Stelios C. Orphanoudakis

An open, component-based information infrastructure for integrated health information networks

A fundamental requirement for achieving continuity of care is the seamless sharing of multimedia clinical information. Different technological approaches can be adopted for enabling the communication and sharing of health record segments. In the context of the emerging global information society, the creation of and access to the integrated electronic health record (I-EHR) of a citizen has been assigned high priority in many countries. This requirement is complementary to an overall requirement for the creation of a health information infrastructure (HII) to support the provision of a variety of health telematics and e-health services. In developing a regional or national HII, the components or building blocks that make up the overall information system ought to be defined and an appropriate component architecture specified. This paper discusses current international priorities and trends in developing the HII. It presents technological challenges and alternative approaches towards the creation of an I-EHR, being the aggregation of health data created during all interactions of an individual with the healthcare system. It also presents results from an ongoing Research and Development (R&D) effort towards the implementation of the HII in HYGEIAnet, the regional health information network of Crete, Greece, using a component-based software engineering approach. Critical design decisions and related trade-offs, involved in the process of component specification and development, are also discussed and the current state of development of an I-EHR service is presented. Finally, Human Computer Interaction (HCI) and security issues, which are important for the deployment and use of any I-EHR service, are considered.

Robot Homing by Exploiting Panoramic Vision

We propose a novel, vision-based method for robot homing, the problem of computing a route so that a robot can return to its initial “home” position after the execution of an arbitrary “prior” path. The method assumes that the robot tracks visual features in panoramic views of the environment that it acquires as it moves. By exploiting only angular information regarding the tracked features, a local control strategy moves the robot between two positions, provided that there are at least three features that can be matched in the panoramas acquired at these positions. The strategy is successful when certain geometric constraints on the configuration of the two positions relative to the features are fulfilled. In order to achieve long-range homing, the features’ trajectories are organized in a visual memory during the execution of the “prior” path. When homing is initiated, the robot selects Milestone Positions (MPs) on the “prior” path by exploiting information in its visual memory. The MP selection process aims at picking positions that guarantee the success of the local control strategy between two consecutive MPs. The sequential visit of successive MPs successfully guides the robot even if the visual context in the “home” position is radically different from the visual context at the position where homing was initiated. Experimental results from a prototype implementation of the method demonstrate that homing can be achieved with high accuracy, independent of the distance traveled by the robot. The contribution of this work is that it shows how a complex navigational task such as homing can be accomplished efficiently, robustly and in real-time by exploiting primitive visual cues. Such cues carry implicit information regarding the 3D structure of the environment. Thus, the computation of explicit range information and the existence of a geometric map are not required.

Matching disparate views of planar surfaces using projective invariants

Feature matching is a prerequisite to a wide variety of vision tasks. This paper presents a method that addresses the problem of matching two views of coplanar points and lines in a unified manner. The views to be matched are assumed to have been acquired from disparate, i.e. very different viewpoints. By employing a randomized search strategy combined with the two-line two-point projective invariant, the proposed method is able to derive small sets of possibly matching points and lines. These candidate matches are then verified by recovering the associated plane homography, which is further used to predict more matches. The resulting scheme is capable of successfully matching features extracted from views that differ considerably, even in the presence of large numbers of outlying features. Experimental results from the application of the method to indoor and aerial images indicate its effectiveness and robustness. q 2000 Elsevier Science B.V. All rights reserved.

I2Cnet: Content-based similarity search in geographically distributed repositories of medical images

The retrieval of images by content is rapidly gaining acceptance as an important function of image database systems. This paper discusses the architecture of I2Cnet, a network of servers which provide content-based query services through a WWW browser. In I2Cnet, algorithms for the representation, storage, and retrieval of medical images based on different descriptions of image content are implemented using description types. AttributeMatch, a description type supported by I2Cnet, aims to capture the knowledge of medical experts in queries by using a similarity criterion which can be tailored to user preferences. We present results showing the query response time of AttributeMatch, obtained with image classes of various sizes, and the degree of similarity of retrieved images to the query image under different similarity criteria.

I2C: a system for the indexing, storage, and retrieval of medical images by content.

Image indexing, storage, and retrieval based on pictorial content is a feature of image database systems which is becoming of increasing importance in many application domains. Medical image database systems, which support the retrieval of images generated by different modalities based on their pictorial content, will provide added value to future generation picture archiving and communication systems (PACS), and can be used as a diagnostic decision support tools and as a tool for medical research and training. We present the architecture and features of I2C, a system for the indexing, storage, and retrieval of medical images by content. A unique design feature of this architecture is that it also serves as a platform for the implementation and performance evaluation of image description methods and retrieval strategies. I2C is a modular and extensible system, which has been developed based on object-oriented principles. It consists of a set of cooperating modules which facilitate the addition of new graphical tools, image description and matching algorithms. These can be incorporated into the system at the application level. The core concept of I2C is an image class hierarchy. Image classes encapsulate different segmentation and image content description algorithms. Medical images are assigned to image classes based on a set of user-defined attributes such as imaging modality, type of study, anatomical characteristics, etc. This class-based treatment of images in the I2C system achieves increased accuracy and efficiency of content-based retrievals, by limiting the search space and allowing specific algorithms to be fine-tuned for images acquired by different modalities or representing different parts of the anatomy.

Methodology for the representation, indexing and retrieval of images by content

Abstract This paper considers the requirements for the design and implementation of an image database system which supports the storage and retrieval of images by content. Attention is focused on a specific methodology for the efficient representation, indexing and retrieval of images based on spatial relationships and properties of objects. Images are first decomposed into groups of objects and are indexed by computing addresses to all such groups. This methodology supports the efficient processing of queries by image example, and avoids exhaustive searching through the entire image database. The performance of an image database system using the above methodology has been evaluated based on simulated images, as well as images obtained with computed tomography and magnetic resonance imaging. The results of this evaluation are presented and discussed.

WebOnCOLL: medical collaboration in regional healthcare networks

Presents WebOnCOLL, a World Wide Web-based medical collaboration environment, which has been designed in the context of the regional healthcare network of Crete. WebOnCOLL employs the infrastructure of regional healthcare networks to provide integrated services for virtual workspaces, annotations, e-mail and online collaboration. Virtual workspaces support collaborative concepts like personal Web pages, bulletin boards, discussion lists, shared workspaces and medical case folders. Annotations provide a natural way for people to interact with multimedia content, while e-mail is one of the most popular forms of communication today. Online collaboration satisfies the need for a more direct form of communication.

Visual Detection of Obstacles Assuming a Locally Planar Ground

Obstacle avoidance is an essential capability of an autonomous robot. This paper presents a method that enables a mobile robot to locate obstacles in its field of view using two images of its surroundings. The method is based on the assumption that the robot is moving on a locally planar ground. Using a set of point features (corners) that have been matched between the two views using normalized cross-correlation, a robust estimate of the homography of the ground is computed. Knowledge of this homography permits us to compensate for the motion of the ground and to detect obstacles as areas in the image that appear nonstationary after the motion compensation. The resulting method does not require camera calibration, is applicable either to stereo pairs or to motion sequence images, does not rely on a dense disparity/flow field and circumvents the 3D reconstruction problem. Experimental results from the application of the method on real images indicate that it is both effective and robust.

Detecting Planes In An Uncalibrated Image Pair.

Plane detection is a prerequisite to a wide variety of vision tasks. This paper proposes a novel method that exploits results from projective geometry to automatically detect planes using two images. Using a set of point and line features that have been matched between images, the method exploits the fact that every pair of a 3D line and a 3D point defines a plane and utilizes an iterative voting scheme for identifying coplanar subsets of the employed feature set. The method does not require camera calibration, circumvents the 3D reconstruction problem, is robust to the existence of mismatched features and is applicable either to stereo or motion sequence images. Sample results from the application of the proposed method to real imagery are also provided.

Robot homing based on corner tracking in a sequence of panoramic images

In robotics, homing can be defined as that behavior which enables a robot to return to its initial (home) position, after traveling a certain distance along an arbitrary path. Odometry has traditionally been used for the implementation of such a behavior, but it has been shown to be an unreliable source of information. In this work, a novel method for visual homing is proposed, based on a panoramic camera. As the robot departs from its initial position, it tracks characteristic features of the environment (corners). As soon as homing is activated, the robot selects intermediate target positions on the original path. These intermediate positions (IPs) are then visited sequentially, until the home position is reached. For the robot to move between two consecutive IPs, it is only required to establish correspondence among at least three corners. This correspondence is obtained through a feature tracking mechanism. The proposed homing scheme is based on the extraction of very low-level sensory information, namely the bearing angles of corners, and has been implemented on a robotic platform. Experimental results show that the proposed scheme achieves homing with a remarkable accuracy, which is not affected by the distance traveled by the robot.