Soumik Ukil

Anatomy-Guided Lung Lobe Segmentation in X-Ray CT Images

The human lungs are divided into five distinct anatomic compartments called the lobes, which are separated by the pulmonary fissures. The accurate identification of the fissures is of increasing importance in the early detection of pathologies, and in the regional functional analysis of the lungs. We have developed an automatic method for the segmentation and analysis of the fissures, based on the information provided by the segmentation and analysis of the airway and vascular trees. This information is used to provide a close initial approximation to the fissures, using a watershed transform on a distance map of the vasculature. In a further refinement step, this estimate is used to construct a region of interest (ROI) encompassing the fissures. The ROI is enhanced using a ridgeness measure, which is followed by a 3-D graph search to find the optimal surface within the ROI. We have also developed an automatic method to detect incomplete fissures, using a fast-marching based segmentation of a projection of the optimal surface. The detected incomplete fissure is used to extrapolate and smoothly complete the fissure. We evaluate the method by testing on data sets from normal subjects and subjects with mild to moderate emphysema.

Smoothing lung segmentation surfaces in 3D x-ray CT images using anatomic guidance

Several methods for automatic lung segmentation in volumetric computed tomography (CT) images have been proposed. Most methods distinguish the lung parenchyma from the surrounding anatomy based on the difference in CT attenuation values. This can lead to an irregular and inconsistent lung boundary for the regions near the mediastinum. This paper presents a fully automatic method for the 3D smoothing of the lung boundary using information from the segmented human airway tree. First, using the segmented airway tree we define a bounding box around the mediastinum for each lung, within which all operations are performed. We then define all generations of the airway tree distal to the right and left mainstem bronchi to be part of the respective lungs, and exclude all other segments. Finally, we perform a fast morphological closing with an ellipsoidal kernel to smooth the surface of the lung. This method has been tested by processing the segmented lungs from eight normal datasets. The mean value of the magnitude of curvature of the contours of mediastinal transverse slices, averaged over all the datasets, is 0.0450 before smoothing and 0.0167 post smoothing. The accuracy of the lung contours after smoothing is assessed by comparing the automatic results to manually traced smooth lung borders by a human analyst. Averaged over all volumes, the root mean square difference between human and computer borders is 0.8691 mm after smoothing, compared to 1.3012 mm before. The mean similarity index, which is an area overlap measure based on the kappa statistic, is 0.9958 (SD 0.0032).

Automatic lung lobe segmentation in x-ray CT images by 3D watershed transform using anatomic information from the segmented airway tree

The human lungs are divided into five distinct anatomic compartments called lobes. The physical boundaries between the lobes are called the lobar fissures. Detection of lobar fissure positions in pulmonary X-ray CT images is of increasing interest for the diagnosis of lung disease. We have developed an automatic method for segmentation of all five lung lobes simultaneously using a 3D watershed transform on the distance transform of a previously generated vessel mask, linearly combined with the original data. Due to the anatomically separate airway sub-trees for individual lobes, we can accurately and automatically place seed points for the watershed segmentation based on the airway tree anatomical description, due to the fact that lower generation airway and vascular tree segments are located near each other. This, along with seed point placement using information on the spatial location of the lobes, can give a close approximation to the actual lobar fissures. The accuracy of the lobar borders is assessed by comparing the automatic segmentation to manually traced lobar boundaries. Averaged over all volumes, the RMS distance errors for the left oblique fissure, right oblique fissure and right horizontal fissure are 3.720 mm, 0.713 mm and 1.109 mm respectively.

Automatic segmentation of pulmonary fissures in x-ray CT images using anatomic guidance

The pulmonary lobes are the five distinct anatomic divisions of the human lungs. The physical boundaries between the lobes are called the lobar fissures. Detection of lobar fissure positions in pulmonary X-ray CT images is of increasing interest for the early detection of pathologies, and also for the regional functional analysis of the lungs. We have developed a two-step automatic method for the accurate segmentation of the three pulmonary fissures. In the first step, an approximation of the actual fissure locations is made using a 3-D watershed transform on the distance map of the segmented vasculature. Information from the anatomically labeled human airway tree is used to guide the watershed segmentation. These approximate fissure boundaries are then used to define the region of interest (ROI) for a more exact 3-D graph search to locate the fissures. Within the ROI the fissures are enhanced by computing a ridgeness measure, and this is used as the cost function for the graph search. The fissures are detected as the optimal surface within the graph defined by the cost function, which is computed by transforming the problem to the problem of finding a minimum s-t cut on a derived graph. The accuracy of the lobar borders is assessed by comparing the automatic results to manually traced lobe segments. The mean distance error between manually traced and computer detected left oblique, right oblique and right horizontal fissures is 2.3 ± 0.8 mm, 2.3 ± 0.7 mm and 1.0 ± 0.1 mm, respectively.

Robust segment-based Stereo using Cost Aggregation.

Introduction Most segment based stereo methods estimate disparity by modeling color segments as 3-D planes [2]. Inherently, such methods are sensitive to segmentation parameters and intolerant to segmentation errors. Two main dependencies of these methods on the underlying segmentation algorithm are: size of segments used for estimating planes, and assignment of a single plane to the whole segment. Specifically, in the case of under-segmentation, there is a higher chance of merging multiple objects (with multiple plane surfaces) into a single segment. Consequently, planes estimated using these segments are erroneous. The effect propagates to the disparity map, wherein a larger segment encompassing multiple objects is incorrectly represented by a single disparity plane. In the over-segmentation case, which gives smaller color segments, the estimated planes may be unreliable, leading to an inaccurate disparity map. Popular segment based methods try to solve this problem by re-fitting the planes on grouped segments, in an iterative manner [2]. We propose a novel algorithm for generating sub-pixel accurate disparities on a perpixel basis, thus alleviating the problems arising from methods that estimate disparities on a per-segment basis. The proposed method computes sub-pixel precision disparity maps using the recent minimum spanning tree (MST) [4] based cost aggregation framework. Since the disparity at every pixel is modeled by a plane equation, the goal is to ensure that all pixels belonging to a planar surface are labeled with the same plane equation. We show that using a reduced and refined set of planes as candidate labels in the aggregation framework ensures homogeneous labeling within a color segment. Proposed Method Our method computes an initial set of plane equations (label set) by fitting planes inside a color segment using the consistent disparities from an initial disparity map. The initial disparity map may be generated using any local or global algorithm. These plane equations form the initial label set and a matching cost volume is computed over this set for every pixel. This cost volume is aggregated using MST based cost aggregation framework and a WTA over the aggregated cost volume gives the initial labeling. The number of labels in the initial set is of the order of the number of segments, with a plane estimate for every segment. The initial labeling is used along with the color segmentation to filter and generate a reduced set of planes. This framework of plane filtering followed by re-labeling leads to a more accurate disparity map. In addition, segment analysis is also used to modify the plane matching cost. We weigh the pixel matching cost by a support factor, where the support factor is derived from the distribution of plane labels within the color segment, as follows:

Video stabilization by estimation of similarity transformation from integral projections

The widespread use of hand held devices having video recording capabilities has made video capture prevalent. However, unwanted hand motion during capture introduces jerks which hampers the video viewing experience. In this paper, a robust method for global motion estimation between frames is presented. The algorithm estimates the rotation, scale and translation parameters between two adjacent frames. All the parameters of the similarity transformation are estimated by aligning the integral projections computed from the images. A novel framework is presented which uses angular integral projections to estimate rotation, scale and translation between adjacent frames. The curve warping technique, Derivative dynamic time warping (DDTW) is used for aligning the projection curves. Experimental results demonstrate the robustness of the proposed approach in stabilizing videos, including those captured under challenging conditions.

Pixel resolution plenoptic disparity using cost aggregation

We present a hierarchical method for estimating pixel resolution disparity from a raw Plenoptic 2.0 light field capture. Accurate pixel resolution disparity is essential for reconstruction of a high quality conventional image, and also for various applications that depend on disparity, like object segmentation, bokeh etc. Most light field disparity estimation methods in the literature compute disparity at microlens resolution, which is much lower than the resolution of the final reconstructed image. The algorithms that do compute pixel resolution disparity are iterative, making them computationally complex. The proposed method computes disparity hierarchically, in two steps. In the first step, microlens resolution disparity is computed, using which a conventional high resolution image is reconstructed. In the second step, globally smooth and accurate disparity is estimated at a pixel level on the reconstructed image, using the computationally efficient minimum spanning tree based cost aggregation approach. Experimental results demonstrate that the accuracy of the disparity maps generated by our method, in comparison to the Multibaseline and Raytrix algorithms is superior.

A fast blink detector using Canonical Correlation Analysis

Blinking is an involuntary action performed by people to keep their eyes moist but this becomes a problem when capturing an image. This problem becomes more pronounced when a flash is being used for image capture. Some of the algorithms that are present in the literature today are quite complex. Also, the detection accuracy of the present algorithms in literature is heavily dependent on temporal information. Temporal information is derived from the continuous video stream, but in the case where a flash is used for capture of an Image, temporal information may not be available. In this paper we propose a simple classification algorithm that is based on CCA (Canonical Correlation Analysis) to perform fast Blink detection for computationally constrained devices.

Three-dimensional and Four-dimensional Cardiopulmonary Image Analysis

Modern medical imaging equipment can provide data that describe the anatomy and function of structures in the body. Image segmentation techniques are needed to take this raw data and identify and delineate the relevant cardiovascular and pulmonary anatomy to put it into a form suitable for 3D and 4D modeling and simulation. These methods must be able to handle large multi-dimensional data sets, possibly limited in resolution, corrupted by noise and motion blur, and sometimes depicting unusual anatomy due to natural shape variation across the population or due to disease processes. This chapter describes modern techniques for robust, automatic image segmentation. Several applications in cardiovascular and pulmonary imaging are presented.

PULMONARY CT IMAGE ANALYSIS AND COMPUTER AIDED DETECTION

This short article summarizes the use of current CT image data for a comprehensive assessment of pulmonary structure and function. It identifies the need for the development of highly automated methods and techniques allowing quantitative analysis of lungs, lung lobes, airway trees, and pulmonary parenchyma. Such analyses serve as the stepping stones for more sophisticated computer-aided detection approaches capable of parenchymal tissue characterization and identification of pulmonary nodules, some of which are discussed