Statistical shape models for 3D medical image segmentation: a review.

We propose an automatic four-chamber heart segmentation system for the quantitative functional analysis of the heart from cardiac computed tomography (CT) volumes. Two topics are discussed: heart modeling and automatic model fitting to an unseen volume. Heart modeling is a nontrivial task since the heart is a complex nonrigid organ. The model must be anatomically accurate, allow manual editing, and provide sufficient information to guide automatic detection and segmentation. Unlike previous work, we explicitly represent important landmarks (such as the valves and the ventricular septum cusps) among the control points of the model. The control points can be detected reliably to guide the automatic model fitting process. Using this model, we develop an efficient and robust approach for automatic heart chamber segmentation in 3D CT volumes. We formulate the segmentation as a two-step learning problem: anatomical structure localization and boundary delineation. In both steps, we exploit the recent advances in learning discriminative models. A novel algorithm, marginal space learning (MSL), is introduced to solve the 9-D similarity transformation search problem for localizing the heart chambers. After determining the pose of the heart chambers, we estimate the 3D shape through learning-based boundary delineation. The proposed method has been extensively tested on the largest dataset (with 323 volumes from 137 patients) ever reported in the literature. To the best of our knowledge, our system is the fastest with a speed of 4.0 s per volume (on a dual-core 3.2-GHz processor) for the automatic segmentation of all four chambers.

Four-Chamber Heart Modeling and Automatic Segmentation for 3-D Cardiac CT Volumes Using Marginal Space Learning and Steerable Features

Purpose To evaluate image quality and contrast opacification from coronary images acquired from 320-detector row computed tomography (CT). Patient dose is estimated for prospective and retrospective ECG-gating; initial correlation between 320-slice CT and coronary catheterization is illustrated. Methods Retrospective image evaluation from forty consecutive patients included subjective assessment of image quality and contrast opacification (80 ml iopamidol 370 mg I/ml followed by 40 ml saline). Region of interest opacification measurements at the ostium and at 2.5 mm diameter were used to determine the gradient of contrast opacification (defined as the proximal minus distal HU measurements) in coronary arteries imaged in a single heartbeat. Estimated effective dose was compared for prospective versus retrospective ECG-gating, two body mass index categories (30 kg/m2 cutoff), and single versus two heartbeat acquisition. When available, CT findings were correlated with those from coronary catheterization. Results Over 89% of arterial segments (15 segment model) had excellent image quality. The most common reason for image degradation was cardiac motion. One segment in one patient was considered unevaluable. Contrast opacification was almost universally considered excellent. The mean Hounsfield units (HU) was greater than 350; the coronary contrast opacification gradient was 30–50 HU. Patient doses were greater for retrospective ECG-gating, larger patients, and those imaged with two heartbeats. For the most common (n = 25) protocol (120 kV, 400 mA, prospective ECG-gating, 60–100% phase window, 16 cm craniocaudal coverage, single heartbeat), the mean dose was 6.8 ± 1.4 mSv. All CT findings were confirmed in the four patients who underwent coronary catheterization. Conclusion Initial 320-detector row coronary CT images have consistently excellent quality and iodinated contrast opacification. These patients were scanned with conservative protocols with respect to iodine load, prospective ECG-gating phase window, and craniocaudal coverage. Future work will focus on lowering contrast and radiation dose while maintaining image quality.

Initial evaluation of coronary images from 320-detector row computed tomography

As a consequence of improved technology, there is growing clinical interest in the use of multi-detector row computed tomography (MDCT) for non-invasive coronary angiography. Indeed, the accuracy of MDCT to detect or exclude coronary artery stenoses has been high in many published studies. This report of a Writing Group deployed by the Working Group Nuclear Cardiology and Cardiac CT (WG 5) of the European Society of Cardiology and the European Council of Nuclear Cardiology summarizes the present state of cardiac CT technology, as well as the currently available data concerning its accuracy and applicability in certain clinical situations. Besides coronary CT angiography, the use of CT for the assessment of cardiac morphology and function, evaluation of perfusion and viability, and analysis of heart valves is discussed. In addition, recommendations for clinical applications of cardiac CT imaging are given and limitations of the technique are described.

https://www.zora.uzh.ch/id/eprint/14228/4/Schroeder_EuropHeartJourn_2008V.pdf

Cardiac computed tomography: Indications, applications, limitations, and training requirements - Report of a Writing Group deployed by the Working Group Nuclear Cardiology and Cardiac CT of the European Society of Cardiology and the European Council of Nuclear Cardiology

3D deeply supervised network for automated segmentation of volumetric medical images.

Multi-chamber heart segmentation is a prerequisite for global quantification of the cardiac function. The complexity of cardiac anatomy, poor contrast, noise or motion artifacts makes this segmentation problem a challenging task. In this paper, we present an efficient, robust, and fully automatic segmentation method for 3D cardiac computed tomography (CT) volumes. Our approach is based on recent advances in learning discriminative object models and we exploit a large database of annotated CT volumes. We formulate the segmentation as a two step learning problem: anatomical structure localization and boundary delineation. A novel algorithm, marginal space learning (MSL), is introduced to solve the 9-dimensional similarity search problem for localizing the heart chambers. MSL reduces the number of testing hypotheses by about six orders of magnitude. We also propose to use steerable image features, which incorporate the orientation and scale information into the distribution of sampling points, thus avoiding the time-consuming volume data rotation operations. After determining the similarity transformation of the heart chambers, we estimate the 3D shape through learning-based boundary delineation. Extensive experiments on multi-chamber heart segmentation demonstrate the efficiency and robustness of the proposed approach, comparing favorably to the state-of-the-art. This is the first study reporting stable results on a large cardiac CT dataset with 323 volumes. In addition, we achieve a speed of less than eight seconds for automatic segmentation of all four chambers.

/pdf/fast-automatic-heart-chamber-segmentation-from-3d-ct-data-3412v7b3xz.pdf

Fast Automatic Heart Chamber Segmentation from 3D CT Data Using Marginal Space Learning and Steerable Features

A method and system for non-invasive assessment of coronary artery stenosis is disclosed. Patient-specific anatomical measurements of the coronary arteries are extracted from medical image data of a patient acquired during rest state. Patient-specific rest state boundary conditions of a model of coronary circulation representing the coronary arteries are calculated based on the patient-specific anatomical measurements and non-invasive clinical measurements of the patient at rest. Patient-specific rest state boundary conditions of the model of coronary circulation representing the coronary arteries are calculated based on the patient-specific anatomical measurements and non-invasive clinical measurements of the patient at rest. Hyperemic blood flow and pressure across at least one stenosis region of the coronary arteries are simulated using the model of coronary circulation and the patient-specific hyperemic boundary conditions. Fractional flow reserve (FFR) is calculated for the at least one stenosis region based on the simulated hyperemic blood flow and pressure.

Method and System for Non-Invasive Functional Assessment of Coronary Artery Stenosis

High performance deformation of volumetric objects is a common problem in computer graphics that has not yet been handled sufficiently. As a supplement to 3D texture based volume rendering, a novel approach is presented, which adaptively subdivides the volume into piecewise linear patches. An appropriate mathematical model based on tri-linear interpolation and its approximations is proposed. New optimizations are introduced in this paper which are especially tailored to an efficient implementation using general purpose rasterization hardware, including new technologies, such as vertex programs and pixel shaders. Additionally, a high performance model for local illumination calculation is introduced, which meets the aesthetic requirements of visual arts and entertainment. The results demonstrate the significant performance benefit and allow for time-critical applications, such as computer assisted surgery.

/pdf/fast-volumetric-deformation-on-general-purpose-hardware-2bpz633ptv.pdf

Fast volumetric deformation on general purpose hardware

A system and method for segmenting chambers of a heart in three dimensional images is disclosed. A set of three dimensional images of a heart is received. The shape of the heart in the three dimensional images is localized. Boundaries of the chambers of the heart in the localized shape are identified using steerable features.

Michael Scheuering

Papers

Four-Chamber Heart Modeling and Automatic Segmentation for 3-D Cardiac CT Volumes Using Marginal Space Learning and Steerable Features

Fast Automatic Heart Chamber Segmentation from 3D CT Data Using Marginal Space Learning and Steerable Features

Method and System for Non-Invasive Functional Assessment of Coronary Artery Stenosis

Fast volumetric deformation on general purpose hardware

System and method for segmenting chambers of a heart in a three dimensional image