Breath-Hold CBCT-Guided CBCT-to-CT Synthesis via Multimodal Unsupervised Representation Disentanglement Learning
IEEE Transactions on Medical Imaging · 2023-08 · 42 (8) · 2313-2324
DOI: 10.1109/tmi.2023.3247759 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2023-08. Verfasst von Yiwen Zhang und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Spiral Cone-Beam Computed Tomography, Breast Neoplasms. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Guangdong Provincial Key Laboratory of Medical Image Processing.
Abstract (Originalsprache)
Adaptive radiation therapy (ART) aims to deliver radiotherapy accurately and precisely in the presence of anatomical changes, in which the synthesis of computed tomography (CT) from cone-beam CT (CBCT) is an important step. However, because of serious motion artifacts, CBCT-to-CT synthesis remains a challenging task for breast-cancer ART. Existing synthesis methods usually ignore motion artifacts, thereby limiting their performance on chest CBCT images. In this paper, we decompose CBCT-to-CT synthesis into artifact reduction and intensity correction, and we introduce breath-hold CBCT images to guide them. To achieve superior synthesis performance, we propose a multimodal unsupervised representation disentanglement (MURD) learning framework that disentangles the content, style, and artifact representations from CBCT and CT images in the latent space. MURD can synthesize different forms of images using the recombination of disentangled representations. Also, we propose a multipath consistency loss to improve structural consistency in synthesis and a multidomain generator to improve synthesis performance. Experiments on our breast-cancer dataset show that MURD achieves impressive performance with a mean absolute error of 55.23±9.94 HU, a structural similarity index measurement of 0.721±0.042, and a peak signal-to-noise ratio of 28.26±1.93 dB in synthetic CT. The results show that compared to state-of-the-art unsupervised synthesis methods, our method produces better synthetic CT images in terms of both accuracy and visual quality.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Natural Science Foundation of China
- Basic and Applied Basic Research Foundation of Guangdong Province
- Guangdong Provincial Key Laboratory of Medical Image Processing
- Guangdong Provincial Hospital of Chinese Medicine Science and Technology Project
Zitieren
APA
Zhang, Y., Li, C., Dai, Z., Zhong, L., Wang, X., & Yang, W. (2023). Breath-Hold CBCT-Guided CBCT-to-CT Synthesis via Multimodal Unsupervised Representation Disentanglement Learning. IEEE Transactions on Medical Imaging, 42(8), 2313-2324. https://doi.org/10.1109/tmi.2023.3247759
Vancouver
Zhang Y, Li C, Dai Z, Zhong L, Wang X, Yang W. Breath-Hold CBCT-Guided CBCT-to-CT Synthesis via Multimodal Unsupervised Representation Disentanglement Learning. IEEE Transactions on Medical Imaging. 2023;42(8):2313-2324. doi:10.1109/tmi.2023.3247759
BibTeX
@article{Zhang2023,
author = {Zhang, Yiwen and Li, Chuanpu and Dai, Zhenhui and Zhong, Liming and Wang, Xuetao and Yang, Wei},
title = {Breath-Hold CBCT-Guided CBCT-to-CT Synthesis via Multimodal Unsupervised Representation Disentanglement Learning},
journal = {IEEE Transactions on Medical Imaging},
year = {2023},
volume = {42},
number = {8},
pages = {2313--2324},
doi = {10.1109/tmi.2023.3247759}
}
EUVIMED