Salwa Elshazly

Appearance models for robust segmentation of pulmonary nodules in 3d LDCT chest images

To more accurately separate each pulmonary nodule from its background in a low dose computer tomography (LDCT) chest image, two new adaptive probability models of visual appearance of small 2D and large 3D pulmonary nodules are used to control evolution of deformable boundaries. The appearance prior is modeled with a translation and rotation invariant Markov-Gibbs random field of voxel intensities with pairwise interaction analytically identified from a set of training nodules. Appearance of the nodules and their background in a current multi-modal chest image is also represented with a marginal probability distribution of voxel intensities. The nodule appearance model is isolated from the mixed distribution using its close approximation with a linear combination of discrete Gaussians. Experiments with real LDCT chest images confirm high accuracy of the proposed approach.

Evaluation of geometric feature descriptors for detection and classification of lung nodules in low dose CT scans of the chest

This paper examines the effectiveness of geometric feature descriptors, common in computer vision, for false positive reduction and for classification of lung nodules in low dose CT (LDCT) scans. A data-driven lung nodule modeling approach creates templates for common nodule types, using active appearance models (AAM); which are then used to detect candidate nodules based on optimum similarity measured by the normalized cross-correlation (NCC). Geometric feature descriptors (e.g., SIFT, LBP and SURF) are applied to the output of the detection step, in order to extract features from the nodule candidates, for further enhancement of output and possible reduction of false positives. Results on the clinical ELCAP database showed that the descriptors provide 2% enhancements in the specificity of the detected nodule above the NCC results when used in a k-NN classifier. Thus quantitative measures of enhancements of the performance of CAD models based on LDCT are now possible and are entirely model-based. Most importantly, our approach is applicable for classification of nodules into categories and pathologies.

An AAM-based detection approach of lung nodules from LDCT scans

In this, paper a new approach for lung nodules detection from LDCT scans is proposed. Intensity models of the nodules are generated using an active appearance model formulation. Template matching is used to compute a similarity score between the AAM template and the input image. The goal is to maximize the similarity measure at different image pixels to increase nodule detection. Conventional template matching does not account for rotation variations. Our proposed template matching approach is formulated as an energy optimization problem that computes a transformation that includes rotation(s) parameters as well as the AAM weighting coefficients. The approach is flexible to different scans and different nodule locations because of the ability to handle the variations in the rotation between the template and the input images. The approach can employ different similarity measures. Experimental results will be shown using three similarity measures from the literature: NCC, ZNCC and ZSSD; which illustrate the efficiency of the proposed approach. ROC curves for various nodule types are constructed on a clinical study with known ground truth, showing significant enhancements over conventional parametric nodule models and traditional template matching criterion.

Variational approach for segmentation of lung nodules

Lung nodules from low dose CT (LDCT) scans may be used for early detection of lung cancer. However, these nodules vary in size, shape, texture, location, and may suffer from occlusion within the tissue. This paper presents an approach for segmentation of lung nodules detected by a prior step. First, regions around the detected nodules are segmented; using automatic seed point placement levels sets. The outline of the nodule region is further improved using the curvature characteristics of the segmentation boundary. We illustrate the effectiveness of this method for automatic segmentation of the Juxta-pleural nodules.

Statistical modeling of the lung nodules in low dose computed tomography scans of the chest

This work presents a novel approach in automatic detection of the lung nodules and is compared with respect to parametric nodule models in terms of sensitivity and specificity. A Statistical method is used for generating data driven models of the nodules appearing in low dose CT (LDCT) scans of the human chest. Four types of common lung nodules are analyzed using the Procrustes based AAM method to create descriptive lung nodules. Performance of the new nodule models on clinical datasets is significant over parametric nodule models in both sensitivity and specificity. The new nodule modeling approach is also applicable for automatic classification of nodules into pathologies given a descriptive database. This approach is a major step forward for early diagnosis of lung cancer.

Data-Driven Lung Nodule Models for Robust Nodule Detection in Chest CT

The quality of the lung nodule models determines the success of lung nodule detection. This paper describes aspects of our data-driven approach for modeling lung nodules using the texture and shape properties of real nodules to form an average model template per nodule type. The ELCAP low dose CT (LDCT) scans database is used to create the required statistics for the models based on modern computer vision techniques. These models suit various machine learning approaches for nodule detection including Bayesian methods, SVM and Neural Networks, and computations may be enhanced through genetic algorithms and Adaboost. The eminence of the new nodule models are studied with respect to parametric models showing significant improvements in both sensitivity and specificity.

Experiments on Sensitivity of Template Matching for Lung Nodule Detection in Low Dose CT Scans

Template matching is a common approach for detection of lung nodules from CT scans. Templates may take different shapes, size and intensity distribution. The process of nodule detection is essentially two steps: isolation of candidate nodules, and elimination of false positive nodules. The processes of outlining the detected nodules and their classification (i.e., assigning pathology for each nodule) complete the CAD system for early detection of lung nodules. This paper is concerned with the template design and evaluating the effectiveness of the first step in the nodule detection process. The paper will neither address the problem of reducing false positives nor would it deal with nodule segmentation and classification. Only parametric templates are considered. Modeling the gray scale distribution for the templates is based on the prior knowledge of typical nodules extracted by radiologists. The effectiveness of the template matching is investigated by cross validation with respect to the ground truth and is described by hit rate curves indicating the probability of detection as function of shape, size and orientation, if applicable, of the templates. We used synthetic and sample real CT scan images in our experiments. It is found that template matching is more sensitive to additive noise than image blurring when tests conducted on synthetic data. On the sample CT scans small size circular and hollow-circular templates provided comparable results to human experts.

Small-size lung nodule modeling and detection with clinical evaluation

In this paper examination of the template modeling process using the Active Appearance Modeling (AAM) approach for automatic detection of lung nodules is investigated. A template matching approach is formulated to compute a similarity score between the AAM templates and the input lung CT slice, where the goal is to maximize the similarity measure at different image pixels to increase nodule detection. The template matching approach is implemented using nine similarity measures. Performance validation for the robustness of the generated models is tested on three clinical databases.

Statistical morphable model for human teeth restoration

While traditional dental fillings are molded during a dental visit, dental restoration (e.g. inlays and onlays) are fabricated in a dental lab to offer a long lasting reparative solution to tooth decay or similar structural damage. Such process requires dental technicians who are highly trained experts in tooth anatomy to pick an appropriate standard tooth model from a tooth database. The success of a restoration process primarily relies on the acquisition and modeling of an accurate 3D shape of the occlusal surface of interest for manufacturing purposes. Based on a single optical image, this paper provides an economical and automated solution for tooth restoration where user intervention is kept at the minimal. The inherit relation between the photometric information and the underlying 3D shape is formulated as a coupled statistical model where the effect of illumination is modeled using Spherical Harmonics. Moreover, shape and texture alignment is accomplished using a proposed definition of anatomical jaw landmarks which are automatically detected. The system is evaluated on database of 32 jaws for crown, inlay, and onlay restoration. Results shows a promising performance for using the proposed approach in clinical application.

Modeling of the lung nodules for detection in LDCT scans

A novel approach is proposed for generating data driven models of the lung nodules appearing in low dose CT (LDCT) scans of the human chest. Four types of common lung nodules are analyzed using Active Appearance Model methods to create descriptive lung nodule models. The proposed approach is also applicable for automatic classification of nodules into pathologies given a descriptive database. This approach is a major step forward for early diagnosis of lung cancer. We show the performance of the new nodule models on clinical datasets which illustrates significant improvements in both sensitivity and specificity.