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.

No abstract

For CD in RRD, related factors include BCVA, IOP, lens status, refractive error, extent of retinal detachment, number of holes, and macular hole. Larger extent of retinal detachment, high myopia, and low IOP are significant and independent risk factors.

Computed tomographic colonography (CTC) has been developed for screening of colon cancer. Flattening the three-dimensional (3D) colon wall into two-dimensional (2D) image is believed to (1) provide supplementary information to the endoscopic views and further (2) facilitate colon registration, taniae coli (TC) detection, and haustral fold segmentation. Though the previously-used conformal mapping-based flattening methods can preserve the angular geometry, they have the limitations in providing accurate information of the 3D inner colon wall due to the lack of undulating topography. In this paper, we present a novel colon-wall flattening method using a strategy of 2.5D approach. Coupling with the conformal flattening model, the presented new approach builds an elevation distance map to depict the neighborhood characteristics of the inner colon wall. We validated the new method via two CTC applications: TC detection and haustral fold segmentation. Experimental results demonstrated the effectiveness of our strategy for CTC studies.