Jimmy C. Azar

Automated classification of glandular tissue by statistical proximity sampling

Due to the complexity of biological tissue and variations in staining procedures, features that are based on the explicit extraction of properties from subglandular structures in tissue images may have difficulty generalizing well over an unrestricted set of images and staining variations. We circumvent this problem by an implicit representation that is both robust and highly descriptive, especially when combined with a multiple instance learning approach to image classification. The new feature method is able to describe tissue architecture based on glandular structure. It is based on statistically representing the relative distribution of tissue components around lumen regions, while preserving spatial and quantitative information, as a basis for diagnosing and analyzing different areas within an image. We demonstrate the efficacy of the method in extracting discriminative features for obtaining high classification rates for tubular formation in both healthy and cancerous tissue, which is an important component in Gleason and tubule-based Elston grading. The proposed method may be used for glandular classification, also in other tissue types, in addition to general applicability as a region-based feature descriptor in image analysis where the image represents a bag with a certain label (or grade) and the region-based feature vectors represent instances.

Histological stain evaluation for machine learning applications

Aims: A methodology for quantitative comparison of histological stains based on their classification and clustering performance, which may facilitate the choice of histological stains for automatic pattern and image analysis. Background: Machine learning and image analysis are becoming increasingly important in pathology applications for automatic analysis of histological tissue samples. Pathologists rely on multiple, contrasting stains to analyze tissue samples, but histological stains are developed for visual analysis and are not always ideal for automatic analysis. Materials and Methods: Thirteen different histological stains were used to stain adjacent prostate tissue sections from radical prostatectomies. We evaluate the stains for both supervised and unsupervised classification of stain/tissue combinations. For supervised classification we measure the error rate of nonlinear support vector machines, and for unsupervised classification we use the Rand index and the F-measure to assess the clustering results of a Gaussian mixture model based on expectation-maximization. Finally, we investigate class separability measures based on scatter criteria. Results: A methodology for quantitative evaluation of histological stains in terms of their classification and clustering efficacy that aims at improving segmentation and color decomposition. We demonstrate that for a specific tissue type, certain stains perform consistently better than others according to objective error criteria. Conclusions: The choice of histological stain for automatic analysis must be based on its classification and clustering performance, which are indicators of the performance of automatic segmentation of tissue into morphological components, which in turn may be the basis for diagnosis.

Automated Tracking of the Carotid Artery in Ultrasound Image Sequences Using a Self Organizing Neural Network

An automated method for the segmentation and tracking of moving vessel walls in 2D ultrasound image sequences is introduced. The method was tested on simulated and real ultrasound image sequences of the carotid artery. Tracking was achieved via a self organizing neural network known as Growing Neural Gas. This topology-preserving algorithm assigns a net of nodes connected by edges that distributes itself within the vessel walls and adapts to changes in topology with time. The movement of the nodes was analyzed to uncover the dynamics of the vessel wall. By this way, radial and longitudinal strain and strain rates have been estimated. Finally, wave intensity signals were computed from these measurements. The method proposed improves upon wave intensity wall analysis, WIWA, and opens up a possibility for easy and efficient analysis and diagnosis of vascular disease through noninvasive ultrasonic examination.

Microarray Core Detection by Geometric Restoration

Whole-slide imaging of tissue microarrays (TMAs) holds the promise of automated image analysis of a large number of histopathological samples from a single slide. This demands high-throughput image processing to enable analysis of these tissue samples for diagnosis of cancer and other conditions. In this paper, we present a completely automated method for the accurate detection and localization of tissue cores that is based on geometric restoration of the core shapes without placing any assumptions on grid geometry. The method relies on hierarchical clustering in conjunction with the Davies-Bouldin index for cluster validation in order to estimate the number of cores in the image wherefrom we estimate the core radius and refine this estimate using morphological granulometry. The final stage of the algorithm reconstructs circular discs from core sections such that these discs cover the entire region of each core regardless of the precise shape of the core. The results show that the proposed method is able to reconstruct core locations without any evidence of localization. Furthermore, the algorithm is more efficient than existing methods based on the Hough transform for circle detection. The algorithm’s simplicity, accuracy, and computational efficiency allow for automated high-throughput analysis of microarray images.

Automatic characterization of the physiological condition of the carotid artery in 2D ultrasound image sequences using spatiotemporal and spatiospectral 2D maps

A novel method for characterizing and visualizing the progression of waves along the walls of the carotid artery is presented. The new approach is noninvasive and able to simultaneously capture the spatial and the temporal propagation of wavy patterns along the walls of the carotid artery in a completely automated manner. Spatiotemporal and spatiospectral 2D maps describing these patterns (in both the spatial and the frequency domains, resp.) were generated and analyzed by visual inspection as well as automatic feature extraction and classification. Three categories of cases were considered: pathological elderly, healthy elderly, and healthy young cases. Automatic differentiation, between cases of these three categories, was achieved with a sensitivity of 97.1% and a specificity of 74.5%. Two features were proposed and computed to measure the homogeneity of the spatiospectral 2D map which presents the spectral characteristics of the carotid artery walls wavy motion pattern which are related to the physical, mechanical (e.g., elasticity), and physiological properties and conditions along the artery. These results are promising and confirm the potential of the proposed method in providing useful information which can help in revealing the physiological condition of the cardiovascular system.