Search

Accurate diagnosis of metastatic cancer is essential for prescribing optimal control strategies to halt further spread of metastasizing disease. While pathological inspection aided by immunohistochemistry staining provides a valuable gold standard for clinical diagnostics, deep learning methods have emerged as powerful tools for identifying clinically relevant features of whole slide histology relevant to a tumor’s metastatic origin. Although deep learning models require significant training data to learn effectively, transfer learning paradigms provide mechanisms to circumvent limited training data by first training a model on related data prior to fine-tuning on smaller data sets of interest. In this work we propose a transfer learning approach that trains a convolutional neural network to infer the metastatic origin of tumor tissue from whole slide images of hematoxylin and eosin (H&E) stained tissue sections and illustrate the advantages of pre-training network on whole slide images of primary tumor morphology. We further characterize statistical dissimilarity between primary and metastatic tumors of various indications on patch-level images to highlight limitations of our indication-specific transfer learning approach. Using a primary-to-metastatic transfer learning approach, we achieved mean class-specific areas under receiver operator characteristics curve (AUROC) of 0.779, which outperformed comparable models trained on only images of primary tumor (mean AUROC of 0.691) or trained on only images of metastatic tumor (mean AUROC of 0.675), supporting the use of large scale primary tumor imaging data in developing computer vision models to characterize metastatic origin of tumor lesions.

The cloud paradigm, based on the idea of delegating to the network any kind of computational resources, is showing a considerable success. The estimated trend is that the number of different cloud-based solutions, approaches, and service providers (CSP) will continue growing. Despite the big number of different cloud solutions that currently exist, most of them are "walled gardens" unable to interoperate. On the other side, a large effort is taking place in the cloud community to develop and identify open solutions and standards. In such a context the concept of cloud federation, an architecture that combines the functionalities of different CSP, is a hot topic. This chapter presents an overview of the cloud federation topic, with special focus on its most important security challenges. Furthermore, it proposes a taxonomy of possible approaches to federation. Then it proposes a comparison of security problems in cloud and grid environment, and a detailed analysis of two relevant security problems, identity management and Cyber Attacks analysis, trying to outline how they can be applied in a federated context. © 2012, IGI Global.