Skip to content

Dual-energy CT reconstruction accelerated with an attention-based U-Net in PyTorch, structured and documented in a MyST Book format.

Notifications You must be signed in to change notification settings

luukfroling/BEP

Repository files navigation

Accelerating dual-energy CT scan reconstruction using machine learning

This repository contains the source code and documentation for my Bachelor Thesis project, completed over an 11-week period. The project investigates how machine learning can accelerate dual-energy CT (DECT) scan reconstruction.

Project website: https://luukfroling.github.io/BEP/

Overview

Dual-energy CT (DECT) imaging acquires scans using two distinct X-ray energy levels, providing material-specific diagnostic information. However, reconstructing high-quality DECT images is computationally expensive.

This project explores how deep learning, specifically an attention-based U-Net, can learn to approximate results from an existing iterative reconstruction algorithm. The goal is to reduce computation time while maintaining comparable image quality.

About

Dual-energy CT reconstruction accelerated with an attention-based U-Net in PyTorch, structured and documented in a MyST Book format.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published