Briony Teather

Socio-cognitive engineering: a methodology for the design of human-centred technology

We describe a general methodology, socio-cognitive engineering, for the design of human-centred technology. It integrates software, task, knowledge and organizational engineering and has been refined and tested through a series of projects to develop computer systems to support training and professional work. In this paper we describe the methodology and illustrate its use through a project to develop a computer-based training system for neuro-radiology.

Structured computer-based training in the interpretation of neuroradiological images

Computer-based systems may be able to address a recognised need throughout the medical profession for a more structured approach to training. We describe a combined training system for neuroradiology, the MR Tutor that differs from previous approaches to computer-assisted training in radiology in that it provides case-based tuition whereby the system and user communicate in terms of a well-founded Image Description Language. The system implements a novel method of visualisation and interaction with a library of fully described cases utilising statistical models of similarity, typicality and disease categorisation of cases. We describe the rationale, knowledge representation and design of the system, and provide a formative evaluation of its usability and effectiveness.

Discriminating Multiple Sclerosis from other Diseases of Similar Presentation Can a Formal Description Approach Help

All patients presenting to an MR Imaging Centre during the periods of study, either in 1988 or 1991, have had their records of signs, symptoms and history prior to scanning reviewed, all abnormal MR images archived and an attempt has been made to follow their subsequent course up to the allocation of a confirmed or working diagnosis by their physicians and surgeons. Using a detailed, menu-driven, computer-based dialogue, abnormal images have been described, blind to all other data, in order to identify image features that may be significant in discriminating between diagnoses. This preliminary study addresses the differential diagnosis of multiple sclerosis from cerebrovascular disease, a problem often confounded by the similar multi-centric, multi-episode clinical presentation. Although the numbers starting with similar clinical presentation, with confirmed or working diagnosis at an acceptable level of certainty, and with completed image descriptions are small (45 Multiple Sclerosis, 6 Cerebrovascular disease), there are strong indications that certain MR image features are more helpful than is generally realised. The association of these features during statistical analysis may improve differential diagnostic certainty. Attention is drawn to the detailed appearances of individual lesions, the prevalence of one or more lesion types in individual patients, the sizes of lesions and the association of lesions affecting arcuate fibres with those affecting grey matter.

Standard terminology for MR image description

A glossary of descriptive terms for use in structured reporting in magnetic resonance cerebral images is presented. The glossary characterises lesions in terms of lesion types, shape, geometric qualifiers, intensity content, scales of intensity and associated signs. Anatomical definitions, disease terms and user instructions are also provided. Terminology is being utilised to establish statistical databases that may be utilised to identify combinations of image features that assist in differential diagnosis.

Statistical Modelling and Structured Image Description for Intelligent Tutoring in MR Imaging of the Head

A collaborative research project between the Medical Systems Research Group, De Montfort University Leicester, and the School of Cognitive and Computing Sciences, University of Sussex, is examining the feasibility of utilising statistical-based principles and a structured image description language for tutoring about radiological image interpretation and diagnosis. This paper describes the construction of a sophisticated intelligent tutoring system (ITS) for the interpretation of magnetic resonance images in the diagnosis of cerebral disease. The outcome of the project will be a tutoring system and diagnostic aid for MR images which can be evaluated in a realistic educational setting. An evaluation of the system will show whether computer-assisted tutoring can be effective in supplementing conventional teaching, by teaching a systematic approach to image interpretation and by providing exposure to a large archive of annotated images.

Computer discrimination between diseases of the brain based on MR image features

In attempting to achieve a diagnosis both novice and expert radiologists tend to simplify the process by grouping contending diagnosis candidates into “small worlds” of similar appearance or similar clinical features. Comparing a current undiagnosed case with an archive of image feature descriptors of past cases also provides opportunities for discovering the roles of individual image features in discrimination. Techniques of implementing such potentially rewarding analyses require a standard language of descriptors (an image description language or IDL) that can be used consistently on an archive of cases to blindly describe them without knowledge of the final diagnoses. It is important that the radiological protocols employed should be matched between examples and new cases and that there should be sufficient numbers in the archive to provide statistically convincing data.

Distinguishing Multiple Sclerosis from Cerebrovascular Disease Magnetic Resonance Imaging Considerations

Using defined terms, the features of MR images of brain lesions and abnormalities in multiple sclerosis (MS) and cerebrovascular disease subjects have been described by an observer blind to all other information. Analysis of the descriptions reveals some helpful differentially diagnostic features.