Fangfang Han

Fast and Adaptive Detection of Pulmonary Nodules in Thoracic CT Images Using a Hierarchical Vector Quantization Scheme

Computer-aided detection (CADe) of pulmonary nodules is critical to assisting radiologists in early identification of lung cancer from computed tomography (CT) scans. This paper proposes a novel CADe system based on a hierarchical vector quantization (VQ) scheme. Compared with the commonly-used simple thresholding approach, the high-level VQ yields a more accurate segmentation of the lungs from the chest volume. In identifying initial nodule candidates (INCs) within the lungs, the low-level VQ proves to be effective for INCs detection and segmentation, as well as computationally efficient compared to existing approaches. False-positive (FP) reduction is conducted via rule-based filtering operations in combination with a feature-based support vector machine classifier. The proposed system was validated on 205 patient cases from the publically available online Lung Image Database Consortium database, with each case having at least one juxta-pleural nodule annotation. Experimental results demonstrated that our CADe system obtained an overall sensitivity of 82.7% at a specificity of 4 FPs/scan. Especially for the performance on juxta-pleural nodules, we observed 89.2% sensitivity at 4.14 FPs/scan. With respect to comparable CADe systems, the proposed system shows outperformance and demonstrates its potential for fast and adaptive detection of pulmonary nodules via CT imaging.

A new 3D texture feature based computer-aided diagnosis approach to differentiate pulmonary nodules

To distinguish malignant pulmonary nodules from benign ones is of much importance in computer-aided diagnosis of lung diseases. Compared to many previous methods which are based on shape or growth assessing of nodules, this proposed three-dimensional (3D) texture feature based approach extracted fifty kinds of 3D textural features from gray level, gradient and curvature co-occurrence matrix, and more derivatives of the volume data of the nodules. To evaluate the presented approach, the Lung Image Database Consortium public database was downloaded. Each case of the database contains an annotation file, which indicates the diagnosis results from up to four radiologists. In order to relieve partial-volume effect, interpolation process was carried out to those volume data with image slice thickness more than 1mm, and thus we had categorized the downloaded datasets to five groups to validate the proposed approach, one group of thickness less than 1mm, two types of thickness range from 1mm to 1.25mm and greater than 1.25mm (each type contains two groups, one with interpolation and the other without). Since support vector machine is based on statistical learning theory and aims to learn for predicting future data, so it was chosen as the classifier to perform the differentiation task. The measure on the performance was based on the area under the curve (AUC) of Receiver Operating Characteristics. From 284 nodules (122 malignant and 162 benign ones), the validation experiments reported a mean of 0.9051 and standard deviation of 0.0397 for the AUC value on average over 100 randomizations.

Vector quantization-based automatic detection of pulmonary nodules in thoracic CT images

Computer-aided detection (CADe) of pulmonary nodules from computer tomography (CT) scans is critical for assisting radiologists to identify lung lesions at an early stage. In this paper, we propose a novel CADe system for lung nodule detection based on a vector quantization (VQ) approach. Compared to existing CADe systems, the extraction of lungs from the chest CT image is fully automatic, and the detection and segmentation of initial nodule candidates (INCs) within the lung volume is fast and accurate due to the self-adaptive nature of VQ algorithm. False positives in the detected INCs are reduced by rule-based pruning in combination with a feature-based support vector machine classifier. We validate the proposed approach on 60 CT scans from a publicly available database. Preliminary results show that our CADe system is effective to detect nodules with a sensitivity of 90.53 % at a specificity level of 86.00%.

Efficient 3D texture feature extraction from CT images for computer-aided diagnosis of pulmonary nodules

Texture feature from chest CT images for malignancy assessment of pulmonary nodules has become an un-ignored and efficient factor in Computer-Aided Diagnosis (CADx). In this paper, we focus on extracting as fewer as needed efficient texture features, which can be combined with other classical features (e.g. size, shape, growing rate, etc.) for assisting lung nodule diagnosis. Based on a typical calculation algorithm of texture features, namely Haralick features achieved from the gray-tone spatial-dependence matrices, we calculated two dimensional (2D) and three dimensional (3D) Haralick features from the CT images of 905 nodules. All of the CT images were downloaded from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), which is the largest public chest database. 3D Haralick feature model of thirteen directions contains more information from the relationships on the neighbor voxels of different slices than 2D features from only four directions. After comparing the efficiencies of 2D and 3D Haralick features applied on the diagnosis of nodules, principal component analysis (PCA) algorithm was used to extract as fewer as needed efficient texture features. To achieve an objective assessment of the texture features, the support vector machine classifier was trained and tested repeatedly for one hundred times. And the statistical results of the classification experiments were described by an average receiver operating characteristic (ROC) curve. The mean value (0.8776) of the area under the ROC curves in our experiments can show that the two extracted 3D Haralick projected features have the potential to assist the classification of benign and malignant nodules.

A shape constrained MAP-EM algorithm for colorectal segmentation

The task of effectively segmenting colon areas in CT images is an important area of interest in medical imaging field. The ability to distinguish the colon wall in an image from the background is a critical step in several approaches for achieving larger goals in automated computer-aided diagnosis (CAD). The related task of polyp detection, the ability to determine which objects or classes of polyps are present in a scene, also relies on colon wall segmentation. When modeling each tissue type as a conditionally independent Gaussian distribution, the tissue mixture fractions in each voxel via the modeled unobservable random processes of the underlying tissue types can be estimated by maximum a posteriori expectation-maximization (MAP-EM) algorithm in an iterative manner. This paper presents, based on the assumption that the partial volume effect (PVE) could be fully described by a tissue mixture model, a theoretical solution to the MAP-EM segmentation algorithm. However, the MAP-EM algorithm may miss some small regions which also belong to the colon wall. Combining with the shape constrained model, we present an improved algorithm which is able to merge similar regions and reserve fine structures. Experiment results show that the new approach can refine the jagged-like boundaries and achieve better results than merely exploited our previously presented MAP-EM algorithm.

A hybrid CNN feature model for pulmonary nodule malignancy risk differentiation

The malignancy risk differentiation of pulmonary nodule is one of the most challenge tasks of computer-aided diagnosis (CADx). Most recently reported CADx methods or schemes based on texture and shape estimation have shown relatively satisfactory on differentiating the risk level of malignancy among the nodules detected in lung cancer screening. However, the existing CADx schemes tend to detect and analyze characteristics of pulmonary nodules from a statistical perspective according to local features only. Enlightened by the currently prevailing learning ability of convolutional neural network (CNN), which simulates human neural network for target recognition and our previously research on texture features, we present a hybrid model that takes into consideration of both global and local features for pulmonary nodule differentiation using the largest public database founded by the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). By comparing three types of CNN models in which two of them were newly proposed by us, we observed that the multi-channel CNN model yielded the best discrimination in capacity of differentiating malignancy risk of the nodules based on the projection of distributions of extracted features. Moreover, CADx scheme using the new multi-channel CNN model outperformed our previously developed CADx scheme using the 3D texture feature analysis method, which increased the computed area under a receiver operating characteristic curve (AUC) from 0.9441 to 0.9702.

A Hybrid CNN Feature Model for Pulmonary Nodule Differentiation Task

Pulmonary nodule differentiation is one of the most challenge tasks of computer-aided diagnosis(CADx). Both texture method and shape estimation approaches previously presented could provide good performance to some extent in the literature. However, no matter 2D or 3D textures extracted, they just tend to observe characteristics of the pulmonary nodules from a statistical perspective according to local features’ change, which hints they are helpless to work as global as the human who always be aware of the characteristics of given target as a combination of local features and global features, thus they have certain limitations. Enlightened by the currently prevailing learning ability of convolutional neural network (CNN) and previously contributions provided by texture features, we here presented a hybrid method for better to complete the differentiation task. It can be observed that our proposed multi-channel CNN model has a better discrimination in capacity according to the projection of distributions of extracted features and achieved a new record with AUC 97.04 on LIDC-IDRI database.

An improved high order texture features extraction method with application to pathological diagnosis of colon lesions for CT colonography

Differentiation of colon lesions according to underlying pathology, e.g., neoplastic and non-neoplastic, is of fundamental importance for patient management. Image intensity based textural features have been recognized as a useful biomarker for the differentiation task. In this paper, we introduce high order texture features, beyond the intensity, such as gradient and curvature, for that task. Based on the Haralick texture analysis method, we introduce a virtual pathological method to explore the utility of texture features from high order differentiations, i.e., gradient and curvature, of the image intensity distribution. The texture features were validated on database consisting of 148 colon lesions, of which 35 are non-neoplastic lesions, using the random forest classifier and the merit of area under the curve (AUC) of the receiver operating characteristics. The results show that after applying the high order features, the AUC was improved from 0.8069 to 0.8544 in differentiating non-neoplastic lesion from neoplastic ones, e.g., hyperplastic polyps from tubular adenomas, tubulovillous adenomas and adenocarcinomas. The experimental results demonstrated that texture features from the higher order images can significantly improve the classification accuracy in pathological differentiation of colorectal lesions. The gain in differentiation capability shall increase the potential of computed tomography (CT) colonography for colorectal cancer screening by not only detecting polyps but also classifying them from optimal polyp management for the best outcome in personalized medicine.

A feasibility study of high order texture features with application to pathological diagnosis of colon lesions for CT Colonography

Differentiation of colon lesions into different pathological phases, e.g., neoplastic and non-neoplastic, is of fundamental importance for patient management. Image intensity-based textural features have been recognized as a useful biomarker for the differentiation task. In this paper, we introduce high order texture features, beyond the intensity, such as gradient and curvature, for that task. We expand the 2D Haralick model to 3D and extract texture feature from high order 3D images. These texture features from image intensity, gradient, and curvature were validated on a database, which consists of 148 lesions where 35 are non-neoplastic and 113 are neoplastic lesion, using the well-known support vector machine (SVM) classifier and the merit of area under the ROC curve (AUC). The AUC of classification was improved from 0.74 (by the use of the image intensity-alone) to 0.85 (by also considering the gradient and curvature images) in differentiating the non-neoplastic lesions from neoplastic ones, e.g., the hyperplastic polyps from the tubular adenoma, tubulovillous adenoma and adenocarcinoma lesions. The experimental results demonstrated that texture features from high order images can significantly improve the classification accuracy in differentiating benign from malignant colon lesions.