Coarse-to-Fine Learning for Planning CT-Enhanced Limited-Angle CBCT Reconstruction

In the image-guided radiation therapy, the on-board cone-beam computed tomography (CBCT) is usually used for volumetric imaging, and the limited-angle scanning protocol is often adopted to avoid the possible collisions of the moving gantry with patients and devices. However, images directly reconstr...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on instrumentation and measurement 2024, Vol.73, p.1-15
Main Authors: Zang, Shizhe, Zhang, Yikun, Hu, Dianlin, Mao, Weilong, Fei, Xuanjia, Ji, Xu, Yao, Yi, Yang, Chunfeng, Coatrieux, Gouenou, Chen, Yang
Format: Article
Language:English
Subjects:
Coarse-to-fine learning
Computed tomography
Image acquisition
Image enhancement
Image quality
Image reconstruction
Image restoration
limited angle
Medical imaging
Optimization
Planning
planning computed tomography (pCT) enhanced cone-beam computed tomography (CBCT)
Radiation therapy
Three-dimensional displays
Tomography
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the image-guided radiation therapy, the on-board cone-beam computed tomography (CBCT) is usually used for volumetric imaging, and the limited-angle scanning protocol is often adopted to avoid the possible collisions of the moving gantry with patients and devices. However, images directly reconstructed using incomplete projection data may suffer from severe artifacts, which cannot provide precise guidance for the following therapeutic procedures. Compared with CBCT, the planning computed tomography (pCT) acquired for the treatment plan can provide high-quality images of the same patient, showing the potential to improve the limited-angle CBCT. In this article, we propose a multidimensional joint cascaded network (MJCNet), which can exploit the prior information from pCT. MJCNet improves the imaging quality of limited-angle CBCT through a coarse-to-fine strategy. In the coarse restoration stage, a 2-D network with two encoders that could extract and exploit the information of pCT is used to remove limited-angle artifacts slice-by-slice. In the fine-tuning stage, a 3-D network with a dense attention mechanism is employed to further improve the image details and remove the interslice artifacts. The real data from different parts of human bodies are collected to evaluate the proposed method. Experimental results demonstrate the promising performance of MJCNet in reducing wedge artifacts, restoring image structures, and correcting hounsfield unit (HU) numbers.
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2024.3406810