The lamina cribrosa is a 3D mesh-like structure within the optical nerve head, consisting of pores through which all the nerve fibers from the retina pass to join the brain. Alterations and damages in this structure have proven to be linked with glaucoma, the second leading global cause of blindness. Therefore, an automatic and accurate 3D pore reconstruction method from 3D images is crucial for carrying out clinical studies. In this article, we present a fully automatic method for the segmentation and reconstruction of axonal pathways from 3D OCT images. Our method has be designed to overcome the difficulties related to the poor image quality and partial annotations. It is based on the registration of two OCT volumes acquired in two orthogonal scanning directions and the design of a U-Net with attention mechanism to segment the pores of the registered 2D en-face images. Finally, the segmented pores are tracked using a parametric snake model to reconstruct the axonal pathways in 3D. Experiments show that 84.7% of the paths are truly detected with a RMSE around 2 pixels, below the pore diameters.

Glaucoma is the second leading cause of blindness in the world. Although its physiopathology remains unclear, the lamina cribrosa, a 3D mesh-like structure consisting of pores, that allow the axons passing through to join the brain, has been identified as the primary site of damage. In this work we present an extended version of U-Net for pore segmentation in 2D en-face OCT images with partial point annotations, i.e. having only a small portion of pore locations in each image labeled. Our method combines the attention gate and the context information to address the difficulties caused by small object segmentation in low signal to noise ratio images. Experimental results show that 71.8% of the annotated pores are successfully segmented.

Tubular structure tracking is a crucial task in the fields of computer vision and medical image analysis. The minimal paths-based approaches have exhibited their strong ability in tracing tubular structures, by which a tubular structure can be naturally modeled as a minimal geodesic path computed with a suitable geodesic metric. However, existing minimal paths-based tracing approaches still suffer from difficulties such as the shortcuts and short branches combination problems, especially when dealing with the images involving complicated tubular tree structures or background. In this paper, we introduce a new minimal paths-based model for minimally interactive tubular structure centerline extraction in conjunction with a perceptual grouping scheme. Basically, we take into account the prescribed tubular trajectories and curvature-penalized geodesic paths to seek suitable shortest paths. The proposed approach can benefit from the local smoothness prior on tubular structures and the global optimality of the used graph-based path searching scheme. Experimental results on both synthetic and real images prove that the proposed model indeed obtains outperformance comparing with the state-of-the-art minimal paths-based tubular structure tracing algorithms.

The study of vascular morphometry requires segmenting vessels with high precision. Of particular clinical interest is the morpho-metric analysis of arterial bifurcations in Adaptive Optics Ophthalmoscopy (AOO) images of eye fundus. In this paper, we extend our previous approach for segmenting retinal vessel branches to the segmentation of bifurcations. This enables us to recover the microvascular tree and extract biomarkers that charactarize the blood flow. Segmentation results are shown to be within the range of intra-and inter-user variability, allowing a preliminary study on biomarkers derived from vessel diameter estimates at arterial bifurcations.

In order to segment elongated structures, we propose a new approach for integrating an approximate parallelism constraint in deformable models . The proposed Parallel Double Snakes evolve simultaneously two contours, in order to minimize an energy functional which attracts these contours towards high image gradients and enforces the approximate parallelism between them by controlling their distance to a centerline under regularity constraints of this line. The proposed approach is applied on retina images, for segmenting retinal layers in optical coherence tomography images of pathological subjects (and it applies to healthy subjects as well). Results are evaluated by comparing with manual segmentations for three retinal layers, and provide a similarity index above 0.87, sensitivity between 0.85 and 0.93, and specificity between 0.84 and 0.94. These results are within the range of intra and inter-expert variability. Moreover, quantitative studies demonstrate that, in our application, our Parallel Double Snake (PDS) model outperforms other parametric active contour algorithms integrating parallelism information.

In this paper, we present a method for automatically segmenting the walls of retinal arteries in adaptive optics images. To the best of our knowledge, this is the first method addressing this problem in such images. To achieve this goal, we propose to model these walls as four curves approximately parallel to a common reference line located near the center of vessels. Once this line is detected, the curves are simultaneously positioned as close as possible to the borders of walls using an original tracking procedure to cope with deformations along vessels. Then, their positioning is refined using a deformable model embedding a parallelism constraint. Such an approach enables us to control the distance of the curves to their reference line and improve the robustness to image noise. This model was evaluated on healthy subjects by comparing the results against segmentations from physicians. Noticeably, the error introduced by this model is smaller or very near the inter-physicians error.

Parametric deformable models are an important technique for image segmentation. In order to improve the robustness of the model, it may be interesting to incorporate a priori information about the shape of the objects to be segmented. In this paper, we propose to add a parallelism constraint. Such a model is relevant in many applications where elongated structures have to be detected. One main advantage of our formulation is that it only needs few parameters to be adjusted in addition to those of traditional snakes. The pro- posed model has been applied for the segmentation of OCT images of tile retina and for the segmentation of retinal vessels. Experimental results, obtained on 25 OCT images and 30 eye fundus images, demonstrated the robustness, flexibility and large potential applicability of this new formulation. The accuracy of the method has been assessed by comparing manual segmentations, made by experts, with the automatic ones.

In this article, the in vivo evaluation of retinal prostheses were achieved either in animals with normal vision or in blind persons. To assess the stimulating electrodes in vivo on an animal with photoreceptor degeneration, we have implanted a P23H rhodopsin rats. The present study describes the implant design and our surgical strategy. The experiments indicate clearly that the implant electrodes can be tested on a leaving rat with photoreceptor degeneration. Future studies can assess the electrode characteristics and the stimulating protocol to trigger cellular and/or animal behavior responses.