity to the categories in the training data collected from typical bone structures. The classified blocks are then used to design an efficient graph-cut based segmentation algorithm. This algorithm requires constructing a graph using image pixel data followed by applying a maximum-flow algorithm which generates a minimum graph-cut that corresponds to an initial image segmentation. Content-based refinements and morphological operations are then applied to obtain the final segmentation. The proposed segmentation technique does not require any user interaction and can distinguish between bone and highly similar adjacent structures, such as fat tissues with high accuracy. The performance of the proposed system is evaluated by testing it on 376 MR images from the Osteoarthritis Initiative (OAI) database. This database included a selection of single images containing the femur and tibia from 200 subjects with varying levels of osteoarthritis severity. Additionally, a full three-dimensional segmentation of the bones from ten subjects with 14 slices each, and synthetic images with background having intensity and spatial characteristics similar to those of bone are used to assess the robustness and consistency of the developed algorithm. The results show an automatic bone detection rate of 0.99 and an average segmentation accuracy of 0.95 using the Dice similarity index.

Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees

OBJECTIVE The goal of this study was to develop an algorithm to semi-automatically segment the meniscus in a series of magnetic resonance (MR) images to use for normal knees and those with moderate osteoarthritis (OA). METHOD The segmentation method was developed then evaluated on 10 baseline MR images obtained from subjects with no evidence, symptoms, or risk factors of knee (OA), and 14 from subjects with established knee OA enrolled in the Osteoarthritis Initiative (OAI). After manually choosing a seed point within the meniscus, a threshold level was calculated through a Gaussian fit model. Under anatomical, intensity, and range constraints, a threshold operation was completed followed by conditional dilation and post-processing. The post-processing operation reevaluates the pixels included and excluded in the area surrounding the meniscus to improve accuracy. The developed method was evaluated for both normal and degenerative menisci by comparing the segmentation algorithm results with manual segmentations from five human readers. RESULTS The semi-automated segmentation method produces results similar to those of trained observers, with an average similarity index over 0.80 for normal participants and 0.75, 0.67, and 0.64 for participants with established knee OA with Osteoarthritis Research Society International (OARSI) joint space narrowing (JSN) scores of 0, one, and two respectively. CONCLUSION The semi-automatic segmentation method produced accurate and consistent segmentations of the meniscus when compared to manual segmentations in the assessment of normal menisci in mild to moderate OA. Future studies will examine the change in volume, thickness, and intensity characteristics at different stages of OA.

Quantitative imaging biomarkers: the application of advanced image processing and analysis to clinical and preclinical decision making.

The importance of medical imaging for clinical decision making has been steadily increasing over the last four decades. Recently, there has also been an emphasis on medical imaging for preclinical decision making, i.e., for use in pharamaceutical and medical device development. There is also a drive towards quantification of imaging findings by using quantitative imaging biomarkers, which can improve sensitivity, specificity, accuracy and reproducibility of imaged characteristics used for diagnostic and therapeutic decisions. An important component of the discovery, characterization, validation and application of quantitative imaging biomarkers is the extraction of information and meaning from images through image processing and subsequent analysis. However, many advanced image processing and analysis methods are not applied directly to questions of clinical interest, i.e., for diagnostic and therapeutic decision making, which is a consideration that should be closely linked to the development of such algorithms. This article is meant to address these concerns. First, quantitative imaging biomarkers are introduced by providing definitions and concepts. Then, potential applications of advanced image processing and analysis to areas of quantitative imaging biomarker research are described; specifically, research into osteoarthritis (OA), Alzheimers disease (AD) and cancer is presented. Then, challenges in quantitative imaging biomarker research are discussed. Finally, a conceptual framework for integrating clinical and preclinical considerations into the development of quantitative imaging biomarkers and their computer-assisted methods of extraction is presented.

Anatomically Anchored Template-Based Level Set Segmentation: Application to Quadriceps Muscles in MR Images from the Osteoarthritis Initiative

In this paper, we present a semi-automated segmentation method for magnetic resonance images of the quadriceps muscles. Our method uses an anatomically anchored, template-based initialization of the level set-based segmentation approach. The method only requires the input of a single point from the user inside the rectus femoris. The templates are quantitatively selected from a set of images based on modes in the patient population, namely, sex and body type. For a given image to be segmented, a template is selected based on the smallest Kullback–Leibler divergence between the histograms of that image and the set of templates. The chosen template is then employed as an initialization for a level set segmentation, which captures individual anatomical variations in the image to be segmented. Images from 103 subjects were analyzed using the developed method. The algorithm was trained on a randomly selected subset of 50 subjects (25 men and 25 women) and tested on the remaining 53 subjects. The performance of the algorithm on the test set was compared against the ground truth using the Zijdenbos similarity index (ZSI). The average ZSI means and standard deviations against two different manual readers were as follows: rectus femoris, 0.78 ± 0.12; vastus intermedius, 0.79 ± 0.10; vastus lateralis, 0.82 ± 0.08; and vastus medialis, 0.69 ± 0.16.

An automated method to segment the femur for osteoarthritis research

In this paper we develop a fully automated method for the segmentation of the femur in axial MR images and its use in the analysis of imaging biomarkers for osteoarthritis (OA). The proposed method is based on anatomical constraints implemented using morphological operations to extract the femur medulla and a level set evolution to extract the femur cortex. The average agreement of the automated segmentation algorithm with ground truth manual segmentations was 0.94 plusmn 0.03 calculated using the Zijdenbos similarity index (ZSI). A pooled variance t-test analysis found significant associations between the KL grade, a clinical measure of OA severity, and both the cross-sectional area (CSA) of the femur medulla (p = 3D 0.02) and the ratio of the femur medulla CSA to the femur cortex CSA (p = 3D 0.04) for women. No significant association between femur measurements and KL grade was found for men.

Segmentation of follicular regions on H&E slides using a matching filter and active contour model

Follicular Lymphoma (FL) accounts for 20-25% of non-Hodgkin lymphomas in the United States. The first step in follicular lymphoma grading is the identification of follicles. The goal of this paper is to develop a technique to segment follicular regions in H&E stained images. The method is based on a robust active contour model, which is initialized by a seed point selected inside the follicle manually by the user. The novel aspect of this method is the introduction of a matched filter for the flattening of background in the L channel of the Lab color space. The performance of the algorithm was tested by comparing it against the manual segmentations of trained readers using the Zijbendos similarity index. The mean accuracy of the final segmentation compared to the manual ground truth was 0.71 with a standard deviation of 0.12.

The Aging Athlete: Part 1, ???Boomeritis??? of the Lower Extremity

OBJECTIVE The purpose of this review is to describe the physiologic changes that occur in the musculoskeletal system during aging and the common injuries that occur in the lower extremity as a consequence of these changes. Several clinical presentations are addressed, and their differential diagnoses are discussed with an emphasis on the most likely injury for each presentation. CONCLUSION A unique quality of the newly aging group of people referred to as baby boomers is their expectation to continue exercising as they grow older, thus the incidence of exercise-induced injuries among older people is increasing. The concepts behind factors that predispose older athletes to certain pathologic conditions that affect the muscles, tendons, and bones of the lower extremity must be understood.

An automated method to detect interstitial adipose tissue in thigh muscles for patients with osteoarthritis

In this paper we explore a method of segmentation of muscle interstitial adipose tissue (IAT) in MR images of the thigh. The objective is to apply the method towards research into biomarkers of osteoarthritis (OA). T1-weighted images of the thigh are intensity standardized through bias field correction and intensity normalization. IAT within the thigh muscles is then segmented using a threshold combined with morphological constraints applied on connected regions in the thresholded image. The morphological constraints can be adjusted to allow for highly sensitive or highly specific IAT segmentation. The use of the morphological constraints improved the specificity of IAT segmentation over a threshold segmentation method from 0.54 to 0.67, while retaining a nearly equivalent sensitivity of 0.82 compared to 0.84. We then present a preliminary statistical analysis to demonstrate the application of the automated IAT segmentation. Finally, we specify a protocol for further exploration of IAT by leveraging the massive imaging dataset of the Osteoarthritis Initiative (OAI).

Image analysis for cystic fibrosis: Automatic lung airway wall and vessel measurement on CT images

Cystic Fibrosis (CF) is the most common lethal genetic disorder in the Caucasian population, affecting about 30,000 people in the United States. It results in inflammation, hence thickening of airway (AW) walls. It has been demonstrated that AW inflammation begins early in life producing structural AW damage. Because this damage can be present in patients who are relatively asymptomatic, lung disease can progress insidiously. High-resolution computed tomographic imaging has also shown that the AWs of infants and young children with CF have thicker walls and are more dilated than those of normal children. The purpose of this study was to develop computerized methods which allow rapid, efficient and accurate assessment of computed tomographic AW and vessel (V) dimensions from axial CT lung images. For this purpose, a full-width-half-max based automatic AW and V size measurement method was developed. The only user input required is approximate center marking of AW and V by an expert. The method was evaluated on a patient population of 4 infants and 4 children with different stages of mild CF related lung disease. This new automated method for assessing early AW disease in infants and children with CF represents a potentially useful outcome measure for future intervention trials.

Automatic registration of large set of microscopic images using high-level features

In this paper, we present a novel method for automatic registration of large set of microscopic images by automatically match high-level region features via finding cyclic structures in a matching graph. The use of high-level features (e.g., regions, landmarks, objects) significantly reduced the computation and provides accurate initialization, which further allows fast convergence of the maximum mutual information algorithm. The scheme is a universal one as it works for other types of high-level features and the matching process is very computationally efficient. We have applied our method in 3-D reconstruction of a unique human cochlear sample and are also applying it to two other set of large microscopic images