Gareth Beddoe

Shape-Based Computer-Aided Detection of Lung Nodules in Thoracic CT Images

In this paper, a new computer tomography (CT) lung nodule computer-aided detection (CAD) method is proposed for detecting both solid nodules and ground-glass opacity (GGO) nodules (part solid and nonsolid). This method consists of several steps. First, the lung region is segmented from the CT data using a fuzzy thresholding method. Then, the volumetric shape index map, which is based on local Gaussian and mean curvatures, and the ldquodotrdquo map, which is based on the eigenvalues of a Hessian matrix, are calculated for each voxel within the lungs to enhance objects of a specific shape with high spherical elements (such as nodule objects). The combination of the shape index (local shape information) and ldquodotrdquo features (local intensity dispersion information) provides a good structure descriptor for the initial nodule candidates generation. Antigeometric diffusion, which diffuses across the image edges, is used as a preprocessing step. The smoothness of image edges enables the accurate calculation of voxel-based geometric features. Adaptive thresholding and modified expectation-maximization methods are employed to segment potential nodule objects. Rule-based filtering is first used to remove easily dismissible nonnodule objects. This is followed by a weighted support vector machine (SVM) classification to further reduce the number of false positive (FP) objects. The proposed method has been trained and validated on a clinical dataset of 108 thoracic CT scans using a wide range of tube dose levels that contain 220 nodules (185 solid nodules and 35 GGO nodules) determined by a ground truth reading process. The data were randomly split into training and testing datasets. The experimental results using the independent dataset indicate an average detection rate of 90.2%, with approximately 8.2 FP/scan. Some challenging nodules such as nonspherical nodules and low-contrast part-solid and nonsolid nodules were identified, while most tissues such as blood vessels were excluded. The methods high detection rate, fast computation, and applicability to different imaging conditions and nodule types shows much promise for clinical applications.

Medical Image Segmentation

Medical image plays an important role in the assist doctors in the diagnosis and treatment of diseases. For the medical image, the further analysis and diagnosis of the target area is based on image segmentation. There are many different kinds of image segmentation algorithms. In this paper, image segmentation algorithms are divided into classical image segmentation algorithms and segmentation methods combined with certain mathematical tools, including threshold segmentation methods, image segmentation algorithms based on the edge, image segmentation algorithms based on the region, image segmentation algorithms based on artificial neural network technology, image segmentation algorithms based on contour model and image segmentation algorithm based on statistical major segmentation algorithm and so on. Finally, the development trend of medical image segmentation algorithms is discussed.

A Robust and Fast System for CTC Computer-Aided Detection of Colorectal Lesions

We present a complete, end-to-end computer-aided detection (CAD) system for identifying lesions in the colon, imaged with computed tomography (CT). This system includes facilities for colon segmentation, candidate generation, feature analysis, and classification. The algorithms have been designed to offer robust performance to variation in image data and patient preparation. By utilizing efficient 2D and 3D processing, software optimizations, multi-threading, feature selection, and an optimized cascade classifier, the CAD system quickly determines a set of detection marks. The colon CAD system has been validated on the largest set of data to date, and demonstrates excellent performance, in terms of its high sensitivity, low false positive rate, and computational efficiency.

Efficient Computer-Aided Detection of Ground-Glass Opacity Nodules in Thoracic CT Images

In this paper, an efficient compute-aided detection method is proposed for detecting ground-glass opacity (GGO) nodules in thoracic CT images. GGOs represent a clinically important type of lung nodule which are ignored by many existing CAD systems. Anti-geometric diffusion is used as preprocessing to remove image noise. Geometric shape features (such as shape index and dot enhancement), are calculated for each voxel within the lung area to extract potential nodule concentrations. Rule based filtering is then applied to remove false positive regions. The proposed method has been validated on a clinical dataset of 50 thoracic CT scans that contains 52 GGO nodules. A total of 48 nodules were correctly detected and resulted in an average detection rate of 92.3%, with the number of false positives at approximately 12.7/scan (0.07/slice). The high detection performance of the method suggested promising potential for clinical applications.

Automatic graph cut segmentation of lesions in CT using mean shift superpixels

This paper presents a new, automatic method of accurately extracting lesions from CT data. It first determines, at each voxel, a five-dimensional (5D) feature vector that contains intensity, shape index, and 3D spatial location. Then, nonparametric mean shift clustering forms superpixels from these 5D features, resulting in an oversegmentation of the image. Finally, a graph cut algorithm groups the superpixels using a novel energy formulation that incorporates shape, intensity, and spatial features. The mean shift superpixels increase the robustness of the result while reducing the computation time. We assume that the lesion is part spherical, resulting in high shape index values in a part of the lesion. From these spherical subregions, foreground and background seeds for the graph cut segmentation can be automatically obtained. The proposed method has been evaluated on a clinical CT dataset. Visual inspection on different types of lesions (lung nodules and colonic polyps), as well as a quantitative evaluation on 101 solid and 80 GGO nodules, both demonstrate the potential of the proposed method. The joint spatial-intensity-shape features provide a powerful cue for successful segmentation of lesions adjacent to structures of similar intensity but different shape, as well as lesions exhibiting partial volume effect.

Reduction of False Positives in Polyp Detection Using Weighted Support Vector Machines

Colorectal cancer is the third highest cause of cancer deaths in US (2007). Early detection and treatment of colon cancer can significantly improve patient prognosis. Manual identification of polyps by radiologists using CT colonography can be labour intensive due to the increasing size of datasets and is error prone due to the complexity of the anatomical structures. There has been increasing interest in computer aided detection (CAD) systems for detecting polyps using CT colonography. For a typical CAD system two major steps can be identified. In the first step image processing techniques are used to detect potential polyp candidates. Many non-polyps are inevitably found in this process. The second step attempts to discount the non-polyp candidates while maintaining true polyps. In practice this is a challenging task as training data is heavily imbalanced, that is, non-polyps dominate the data. This paper describes how the weighted support vector machine (weighted-SVM) can be used to tackle the problem effectively. The weighted-SVM generalises the traditional SVM by applying different penalties to different classes. This trains the classifier to give favour to the most weighted class (in this case true polyps). In this paper the method was applied to data obtained from the intermediate results from a CAD system, originally applied to 209 cases. The results show that the weighted-SVM can play an important role in CAD algorithms for colorectal polyps.

Learning from imbalanced data: a comparative study for colon CAD

Classification plays an important role in the reduction of false positives in many computer aided detection and diagnosis methods. The difficulty of classifying polyps lies in the variation of possible polyp shapes and sizes and the imbalance between the number of polyp and non-polyp regions available in the training data. CAD schemes for medical applications demand high levels of sensitivity even at the expense of keeping a certain number of false positives. In this paper, we investigate some state-of-the-art solutions to the imbalanced data problem: Synthetic Minority Over-sampling Technique (SMOTE) and weighted Support Vector Machines (SVM). We tested these methods using a diverse database of CT colonography, which included a wide spectrum of dificult cases to detect polyps. We performed several experiments with different combinations of over-sampling techniques on training data. The results demonstrated that SVMs have achieved much better performance over C4.5 with different over-sampling techniques. Also, the results show that weighted SVM without over-sampling can achieve comparable performance in terms of sensitivity and specificity to conventional SVM combined with the over-sampling approach.

Feature selection for computer-aided polyp detection using MRMR

In building robust classifiers for computer-aided detection (CAD) of lesions, selection of relevant features is of fundamental importance. Typically one is interested in determining which, of a large number of potentially redundant or noisy features, are most discriminative for classification. Searching all possible subsets of features is impractical computationally. This paper proposes a feature selection scheme combining AdaBoost with the Minimum Redundancy Maximum Relevance (MRMR) to focus on the most discriminative features. A fitness function is designed to determine the optimal number of features in a forward wrapper search. Bagging is applied to reduce the variance of the classifier and make a reliable selection. Experiments demonstrate that by selecting just 11 percent of the total features, the classifier can achieve better prediction on independent test data compared to the 70 percent of the total features selected by AdaBoost.

Image segmentation using joint spatial-intensity-shape features: application to CT lung nodule segmentation

Automatic segmentation of medical images is a challenging problem due to the complexity and variability of human anatomy, poor contrast of the object being segmented, and noise resulting from the image acquisition process. This paper presents a novel feature-guided method for the segmentation of 3D medical lesions. The proposed algorithm combines 1) a volumetric shape feature (shape index) based on high-order partial derivatives; 2) mean shift clustering in a joint spatial-intensity-shape (JSIS) feature space; and 3) a modified expectation-maximization (MEM) algorithm on the mean shift mode map to merge the neighboring regions (modes). In such a scenario, the volumetric shape feature is integrated into the process of the segmentation algorithm. The joint spatial-intensity-shape features provide rich information for the segmentation of the anatomic structures or lesions (tumors). The proposed method has been evaluated on a clinical dataset of thoracic CT scans that contains 68 nodules. A volume overlap ratio between each segmented nodule and the ground truth annotation is calculated. Using the proposed method, the mean overlap ratio over all the nodules is 0.80. On visual inspection and using a quantitative evaluation, the experimental results demonstrate the potential of the proposed method. It can properly segment a variety of nodules including juxta-vascular and juxta-pleural nodules, which are challenging for conventional methods due to the high similarity of intensities between the nodules and their adjacent tissues. This approach could also be applied to lesion segmentation in other anatomies, such as polyps in the colon.

Simultaneous feature selection and classification based on genetic algorithms: an application to colonic polyp detection

Selecting a set of relevant features is a crucial step in the process of building robust classifiers. Searching all possible subsets of features is computationally impractical for large number of features. Generally, classifiers are used for the evaluation of the separability of a certain feature subset. The performance of these classifiers depends on some predefined parameters. However, the choice of these parameters for a given classifier is influenced by the given feature subset and vice versa. The computational cost for feature selection would be largely increased by including the selection of optimal parameters for the classifier (for each subset). This paper attempts to tackle the problem by introducing genetic algorithms (GAs) to combine the processes. The proposed approach can choose the most relevant features from a feature set whilst simultaneously optimising the parameters of the classifier. Its performance was tested on a colon polyp database from a cohort study using a weighted support vector machine (SVM) classifier. As a general approach, other classifiers such as artificial neural networks (ANN) and decision trees could be used. This approach could also be applied to other classification problems such as other computer aided detection/diagnosis applications.