Optic disc (OD) appearance in fundus images is one of the clinical indicators considered in the assessment of retinal diseases such as glaucoma. The cup-to-disc ratio (CDR) is the most common clinical measurement used to characterize glaucoma. However, the CDR only evaluates the relative sizes of the cup and the OD via their diameters. We propose to construct an atlas-based shape descriptor (ASD) to statistically characterize the geometric deformations of the OD shape and of the blood vessels’ configuration inside the OD region. A local representation of the OD region is proposed to construct a well-defined statistical atlas using nonlinear registration and statistical analysis of deformation fields. The shape descriptor is defined as being composed of several statistical measures from the atlas. Analysis of the average model and its principal modes of deformation are performed on a healthy population. The components of the ASD show a significant difference between pathological and healthy ODs. We show that the ASD is able to characterize healthy and glaucomatous OD regions. The deviation map extracted from the atlas can be used to assist clinicians in an early detection of deformation abnormalities in the OD region.
The optic disc (OD) and the macula are important structures in automatic diagnosis of most retinal diseases inducing vision defects such as glaucoma, diabetic or hypertensive retinopathy and age-related macular degeneration. We propose a new method to detect simultaneously the macula and the OD boundary. First, the color fundus images are processed to compute several maps highlighting the different anatomical structures such as vessels, the macula and the OD. Then, macula candidates and OD candidates are found simultaneously and independently using seed detectors identified on the corresponding maps. After selecting a set of macula/OD pairs, the top candidates are sent to the OD segmentation method. The segmentation method is based on local K-means applied to color coordinates in polar space followed by a polynomial fitting regularization step. Pair scores are updated, resulting in the final best macula/OD pair. The method was evaluated on two public image databases: ONHSD and MESSIDOR. The results show an overlapping area of 0.84 on ONHSD and 0.90 on MESSIDOR, which is better than recent state of the art methods. Our segmentation method is robust to contrast and illumination problems and outputs the exact boundary of the OD, not just a circular or elliptical model. The macula detection has an accuracy of 94%, which again outperforms other macula detection methods. This shows that combining the OD and macula detections improves the overall accuracy. The computation time for the whole process is 6.4 seconds, which is faster than other methods in the literature.
Registration of thoracoscopic images to a preoperative 3D model of the spine is a prerequisite for minimally invasive
surgical guidance. We propose an active self-calibration method of thoracoscopic image sequences acquired by an
angled monocular endoscope with varying focal length during minimally invasive surgery of the spine. The extrinsic
parameters are updated in real time by a motion tracking system while the intrinsic parameters are determined from a set
of geometrical primitives extracted from the image of the surgical instrument tracked throughout the thoracoscopic
sequence. A particle filter was used for the tracking of the instrument on the image sequence that was preprocessed to
detect and correct reflexions due to the light source. The proposed method requires undertaking a pure rotation of the
endoscope to update the focal length and exploits the inherent temporal rigid motion of the instrument through
consecutive frames. A pure rotation is achievable by undertaking a rotation of the scope cylinder with respect to the head
of the camera. Therefore, the surgeon may take full advantage of an angled endoscope by adjusting focus and zoom
during surgery. Simulation experiments have assessed the accuracy of the obtained parameters and the optimal number
of geometrical primitives required for an active self-calibration of the angled monocular endoscope. Finally, an in vitro
experiment demonstrated that 3D reconstruction of rigid structures tracked throughout a monocular thoracoscopic image
sequence is feasible and its accuracy is adequate for the registration of thoracoscopic images to a preoperative MRI 3D
model of the spine.