Chris Bailey

Haoliang Sun, Xiantong Zhen, Chris Bailey et al.

The Cobb angle that quantitatively evaluates the spinal curvature plays an important role in the scoliosis diagnosis and treatment. Conventional measurement of these angles suffers from huge variability and low reliability due to intensive manual intervention. However, since there exist high ambiguity and variability around boundaries of vertebrae, it is challenging to obtain Cobb angles automatically. In this paper, we formulate the estimation of the Cobb angles from spinal X-rays as a multi-output regression task. We propose structured support vector regression (S^2VR) to jointly estimate Cobb angles and landmarks of the spine in X-rays in one single framework. The proposed S^2VR can faithfully handle the nonlinear relationship between input images and quantitative outputs, while explicitly capturing the intrinsic correlation of outputs. We introduce the manifold regularization to exploit the geometry of the output space. We propose learning the kernel in S2VR by kernel target alignment to enhance its discriminative ability. The proposed method is evaluated on the spinal X-rays dataset of 439 scoliosis subjects, which achieves the inspiring correlation coefficient of 92.76% with ground truth obtained manually by human experts and outperforms two baseline methods. Our method achieves the direct estimation of Cobb angles with high accuracy, which indicates its great potential in clinical use.

Lionel Montrieux, Rogerio de Lemos, Chris Bailey

As organisations expand and interconnect, authorisation infrastructures become increasingly difficult to manage. Several solutions have been proposed, including self-adaptive authorisation, where the access control policies are dynamically adapted at run-time to respond to misuse and malicious behaviour. The ultimate goal of self-adaptive authorisation is to reduce human intervention, make authorisation infrastructures more responsive to malicious behaviour, and manage access control in a more cost effective way. In this paper, we scope and define the emerging area of self-adaptive authorisation by describing some of its developments, trends and challenges. For that, we start by identifying key concepts related to access control and authorisation infrastructures, and provide a brief introduction to self-adaptive software systems, which provides the foundation for investigating how self-adaptation can enable the enforcement of authorisation policies. The outcome of this study is the identification of several technical challenges related to self-adaptive authorisation, which are classified according to the different stages of a feedback control loop.