Advancing Bag-of-visual-words Representations For Lesion Classification In Retinal Images.

Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2 ± 2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors.

Chronic Continuous Exenatide Infusion Does Not Cause Pancreatic Inflammation And Ductal Hyperplasia In Non-human Primates.

In this study, we aimed to evaluate the effects of exenatide (EXE) treatment on exocrine pancreas of nonhuman primates. To this end, 52 baboons (Papio hamadryas) underwent partial pancreatectomy, followed by continuous infusion of EXE or saline (SAL) for 14 weeks. Histological analysis, immunohistochemistry, Computer Assisted Stereology Toolbox morphometry, and immunofluorescence staining were performed at baseline and after treatment. The EXE treatment did not induce pancreatitis, parenchymal or periductal inflammatory cell accumulation, ductal hyperplasia, or dysplastic lesions/pancreatic intraepithelial neoplasia. At study end, Ki-67-positive (proliferating) acinar cell number did not change, compared with baseline, in either group. Ki-67-positive ductal cells increased after EXE treatment (P = 0.04). However, the change in Ki-67-positive ductal cell number did not differ significantly between the EXE and SAL groups (P = 0.13). M-30-positive (apoptotic) acinar and ductal cell number did not change after SAL or EXE treatment. No changes in ductal density and volume were observed after EXE or SAL. Interestingly, by triple-immunofluorescence staining, we detected c-kit (a marker of cell transdifferentiation) positive ductal cells co-expressing insulin in ducts only in the EXE group at study end, suggesting that EXE may promote the differentiation of ductal cells toward a β-cell phenotype. In conclusion, 14 weeks of EXE treatment did not exert any negative effect on exocrine pancreas, by inducing either pancreatic inflammation or hyperplasia/dysplasia in nonhuman primates.