Biomedical subjects

Eric Zapletal

Publications and source records attributed to Eric Zapletal.

5 recordsLinked to original sources

PubMed2005

Computation of semantic similarity within an ontology of breast pathology to assist inter-observer consensus.

Computer-assisted consensus in medical imaging involves automatic comparison of morphological abnormalities observed by physicians in images. We built an ontology of morphological abnormalities in breast pathology to assist inter-observer consensus. Concepts of morphological abnormalities extracted from existing terminologies, published grading systems and medical reports were organized in an taxonomic hierarchy and furthermore linked by the relation "is a diagnostic criterion of" according to diagnostic meaning. We implemented position-based, content-based and mixed semantic similarity measures between concepts in this ontology and compared the results with experts' judgment. The position-based similarity measure using both taxonomic and non-taxonomic relations performed as well as the other measures and was used for automatic comparison of morphological abnormalities within the IDEM computer-assisted consensus platform.

Breast↗

PubMed2005

Integration of multiple ontologies in breast cancer pathology.

The diagnostic variability in pathology, widely reported in the literature, is partly due to the use of different classification systems by pathologists. The descriptions of morphological characteristics on the same image within different classification systems can be considered as different points of view of pathologists. Our aim is to represent the points of view of the experts in pathology during image interpretation and to propose a method ological and technical solution in order to implement interoperability between these points of view. According to the hybrid ontology approach, we developed a system in three stages consisting in 1) the representation of the various points of view in local ontologies 2) the realization of a shared vocabulary and the development of a mapping tool used to allow the matching of local ontologies and shared vocabulary 3) the development of a transcoding algorithm for the translation of a case description from one point of view to another. A first evaluation of the transcoding algorithm was conducted for 33 cases of breast pathology. Our results show that the pathologists generally produce descriptions of the cases which do not follow rigorously the interpretation rules corresponding to the point of view they assert to adopt. While most of the concepts of local ontologies can be transcoded from a local ontology to another one (varying from 62.5 % to 100% according to the local ontology), the transcoding of a description which is valid according to a certain point of view, often results in a description which is not rigorously in accordance with the new point of view. These results underline the differences of interpretation rules existing in the different points of view.

Algorithms↗

PubMed2004

Specifications and implementation of a new exchange format to support computerized consensus in pathology.

In the pathology domain, consensus sessions around multi-headed microscopes enhance reproducibility and can reduce inter- and intra-observer variability. Computerized tools and Web technology could facilitate the organization of consensus sessions and assist pathologists to agree on features that are relevant to diagnosis. In the context of the IDEM project, whose aim is to achieve a computerized platform to allow pathologists to derive consensual diagnostic during Internet-based collaborative sessions, we propose a new extension of the existing TELESLIDE format. This new extended format enables the storage and the exchange of multi-experts descriptions that will be processed by the IDEM consensus engine to produce consensual descriptions. We describe this new format and its implementation in the IDEM teleconsensus platform.

Consensus↗

PubMed2003

A collaborative platform for consensus sessions in pathology over Internet.

The design of valid databases in pathology faces the problem of diagnostic disagreement between pathologists. Organizing consensus sessions between experts to reduce the variability is a difficult task. The TRIDEM platform addresses the issue to organize consensus sessions in pathology over the Internet. In this paper, we present the basis to achieve such collaborative platform. On the one hand, the platform integrates the functionalities of the IDEM consensus module that alleviates the consensus task by presenting to pathologists preliminary computed consensus through ergonomic interfaces (automatic step). On the other hand, a set of lightweight interaction tools such as vocal annotations are implemented to ease the communication between experts as they discuss a case (interactive step). The architecture of the TRIDEM platform is based on a Java-Server-Page web server that communicate with the ObjectStore PSE/PRO database used for the object storage. The HTML pages generated by the web server run Java applets to perform the different steps (automatic and interactive) of the consensus. The current limitations of the platform is to only handle a synchronous process. Moreover, improvements like re-writing the consensus workflow with a protocol such as BPML are already forecast.

Computer Systems↗

PubMed2002

A customizable similarity measure between histological cases.

IDEM, a computerized environment dedicated to pathologists, includes a Case Based Reasoning (CBR) procedure to retrieve similar histological cases in the database. The relevancy of a retrieved case strongly depends on the similarity measure comparing case descriptions. The present work deals with the definition of a similarity measure in the context of IDEM. In a first step, a theoretical measure (relational, numerical and informed), based on the domain constraints, was selected. In a second step, the theoretical measure is optimized according to the current case base. Results are presented for a database of 53 cases of breast tumors. The contribution of this work is to give to pathologists an interactive environment that optimizes the similarity measure between histological cases. This work is also a contribution to the CBR cycle life since the similarity measure can be adapted while new cases are added to the base.

Artificial Intelligence↗