Teodora Chitiboi

Principles and methods for automatic and semi-automatic tissue segmentation in MRI data.

Abstract The development of magnetic resonance imaging (MRI) revolutionized both the medical and scientific worlds. A large variety of MRI options have generated a huge amount of image data to interpret. The investigation of a specific tissue in 3D or 4D MR images can be facilitated by image processing techniques, such as segmentation and registration. In this work, we provide a brief review of the principles and methods that are commonly applied to achieve superior tissue segmentation results in MRI. The impacts of MR image acquisition on segmentation outcome and the principles of selecting and exploiting segmentation techniques tailored for specific tissue identification tasks are discussed. In the end, two exemplary applications, breast and fibroglandular tissue segmentation in MRI and myocardium segmentation in short-axis cine and real-time MRI, are discussed to explain the typical challenges that can be posed in practical segmentation tasks in MRI data. The corresponding solutions that are adopted to deal with these challenges of the two practical segmentation tasks are thoroughly reviewed.

Context-based segmentation and analysis of multi-cycle real-time cardiac MRI

The recent development of a real-time magnetic resonance imaging (MRI) technique with 20 to 30 ms temporal resolution allows for imaging multiple consecutive heart cycles, without the need for breath holding or ECG synchronization. Manual analysis of the resulting image series is no longer feasible because of their length. We propose a region-based algorithm for automatically segmenting the myocardium in consecutive heart cycles based on local context and prior knowledge. The method was evaluated on ten real-time MRI series and compared to segmentations by two observers, with promising results. We show that our approach enables a multicycle analysis of the heart function robust to breathing and arrhythmia.

Automatic MRI segmentation of para-pharyngeal fat pads using interactive visual feature space analysis for classification

BackgroundObstructive sleep apnea (OSA) is a public health problem. Detailed analysis of the para-pharyngeal fat pads can help us to understand the pathogenesis of OSA and may mediate the intervention of this sleeping disorder. A reliable and automatic para-pharyngeal fat pads segmentation technique plays a vital role in investigating larger data bases to identify the anatomic risk factors for the OSA.MethodsOur research aims to develop a context-based automatic segmentation algorithm to delineate the fat pads from magnetic resonance images in a population-based study. Our segmentation pipeline involves texture analysis, connected component analysis, object-based image analysis, and supervised classification using an interactive visual analysis tool to segregate fat pads from other structures automatically.ResultsWe developed a fully automatic segmentation technique that does not need any user interaction to extract fat pads. Our algorithm is fast enough that we can apply it to population-based epidemiological studies that provide a large amount of data. We evaluated our approach qualitatively on thirty datasets and quantitatively against the ground truths of ten datasets resulting in an average of approximately 78% detected volume fraction and a 79% Dice coefficient, which is within the range of the inter-observer variation of manual segmentation results.ConclusionThe suggested method produces sufficiently accurate results and has potential to be applied for the study of large data to understand the pathogenesis of the OSA syndrome.

3D superquadric glyphs for visualizing myocardial motion

Various cardiac diseases can be diagnosed by the analysis of myocardial motion. Relevant biomarkers are radial, longitudinal, and rotational velocities of the cardiac muscle computed locally from MR images. We designed a visual encoding that maps these three attributes to glyph shapes according to a barycentric space formed by 3D superquadric glyphs. The glyphs show aggregated myocardial motion information following the AHA model and are displayed in a respective 3D layout.

Automatic Pharynx Segmentation from MRI Data for Obstructive Sleep Apnea Analysis

Obstructive sleep apnea (OSA) is a public health problem. Volumetric analysis of the upper airways can help us to understand the pathogenesis of OSA. A reliable pharynx segmentation is the first step in identifying the anatomic risk factors for this sleeping disorder. As manual segmentation is a time-consuming and subjective process, a fully automatic segmentation of pharyngeal structures is required when investigating larger data bases such as in cohort studies. We develop a context-based automatic algorithm for segmenting pharynx from magnetic resonance images (MRI). It consists of a pipeline of steps including pre-processing (thresholding, connected component analysis) to extract coarse 3D objects, classification of the objects (involving object-based image analysis (OBIA), visual feature space analysis, and silhouette coefficient computation) to segregate pharynx from other structures automatically, and post-processing to refine the shape of the identified pharynx (including extraction of the oropharynx and propagating results from neighboring slices to slices that are difficult to delineate). Our technique is fast such that we can apply our algorithm to population-based epidemiological studies that provide a high amount of data. Our method needs no user interaction to extract the pharyngeal structure. The approach is quantitatively evaluated on ten datasets resulting in an average of approximately 90% detected volume fraction and a 90% Dice coefficient, which is in the range of the interobserver variation within manual segmentation results.

Visual analysis of medical image segmentation feature space for interactive supervised classification

Classification of image regions is a crucial step in many image segmentation algorithms. Assigning a segment to a certain class can be based on various numerical characteristics such as size, intensity statistics, or shape, which build a multi-dimensional feature space describing the segments. It is commonly unclear and not intuitive, however, how much influence or weight should be assigned to the individual features to obtain a best classification. We propose an interactive supervised approach to the classification step based on a feature-space visualization. Our visualization method helps the user to better understand the structure of the feature space and to interactively optimize feature selection and assigned weights. When investigating labeled training data, the user generates optimal descriptors for each target class. The obtained set of descriptors can then be transferred to classify unlabeled data. We show the effectiveness of our approach by embedding our interactive supervised classification method into a medical image segmentation pipeline for two application scenarios: detecting vertebral bodies in sagittal CT image slices, where we improve the overall accuracy, and detecting the pharynx in head MRI data.

Evaluation of a phase-based motion tracking method for the calculation of myocardial stress and strain from tagged MRI

Background Tagged MRI is an established technique for the tracking of local deformations of the myocardium. The quantitative assessment of myocardial stress and strain is however a non-trivial task and only few software tools are available for clinical use. The purpose of this work was the evaluation of a phase-based motion tracking method for fully automatic calculation of deformation parameters from tagged MRI sequences [1]. Methods

Automatic Perfusion Analysis Using Phase-Based Registration and Object-Based Image Analysis

MRI perfusion imaging enables the non-invasive assessment of myocardial blood supply. The purpose of the presented work is to enable a quantitative assessment of the image sequences for clinical application. To this end an automatic preprocessing including ROI detection and outlier removal has been combined with a phase-based registration approach and an object-based myocardium segmentation. The suggested processing pipeline has been tested with 21 image sequences provided by the STACOM motion correction challenge. The corrected image sequences have been assessed by comparison with gamma variate curves fitted to the voxels intensity curves. The automatic segmentation could be compared with expert segmentations provided by the challenge organizers. The results indicate an improvement through the motion correction and a good agreement with the reference segmentation in most cases.

Object-Based Boundary Properties

While object-based image analysis specializes in using region features for object detection, it lacks the possibility to use border strength and local geometry, common in edge detection. We propose to enhance common object-based image representation with boundary features that measure strength and continuity. Using these we formulate strategies for merging regions in a partitioned image to identify potentially regular shapes. To illustrate the capacity of this approach, we apply the proposed concepts to CT bone segmentation.

Multi-cycle Reconstruction of Cardiac MRI for the Analysis of Inter-ventricular Septum Motion During Free Breathing

Small variations in left-ventricular preload due to respiration produce measurable changes in cardiac function in normal subjects. We show that this mechanism is altered in patients with reduced ejection fraction (EF), hypertrophy, or volume-loaded right ventricle (RV). We propose a multi-dimensional retrospective image reconstruction, based on an adaptive, soft classification of data into respiratory and cardiac phases, to study these effects.