Probabilistic Capsule Diffusion Framework for Uncertainty Aware Medical Image Reconstruction

Abstract

Reconstruction of medical images is important in improving the diagnosis especially in conditions of noisy and uncertain imaging. Nevertheless, the traditional methods of reconstruction can hardly preserve fine forms of anatomy and do not have effective methods of uncertainty estimation. This paper will introduce a Probabilistic Capsule Diffusion Framework of Uncertainty-Aware Medical Image Reconstruction that combines probabilistic diffusion modeling with capsule-based hierarchical feature learning to enhance the reconstruction accuracy and reliability. The diffusion method allows learning strong probabilistic latent representations, and the capsule network allows the preservation of space and structure. The probabilistic capsule modeling also offers the estimation of uncertainty by variance-based confidence mapping. The proposed framework was tested on the Kaggle Brain MRI data in different noise levels. The results of the experiments showed high performance in terms of Peak Signalto-Noise Ratio of 43.02 dB, Structural Similarity Index of 0.987, and reconstruction accuracy of 99.9% which was much better than the traditional CNN, GAN, and diffusion-based reconstruction algorithms. The framework also had low reconstruction error of 0.008 and high score of confidence of 0.982 which means that it quantifies uncertainty well.