Skip to Main content Skip to Navigation
Theses

Contribution à la classification automatique de tissus corporels par intégration des connaissances médicales qualitatives : application aux maladies et déficiences musculo-squelletiques

Abstract : In the diagnosis using MRI images, image segmentation techniques plays a key role. Nevertheless, segmentation with context independent features such as grey level and texture often leads to unsatisfactory results because these general features can not take into account the specialized background knowledge. Therefore, it is necessary to incorporate our a priori knowledge on medical image analysis for obtaining better results of tissue classification.In this context, two main contributions have been proposed in order to improve FCM-based image segmentation quality. The first contribution is that we developed a new FCM-based algorithm for image segmentation. The second contribution is the development of an intelligent system for tissue classification. It consists of two steps. The first step is a specific tissue classification system of thigh. The second step is a generalized intelligent system for tissue classification
Complete list of metadata

https://hal-uphf.archives-ouvertes.fr/tel-03018996
Contributor : Julie Cagniard Connect in order to contact the contributor
Submitted on : Monday, November 23, 2020 - 10:56:53 AM
Last modification on : Friday, October 1, 2021 - 8:36:03 AM
Long-term archiving on: : Wednesday, February 24, 2021 - 6:46:17 PM

File

2009VALE0005_KANG_HAN.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : tel-03018996, version 1

Collections

Citation

Han Kang. Contribution à la classification automatique de tissus corporels par intégration des connaissances médicales qualitatives : application aux maladies et déficiences musculo-squelletiques. Informatique [cs]. Université de Valenciennes et du Hainaut-Cambrésis, 2009. Français. ⟨NNT : 2009VALE0005⟩. ⟨tel-03018996⟩

Share

Metrics

Record views

31

Files downloads

26