Case Retrieval in Medical Databases by Fusing Heterogeneous Information

Department of Image et Traitement de l'Information, Institut Telecom/Telecom Bretagne, F-29200 Brest, France.
IEEE transactions on medical imaging 01/2011; 30(1):108-18. DOI: 10.1109/TMI.2010.2063711
Source: PubMed


A novel content-based heterogeneous information retrieval framework, particularly well suited to browse medical databases and support new generation computer aided diagnosis (CADx) systems, is presented in this paper. It was designed to retrieve possibly incomplete documents, consisting of several images and semantic information, from a database; more complex data types such as videos can also be included in the framework. The proposed retrieval method relies on image processing, in order to characterize each individual image in a document by their digital content, and information fusion. Once the available images in a query document are characterized, a degree of match, between the query document and each reference document stored in the database, is defined for each attribute (an image feature or a metadata). A Bayesian network is used to recover missing information if need be. Finally, two novel information fusion methods are proposed to combine these degrees of match, in order to rank the reference documents by decreasing relevance for the query. In the first method, the degrees of match are fused by the Bayesian network itself. In the second method, they are fused by the Dezert-Smarandache theory: the second approach lets us model our confidence in each source of information (i.e., each attribute) and take it into account in the fusion process for a better retrieval performance. The proposed methods were applied to two heterogeneous medical databases, a diabetic retinopathy database and a mammography screening database, for computer aided diagnosis. Precisions at five of 0.809 ± 0.158 and 0.821 ± 0.177, respectively, were obtained for these two databases, which is very promising.

Download full-text


Available from: Christian Roux,
    • "Thus, it is not possible to notify relevant experts on the fly to give help to a patient who is becoming depressed. Due to the continuing advance of information technology, increasing numbers of studies are utilizing information technology for the automatic inference of the status of patients and to obtain results [22]. In various research areas, ontology [23] is an important technique for representing the terminology used in certain domains. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Recently, depression becomes a general disease in the world. Most of people are not aware of the possibility of getting depressed himself in daily life. Therefore, to diagnose the possibility of getting depressed accurately becomes an important issue in health-care domain. In this paper, we build an inference model based on ontology and Bayesian Network for inferring the possibility of getting depressed and implement a prototype using mobile agent platform to show the proof-of-the-concept using mobile cloud. We proposed an ontology model to build the terminology of depression and utilize Bayesian Network to infer the probability of getting depressed. In addition, the work is implemented using multi-agents and runs on the Android platform to demonstrate the feasibility and address the implementation issues. The result shows that it can be well inferred in the depression diagnosis.
    Future Generation Computer Systems 08/2014; 43-44. DOI:10.1016/j.future.2014.05.004 · 2.79 Impact Factor
  • Source
    • "Considering related diseases have similar solutions, medical case retrieval is suggested by heterogeneous information fusion [4]. In addition, support vector machine (SVM)-based frameworks are also popular in medical image retrieval system during image filtering and dynamic features fusion [5]. "

    KSII Transactions on Internet and Information Systems 02/2014; 8(1):249-268. · 0.56 Impact Factor
  • Source
    • "It relies on retinal image G. Quellec, M. Lamard, B. Cochener, C. Roux and G. Cazuguel are with Inserm, UMR 1101, Brest, F-29200 France G. Quellec is with ARTORG Center for Biomedical Engineering Research , University of Bern, Bern, CH-3010 Switzerland M. Lamard and B. Cochener are with Univ Bretagne Occidentale, Brest, F-29200 France B. Cochener is with CHRU Brest, Service d'Ophtalmologie, Brest, F- 29200 France E.Decencì ere is with Centre for Mathematical Morphology, Systems and Mathematics Department, MINES ParisTech, Fontainebleau, F-77300 France B. Lay is with ADCIS, Saint-Contest, F-14280 France A. Chabouis is with HôpitalLariboisì ere -APHP, Service d'Ophtalmologie, Paris, F-75475 France C. Roux and G. Cazuguel are with Institut Mines-Telecom; Telecom Bretagne; UEB; Dpt ITI, Brest, F-29200 France processing and data mining methodologies developed in the past few years by the Centre for Mathematical Morphology [6], [7], [8], in Paris, and by the LaTIM Laboratory [9], [10], [11], [12], in Brest, France. The project benefits from a large amount of data collected in the OPHDIAT telemedical network for diabetic retinopathy screening [3]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents TeleOphta, an automatic system for screening diabetic retinopathy in teleophthalmology networks. Its goal is to reduce the burden on ophthalmologists by automatically detecting non referable examination records, i.e. examination records presenting no image quality problems and no pathological signs related to diabetic retinopathy or any other retinal pathology. TeleOphta is an attempt to put into practice years of algorithmic developments from our groups. It combines image quality metrics, specific lesion detectors and a generic pathological pattern miner to process the visual content of eye fundus photographs. This visual information is further combined with contextual data in order to compute an abnormality risk for each examination record. The TeleOphta system was trained and tested on a large dataset of 25,702 examination records from the OPHDIAT screening network in Paris. It was able to automatically detect 68% of the non referable examination records while achieving the same sensitivity as a second ophthalmologist. This suggests that it could safely reduce the burden on ophthalmologists by 56%.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 07/2013; 2013:7144-7147. DOI:10.1109/EMBC.2013.6611205
Show more