Joint capsule segmentation in ultrasound images of the metacarpophalangeal joint using a split and merge approach

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2018

Autores

Martins, N (Autor) Outra; Sultan, MS (Autor) Outra; Veiga, D (Autor) Outra; Ferreira, M (Autor) Outra; Coimbra, M (Autor) FCUP

Ata de Conferência Internacional

Título: 2018 IEEE EMBS International Conference on Biomedical & Health Informatics, BHI 2018, Las Vegas, NV, USA, March 4-7, 2018

Páginas: 243-246

2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018

4 March 2018 through 7 March 2018

Indexação

Scopus - 3 Citações

Outras Informações

ID Authenticus: P-00P-EA6

DOI: 10.1109/bhi.2018.8333414

Abstract (EN): This work presents a new approach for the identification of the joint capsule in ultrasound images of the metacarpophalangeal joint. These images are used to diagnose rheumatic diseases which are one of the main causes of impairment and pain in developed countries. The early diagnosis of these conditions is crucial to a proper treatment and follow-up and so, this work contributes to the automatic extraction of relevant information from the resulting images. The algorithm uses the metacarpus, phalange and extensor tendon positions to create a region of interest. Next, a split and merge approach is used to identify the joint capsule, where the split is done using the Simple Linear Iterative Clustering algorithm and the merge is achieved with a special region growing with shape constraints. After that, the results are refined using a Localizing Active Contours method. Results shown that the segmentation is possible with 60% of the joint capsules identified with a Dice Coefficient higher than 0.7. © 2018 IEEE.

Idioma: Inglês

Tipo (Avaliação Docente): Científica