A Dual-Domain Diffusion Model for Sparse-View CT Reconstruction

Abstract

A new deep-learning approach, dual-domain diffusion model (DDDM), is proposed for sparse-view CT reconstruction, which is composed of a sinogram upgrading module (SUM) and an image refining module (IRM) connected in series. In the sinogram domain, a novel degrading and upgrading framework is defined, in which SUM is trained to upgrade sparse-view sinograms step by step to reverse the degradation process of CT images caused by successive down-sampling of scanning views. In the image domain, IRM adopts an improved denoising diffusion framework to further reduce remaining artifacts and restore image details, where a skip connection from the original sparseview sinogram is introduced to constrain the generation of details. Our DDDM shows significant improvement over deep-learning baseline models in both classical similarity metrics and perceptual loss, and has good generalization to untrained organs. We release our code at: https://github.com/YC-Markus/code-for-DDDM.

Multi-Scale Digital Pathology Patch-Level Prostate Cancer Grading Using Deep Learning: Use Case Evaluation of DiagSet Dataset

“…Furthermore, the integration of a segmentation model as a feature extractor allows our model to discern spatial relationships and semantic context within the images. Additionally, the segmentation model helps in isolating the relevant regions of interest within the images, reducing noise and irrelevant data that could potentially hinder the classification performance [ 55 ].…”

Optimization of resources in intelligent electronic health systems based on internet of things to predict heart diseases via artificial neural network

“…Its low computational requirements are a result of its simplicity [ 50 ]. This unsupervised filtering technique is designed to work with data from real-time sensors and produce noise-free results that are closer to the actual sensor readings [ 51 ]. If any values are missing from the structured data set, the second filter will fill them in using the median and mean of the available data.…”

Intelligent Recognition of Multimodal Human Activities for Personal Healthcare

“…This matrix comprehends four parameters namely true negative and positives, false negative and positives, characterized as TN, TP, FN, and FP. The metrics adopted are precision, accuracy, and recall [28]. For attaining a better balance between sensitivity and precision, the paper employed an additional metric of F1 score [29] for the experimentations.…”