Biomedical subjects

Yongjin Zhou

Publications and source records attributed to Yongjin Zhou.

3 recordsLinked to original sources

PubMed2004

A fast snake model based on non-linear diffusion for medical image segmentation.

In this paper, the traditional snake model and gradient vector flow (GVF) snake model are studied, which are believed to be quite slow due to the need to compute inverse matrix. Actually, the GVF in the latter snake model is formed by a biased linear diffusion procedure, and there would be oscillations around the edge of the object. Based on GVF generated through non-linear diffusion, we present a fast GVF (FGVF) snake model which is much faster than the traditional snake model and GVF snake model, and would cause no degradation of stability and flexibility, meanwhile, it could reduce the oscillations around the edges. The segmentation results using FGVF and error analysis on simulated images are presented. Finally, the demonstration of FGVF applied to Computed Tomography and Magnetic Resonance images are shown, the segmentation results are satisfactory visually with much less computation time in comparison with former snakes.

Algorithms↗

PubMed2004

A tunable incremental factor augmented inverse image alignment method in fundus angiogram registration and mosaicing.

A tunable incremental factor is introduced into the inverse compositional image alignment method in registration of fundus blood vessel angiograms under confocal scanning laser ophthalmoscope. The augmented version need less iteration to converge and hardly causes degradation to the registration precision, mainly due to the favorable convexity of the sum of squared differences (SSD) function between the angiograms around the correct registration. And as a compromise between the fidelity of diagnostic information and visual purpose, an adaptive blending strategy based on undecimated discrete sequence wavelet transform is presented in this paper to mosaic fundus angiograms. The effectiveness and efficiency of the tunable incremental factor algorithm is exemplified in the experimental results on clinical indocyanine green angiograms, and the convexity of the SSD function under ideal imaging condition is also illustrated in the paper.

Algorithms↗

PubMedDate not supplied

Inverse image alignment method for image mosaicing and video stabilization in fundus indocyanine green angiography under confocal scanning laser ophthalmoscope.

An efficient image registration algorithm, the Inverse Compositional image alignment method based on minimization of Sum of Squared Differences of images, is applied in fundus blood vessel angiography under confocal scanning laser ophthalmoscope, to build image mosaics which have larger field of view without loss of resolution to assist diagnosis. Furthermore, based on similar technique, the angiography video stabilization algorithm is implemented for fundus documenting. The actual underlying models of motion between images and corresponding convergence criteria are also discussed. The experiment results in fundus images demonstrate the effectiveness of the registration scheme.

Algorithms↗