Curvature integration in a 5D kernel for extracting vessel connections in retinal images
| Autor: | Giovanna Citti, Alessandro Sarti, Marta Favali, Bart M. ter Haar Romeny, Samaneh Abbasi-Sureshjani |
|---|---|
| Přispěvatelé: | Abbasi-Sureshjani, Samaneh, Favali, Marta, Citti, Giovanna, Sarti, Alessandro, Ter Haar Romeny, Bart M., Medical Image Analysis |
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Brain modeling Computer science Computer Vision and Pattern Recognition (cs.CV) Image Processing Computer Science - Computer Vision and Pattern Recognition Retinal Vessels/diagnostic imaging 02 engineering and technology Phantoms Imaging chemistry.chemical_compound 0302 clinical medicine Mathematical model Primary visual cortex Biomedical imaging Blood vessels Spectral clustering Image Processing Computer-Assisted 0202 electrical engineering electronic engineering information engineering Computer-Assisted/methods Cluster Analysis Computer vision Segmentation media_common Visualization Phantoms Imaging Computer Graphics and Computer-Aided Design Retinal image analysi medicine.anatomical_structure Retinal image analysis Kernel (image processing) 020201 artificial intelligence & image processing Algorithms Junctions Image Processing Computer-Assisted/methods media_common.quotation_subject Curvature Retina 03 medical and health sciences Perception medicine Humans Contextual affinity matrix Curvilinear coordinates business.industry Retinal Vessels Retinal Visual cortex chemistry Artificial intelligence Retina/diagnostic imaging business 030217 neurology & neurosurgery Software Perceptual grouping |
| Zdroj: | IEEE Transactions on Image Processing, 27(2):8063447, 606-621. Institute of Electrical and Electronics Engineers |
| ISSN: | 1941-0042 1057-7149 |
| DOI: | 10.1109/TIP.2017.2761543 |
| Popis: | Tree-like structures such as retinal images are widely studied in computer-aided diagnosis systems for large-scale screening programs. Despite several segmentation and tracking methods proposed in the literature, there still exist several limitations specifically when two or more curvilinear structures cross or bifurcate, or in the presence of interrupted lines or highly curved blood vessels. In this paper, we propose a novel approach based on multi-orientation scores augmented with a contextual affinity matrix, which both are inspired by the geometry of the primary visual cortex (V1) and their contextual connections. The connectivity is described with a five-dimensional kernel obtained as the fundamental solution of the Fokker-Planck equation modelling the cortical connectivity in the lifted space of positions, orientations, curvatures and intensity. It is further used in a self-tuning spectral clustering step to identify the main perceptual units in the stimuli. The proposed method has been validated on several easy and challenging structures in a set of artificial images and actual retinal patches. Supported by quantitative and qualitative results, the method is capable of overcoming the limitations of current state-of-the-art techniques. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|