Abstract
Mosaicking of retinal images is potentially useful for ophthalmologists and computer-aided diagnostic schemes. Vascular bifurcations can be used as features for matching and stitching of retinal images. A fully convolutional network model is employed to segment vascular structures in retinal images to detect vascular bifurcations. Then, bifurcations are extracted as feature points on the vascular mask by a robust and efficient approach. Transformation parameters for stitching can be estimated from the correspondence of vascular bifurcations. The proposed feature detection and mosaic method is evaluated on retinal images of 14 different eyes, 62 retinal images. The proposed method achieves a considerably higher average recall rate of matching for paired images compared with speeded-up robust features and scale-invariant feature transform. The running time of our method was also lower than other methods. Results produced by the proposed method superior to that of AutoStitch, photomerge function in Photoshop cs6 and ICE, demonstrate that accurate matching of detected vascular bifurcations could lead to high-quality mosaic of retinal images.
Highlights
Retinal images are crucial for ophthalmologists to diagnose a series of diseases
The retinal image captured by a fundus camera or scanning laser ophthalmoscope can only cover a local area of the eye. e retinal images captured in different field areas must be stitched together to form a mosaic image that meets the needs of the analysis of the entire area of the fundus in research and clinical diagnosis
Overview. is work aims to develop a practical and useful method for detecting robust and sufficient features with indistinct vascular structures and constructing an automatic mosaic of multiple retinal images. e image stitching process can be summarized by the steps shown in Figure 2. e novelty of the paper include the following: (1) e binary image of vascular structures instead of the original image was used for bifurcation detection
Summary
Retinal images are crucial for ophthalmologists to diagnose a series of diseases. The retinal image captured by a fundus camera or scanning laser ophthalmoscope can only cover a local area of the eye. Ryan et al [5] studied the registration of retinal images using landmark correspondence. This approach obtains remarkably few matching point pairs. Landmark matching formulation [1] is based on retinal image alignment by enforcing sparsity in correspondence matrix. Such approach needs a complicated computational process and high cost
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.