3D Image Analysis and Artificial Intelligence for Bone Disease Classification

Abdurrahim Akgundogdu (1) , Rachid Jennane (2) , Gabriel Aufort (3) , Claude-Laurent Benhamou (4) , Osman Nuri Ucan (5)

1 Istanbul University
2 IRAUS - Département Images, Robotique, Automatique et Signal [Orléans]
3 Ludia Inc.
4 INSERM U658
5 Dept. of Electrical Electronics Engineering (Istanbul Aydin University)

In order to prevent bone fractures due to disease and ageing of the population, and to detect problems while still in their early stages, 3D bone micro architecture needs to be investigated and characterized. Here, we have developed various image processing and simulation techniques to investigate bone micro architecture and its mechanical stiffness. We have evaluated morphological, topological and mechanical bone features using artificial intelligence methods. A clinical study is carried out on two populations of arthritic and osteoporotic bone samples. The performances of Adaptive Neuro Fuzzy Inference System (ANFIS), Support Vector Machines (SVM) and Genetic Algorithm (GA) in classifying the different samples have been compared. Results show that the best separation success (100 %) is achieved with Genetic Algorithm.

Mots clés: Trabecular bone; Hybrid Skeleton Graph Analysis; SVM; GA; ANFIS

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Abdurrahim Akgundogdu, Rachid Jennane, Gabriel Aufort, Claude-Laurent Benhamou, Osman Nuri Ucan. 3D Image Analysis and Artificial Intelligence for Bone Disease Classification. Journal of Medical Systems, 2010, 34 (5), pp.815-828. ⟨10.1007/s10916-009-9296-3⟩. ⟨hal-00655386⟩