Sokratis Makrogiannis

Bone texture characterization for osteoporosis diagnosis using digital radiography

We introduce texture classification techniques to effectively diagnose osteoporosis in bone radiography data. Osteoporosis is an age-related systemic bone skeletal disorder characterized by low bone mass and bone structure deterioriation that results in increased bone fragility and higher fracture risk. Therefore, early diagnosis can effectively predict fracture risk and prevent the disease. Automated diagnosis from digital radiographs is very challenging since the scans of healthy and osteoporotic subjects show little or no visual differences, and their density histograms mostly overlap. We designed a system to separate healthy from osteoporotic subjects using high-dimensional textural feature representations computed from radiographs. These features were then reduced using feature selection to obtain the more discriminant subset that was finally classified by our methods. The top performing approach yields 79.3% accuracy and 81% area under the ROC over 116 bone radiographs.We introduce texture classification techniques to effectively diagnose osteoporosis in bone radiography data. Osteoporosis is an age-related systemic bone skeletal disorder characterized by low bone mass and bone structure deterioriation that results in increased bone fragility and higher fracture risk. Therefore, early diagnosis can effectively predict fracture risk and prevent the disease. Automated diagnosis from digital radiographs is very challenging since the scans of healthy and osteoporotic subjects show little or no visual differences, and their density histograms mostly overlap. We designed a system to separate healthy from osteoporotic subjects using high-dimensional textural feature representations computed from radiographs. These features were then reduced using feature selection to obtain the more discriminant subset that was finally classified by our methods. The top performing approach yields 79.3% accuracy and 81% area under the ROC over 116 bone radiographs.

Imaging and tracking HIV viruses in human cervical mucus

Abstract. We describe a systematic approach to image, track, and quantify the movements of HIV viruses embedded in human cervical mucus. The underlying motivation for this study is that, in HIV-infected adults, women account for more than half of all new cases and most of these women acquire the infection through heterosexual contact. The endocervix is believed to be a susceptible site for HIV entry. Cervical mucus, which coats the endocervix, should play a protective role against the viruses. Thus, we developed a methodology to apply time-resolved confocal microscopy to examine the motion of HIV viruses that were added to samples of untreated cervical mucus. From the images, we identified the viruses, tracked them over time, and calculated changes of the statistical mean-squared displacement (MSD) of each virus. Approximately half of tracked viruses appear constrained while the others show mobility with MSDs that are proportional to τα+ν2τ2, over time range τ, depicting a combination of anomalous diffusion (0<α<0.4) and flow-like behavior. The MSD data also reveal plateaus attributable to possible stalling of the viruses. Although a more extensive study is warranted, these results support the assumption of mucus being a barrier against the motion of these viruses.

Spatio-temporal Level-Set Based Cell Segmentation in Time-Lapse Image Sequences

Automated segmentation and tracking of cells in time-lapse imaging is a process of fundamental significance in several biomedical applications. In this work our interest is focused on cell segmentation over a set of fluorescence microscopy images with varying levels of difficulty with respect to cell density, resolution, contrast, and signal-to-noise ratio. We utilize a region-based approach to curve evolution based on the level-set formulation. We introduce and test the use of temporal linking for level-set initialization to improve the robustness and computational time of level-set convergence. We validate our segmentation approach against manually segmented images provided by the Cell Tracking Challenge consortium. Our method produces encouraging segmentation results with an average DICE score of 0.78 over a variety of simulated and real sequences and speeds up the convergence rate by an average factor of 10.2.

Spatio-temporal diffusion-based dynamic cell segmentation

Cell segmentation is a critical step for quantification and monitoring of cell behavior in image sequences. In this study, we propose to use a non-linear heat diffusion equation model in the joint spatio-temporal domain for cell segmentation of time-lapse image sequences. Moving regions are initially detected in each set of three consecutive sequence images by numerically solving a system of coupled spatio-temporal partial differential equations and determining the optimal values for the temporal and spatial diffusion parameters. After the spatio-temporal diffusion stage is completed, we compute the edge map by non-parametric density estimation using Parzen kernels. This process is followed by watershed-based segmentation to detect the moving cells. We applied this method on several datasets of fluorescence microscopy images with varying levels of difficulty with respect to cell density, resolution, contrast, and signal-to-noise ratio. We compared the results with those produced by Chan and Vese level-set based segmentation and a temporally linked level set technique. We validated all segmentation techniques against reference masks provided by the international Cell Tracking Challenge consortium. Our proposed method produced encouraging segmentation accuracy, especially when applied to images containing cells undergoing mitosis and low SNR. The performance evaluation clearly indicates the efficiency and robustness of this method in detecting and segmenting the cells with an average Dice similarity coefficient of 85% over a variety of simulated and real fluorescent image sequences. The proposed technique yielded average improvements of 7% in segmentation accuracy compared to both strictly spatial and temporally linked Chan-Vese techniques.

Automated skeletal tissue quantification in the lower leg using peripheral quantitative computed tomography

OBJECTIVE In this paper we introduce a methodology for hard and soft tissue quantification at proximal, intermediate and distal tibia sites using peripheral quantitative computed tomography scans. Quantification of bone properties is crucial for estimating bone structure resistance to mechanical stress and adaptations to loading. Soft tissue variables can be computed to investigate muscle volume and density, muscle-bone relationship, and fat infiltration. APPROACH We employed implicit active contour models and clustering techniques for automated segmentation and identification of bone, muscle and fat at [Formula: see text], [Formula: see text], and [Formula: see text] tibia length. Next, we calculated densitometric, area and shape characteristics for each tissue type. We implemented our approach as a multi-platform tool denoted by TIDAQ (tissue identification and quantification) to be used by clinical researchers. MAIN RESULTS We validated the proposed method against reference quantification measurements and tissue delineations obtained by semi-automated workflows. The average Deming regression slope between the tested and reference method was 1.126 for cross-sectional areas and 1.078 for mineral densities, indicating very good agreement. Our method produced high average coefficient of variation (R 2) estimates: 0.935 for cross-sectional areas and 0.888 for mineral densities over all tibia sites. In addition, our tissue segmentation approach achieved an average Dice coefficient of 0.91 over soft and hard tissues, indicating very good delineation accuracy. SIGNIFICANCE Our methodology should allow for high throughput, accurate and reproducible automatic quantification of muscle and bone characteristics of the lower leg. This information is critical to evaluate risk of future adverse outcomes and assess the effect of medications, hormones, and behavioral interventions aimed at improving bone and muscle strength.

A preliminary study for automatic accurate detection of adenomatous polyps in the small intestine

In this paper we present a novel preliminary study based on state of the art computation techniques applied on WCE video images for extracting features and patterns from different views of the same polyp. The extracted pattern and features are synthesized by using LG registration technique to create better views for each polyp by removing artifacts and noise. The outcome images (views) from each polyp will be used for the training and testing of a machine learning system that will separate the two types of diminutive polyps.

Sparse Representation Using Block Decomposition for Characterization of Imaging Patterns

In this work we introduce sparse representation techniques for classification of high-dimensional imaging patterns into healthy and diseased states. We also propose a spatial block decomposition methodology that is used for training an ensemble of classifiers to address irregularities of the approximation problem. We first apply this framework to classification of bone radiography images for osteoporosis diagnosis. The second application domain is separation of breast lesions into benign and malignant. These are challenging classification problems because the imaging patterns are typically characterized by high Bayes error rate in the original space. To evaluate the classification performance we use cross-validation techniques. We also compare our sparse-based classification with state-of-the-art texture-based classification techniques. Our results indicate that decomposition into patches addresses difficulties caused by ill-posedness and improves original sparse classification.

Image-Based Tissue Distribution Modeling for Skeletal Muscle Quality Characterization

The identification and characterization of regional body tissues is essential to understand changes that occur with aging and age-related metabolic diseases such as diabetes and obesity and how these diseases affect trajectories of health and functional status. Imaging technologies are frequently used to derive volumetric, area, and density measurements of different tissues. Despite the significance and direct applicability of automated tissue quantification and characterization techniques, these topics have remained relatively under explored in the medical image analysis literature. We present a method for identification and characterization of muscle and adipose tissue in the mid-thigh region using MRI. We propose an image-based muscle quality prediction technique that estimates tissue-specific probability density models and their eigenstructures in the joint domain of water- and fat-suppressed voxel signal intensities along with volumetric and intensity-based tissue characteristics computed during the quantification stage. We evaluated the predictive capability of our approach against reference biomechanical muscle quality (MQ) measurements using statistical tests and classification performance experiments. The reference standard for MQ is defined as the ratio of muscle strength to muscle mass. The results show promise for the development of noninvasive image-based MQ descriptors.

Joint level-set and spatio-temporal motion detection for cell segmentation.

BackgroundCell segmentation is a critical step for quantification and monitoring of cell cycle progression, cell migration, and growth control to investigate cellular immune response, embryonic development, tumorigenesis, and drug effects on live cells in time-lapse microscopy images.MethodsIn this study, we propose a joint spatio-temporal diffusion and region-based level-set optimization approach for moving cell segmentation. Moving regions are initially detected in each set of three consecutive sequence images by numerically solving a system of coupled spatio-temporal partial differential equations. In order to standardize intensities of each frame, we apply a histogram transformation approach to match the pixel intensities of each processed frame with an intensity distribution model learned from all frames of the sequence during the training stage. After the spatio-temporal diffusion stage is completed, we compute the edge map by nonparametric density estimation using Parzen kernels. This process is followed by watershed-based segmentation and moving cell detection. We use this result as an initial level-set function to evolve the cell boundaries, refine the delineation, and optimize the final segmentation result.ResultsWe applied this method to several datasets of fluorescence microscopy images with varying levels of difficulty with respect to cell density, resolution, contrast, and signal-to-noise ratio. We compared the results with those produced by Chan and Vese segmentation, a temporally linked level-set technique, and nonlinear diffusion-based segmentation. We validated all segmentation techniques against reference masks provided by the international Cell Tracking Challenge consortium. The proposed approach delineated cells with an average Dice similarity coefficient of 89 % over a variety of simulated and real fluorescent image sequences. It yielded average improvements of 11 % in segmentation accuracy compared to both strictly spatial and temporally linked Chan-Vese techniques, and 4 % compared to the nonlinear spatio-temporal diffusion method.ConclusionsDespite the wide variation in cell shape, density, mitotic events, and image quality among the datasets, our proposed method produced promising segmentation results. These results indicate the efficiency and robustness of this method especially for mitotic events and low SNR imaging, enabling the application of subsequent quantification tasks.

Finding the N-cuts of Watershed Partitions for Image Segmentation

The normalized cut (N-cut) algorithm uses an algebraic graph optimization technique for image segmentation. Although N-cut produces good results for a variety of images, it has some weaknesses, such as high computational cost and sub-optimal partitions. In this paper we adopt the watershed transform to address these problems. Watershed can improve slow computing speed and produce closed object boundaries. However, watershed itself has the drawback of over-segmentation. Therefore, we propose to first apply watershed, then build a graph from the watershed regions, and find the N-cuts of the watershed region graph to improve segmentation accuracy. The objective of this paper is two-fold; the first goal is to reduce the complexity of this problem by optimizing region-based graph structures. The second goal is to validate the performance of the existing and proposed methods, and to test the hypothesis that region-based analysis reduces the complexity of optimization problem and improves segmentation accuracy.