KIDS : A distributed expert system for biomedical image interpretation

Ovalle, Anaelia; Garbay, Catherine

doi:10.1007/bfb0033770

Cited by 12 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The expert possesses visual as well as Our primary goal is to complete the knowledge base of diagnostic skills. The first one consists in identifying cell KIDS (Knowledge-based Image Diagnosis System) [2], a types, by referring to a kind of "mental image bank" in which multi-agent system dedicated to breast carcinoma. KIDS is the expert navigates, and that is entirely personnal.…”

Section: Environment Designmentioning

confidence: 99%

From knowledge modelling to expertise elicitation in cytology

Hugonnard

Garbay

1992

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

This paper deals with the design of a multi-agent knowledge acquisition environment dedicated to cytology. This environment is intended to remain compatible with a robust theory of knowledge and the distributed artificial Intelli gence concepts. The design, based on three coope rating modes (elicitation, presentation and resolu tion), is first of all introduced. Two elicitation forms are then described, which fit the cytological expertise. Finally, the user interface is presented before discussing the main points of the approach. I. IN TRODUCTIONThe contribution of multi-agent approach to complex problem solving, such as cytological image interpretation, has been presented in [1]. Considering knowledge acquisition as a complex problem, we propose to base its modelling on a multi-agent approach. Following a thorough knowledge study, this modelling is based on three cooperative modes of work : elicitation, presentation and resolution. After the description of the environment design, we will present more precisely the elicitation and presentation modes in the context of cytology. The user interface is finally introduced before discussing and concluding. II. ENVIRONMENT DESIGNA. Global modelling from one knowledge model (expert, user or system) to the other. Furthermore, the knowledge study has revealed that several elicitation and presentation styles were needed. Their study has been conducted in the framework of cytology.

show abstract

Section: Environment Designmentioning

confidence: 99%

From knowledge modelling to expertise elicitation in cytology

Hugonnard

Garbay

1992

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

show abstract

“…However, the uncertainty and the errors that are involved in the collection of image data, in particular in the case of cytological images, have resulted in the implementation of a limited number of highly specialised applications that involve the combined use of artificial intelligence techniques [7,6], representation of a priori knowledge [16], or mathematical formulation [5]. Recently systems that use artificial neural networks [4,9] have also been developed.…”

Section: Introductionmentioning

confidence: 99%

Neural network platform for recognizing a sequence of cell images

Psarrou

Buxton

1992

SPIE Proceedings

View full text Add to dashboard Cite

The aim of the research introduced in this paper is to develop a unified neural network platform to model the behaviour of cancerous cells. Neural networks will be used to both extract features from the cell images and control the process for recognising whether a sequence of cell images match the locomotive and social behaviour of a cancerous cell and its probability to metastasize. The problem first tackled is the extraction of cell features from the images as, for example, the centre of the cell. This paper gives an overview of the application and presents the results drawn from two neural network architectures, an "all connected" and a "locally connected" network, used for the extraction of cell centroid areas from images. Both networks are implemented on a Distributed Array of Processors (DAP) and trained using the backpropagation learning algorithm.

show abstract

“…The utilization of this model in the process of system design permits in fact to build robust and reliable systems. The multi-agent system KIDS (Knowledge based Image Diagnosis System) devoted to biomedical im � ge interpretation uses a distributed approach to model medIcal reasoning in cytology [2].…”

Section: Introductionmentioning

confidence: 99%

Towards a formal task model for biomedical diagnosis assistance

Derder

Ovalle

Garbay

1992

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

We describe current research on biomedi cal diagnosis assistance for cytological specimen exploration. The Multi-Agent System KIDS, a sys tem devoted to Biomedical Image Interpretation, is briefly presented and discussed. A second study is then presented, which focus on screening and propose a new task model. This model not only considers the input I output features of a task, as inKIDS, but also takes into account the main para meters implied in the human approach to each task.

show abstract

KIDS : A distributed expert system for biomedical image interpretation

Cited by 12 publications

References 5 publications

From knowledge modelling to expertise elicitation in cytology

From knowledge modelling to expertise elicitation in cytology

Neural network platform for recognizing a sequence of cell images

Towards a formal task model for biomedical diagnosis assistance

Contact Info

Product

Resources

About