Tehran University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share By
A Deep Learning Method for High-Quality Ultra-Fast Ct Image Reconstruction From Sparsely Sampled Projections Publisher



Khodajouchokami H1 ; Hosseini SA1 ; Ay MR2, 3
Authors

Source: Nuclear Instruments and Methods in Physics Research# Section A: Accelerators# Spectrometers# Detectors and Associated Equipment Published:2022


Abstract

Few-view or sparse-view computed tomography has been recently introduced as a great potential to speed up data acquisition and alleviate the amount of patient radiation dose. This study aims to present a method for high-quality ultra-fast image reconstruction from sparsely sampled projections to overcome problems of previous methods, missing and blurring tissue boundaries, low-contrast objects, variations in shape and texture between the images of different individuals, and their outcomes. To this end, a new deep learning (DL) framework based on convolution neural network (CNN) models is proposed to solve the problem of CT reconstruction under sparsely sampled data, named the multi-receptive field densely connected CNN (MRDC-CNN). MRDC-CNN benefits from an encoder–decoder structure by proposing dense skip connections to recover the missing information, multi-receptive field modules to enlarge the receptive field, and having no batch normalization layers to boost the performance. The MRDC-CNN with a hybrid loss function format introduces several auxiliary losses combined with the main loss to accelerate convergence rate and alleviate the gradient vanishing problem during network training and maximize its performance. Results have shown that MRDC-CNN is 4–6times faster than the state-of-the-art methods, with fewer memory requirements, better performance in objective quality evaluations, and improved visual quality. The results indicated the superiority of our proposed method compared to the latest algorithms. In conclusion, the proposed method could lead to high-quality CT imaging with quicker imaging speed and lower radiation dose. The source code is available on a GitHub repository at this link. © 2022 Elsevier B.V.
Other Related Docs
7. A Hybrid Capsule Network for Automatic 3D Mandible Segmentation Applied in Virtual Surgical Planning, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society# EMBS (2022)
9. Accurate Automatic Glioma Segmentation in Brain Mri Images Based on Capsnet, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society# EMBS (2021)
10. Cascaded Learning With Generative Adversarial Networks for Low Dose Ct Denoising, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society# EMBS (2021)
11. Atb-Net: A Novel Attention-Based Convolutional Neural Network for Predicting Full-Dose From Low-Dose Pet Images, 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record# NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors# RTSD 2022 (2021)
12. Deep Adaptive Transfer Learning for Site-Specific Pet Attenuation and Scatter Correction From Multi-National/Institutional Datasets, 2022 IEEE NSS/MIC RTSD - IEEE Nuclear Science Symposium# Medical Imaging Conference and Room Temperature Semiconductor Detector Conference (2022)
15. Deep Learning-Based Automated Delineation of Head and Neck Malignant Lesions From Pet Images, 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference# NSS/MIC 2020 (2020)
17. Deep Active Learning Model for Adaptive Pet Attenuation and Scatter Correction in Multi-Centric Studies, 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record# NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors# RTSD 2022 (2021)