Retinal fundus image registration framework using Bayesian integration and asymmetric Gaussian mixture model

Abstract

Retinal image registration, which is applied in diagnosing and treating eye diseases, plays an important role in medical image analysis. Existing methods suffer from problems due to different imaging viewpoints, times, quality, modalities, and retinal disasters. In this paper, we propose an efficient retinal images registration framework that overcomes these challenges without supervision. We present a layer-wise matching method to achieve a uniform distribution of features in both image-space and scale-space. Then, a novel method called Bayesian integration is generated to accumulate more meaningful inputs. We use the results of different matches as priors, assign a score to each match, and categorize them using a dynamic threshold. Finally, in accordance with previous work, we transform the problem into a probabilistic model, with the asymmetric Gaussian mixture model representing the distribution. A robust estimation is performed on a non-rigid transformation. The experimental results demonstrate that our proposed framework is robust to kinds of retinal image degradation and produces a more stable and accurate result than state-of-the-art methods.

A universal medically assisted model for anatomical landmark detection in radioactive images

“…Precisely detecting landmarks in medical images has emerged as a critical field 2 . Existing computer‐aided diagnosis methods play a significant role in numerous applications, including medical image registration, 3 tissue segmentation, 4 parameter measurement, 5 pathological diagnosis, 6 treatment planning, 7 surgical guidance, 8 and initialization processes within the domain of other medical image processing 9 . However, due to the diversity of human anatomical structures, some anatomical entities include closely located or potentially locally similar landmarks.…”