United multi-task learning for abdominal contrast-enhanced CT synthesis through joint deformable registration
Computer Methods and Programs in Biomedicine · 2023-04 · 231 · 107391
DOI: 10.1016/j.cmpb.2023.107391 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2023-04. Verfasst von Liming Zhong und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processi…. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Tomography, X-Ray Computed. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 50 Literaturangaben.
Abstract (Originalsprache)
Synthesizing abdominal contrast-enhanced computed tomography (CECT) images from non-enhanced CT (NECT) images is of great importance, in the delineation of radiotherapy target volumes, to reduce the risk of iodinated contrast agent and the registration error between NECT and CECT for transferring the delineations. NECT images contain structural information that can reflect the contrast difference between lesions and surrounding tissues. However, existing methods treat synthesis and registration as two separate tasks, which neglects the task collaborative and fails to address misalignment between images after the standard image pre-processing in training a CECT synthesis model. Thus, we propose an united multi-task learning (UMTL) for joint synthesis and deformable registration of abdominal CECT. Specifically, our UMTL is an end-to-end multi-task framework, which integrates a deformation field learning network for reducing the misalignment errors and a 3D generator for synthesizing CECT images. Furthermore, the learning of enhanced component images and the multi-loss function are adopted for enhancing the performance of synthetic CECT images. The proposed method is evaluated on two different resolution datasets and a separate test dataset from another center. The synthetic venous phase CECT images of the separate test dataset yield mean absolute error (MAE) of 32.78±7.27 HU, mean MAE of 24.15±5.12 HU on liver region, mean peak signal-to-noise rate (PSNR) of 27.59±2.45 dB, and mean structural similarity (SSIM) of 0.96±0.01. The Dice similarity coefficients of liver region between the true and synthetic venous phase CECT images are 0.96±0.05 (high-resolution) and 0.95±0.07 (low-resolution), respectively. The proposed method has great potential in aiding the delineation of radiotherapy target volumes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Guangzhou 510515, China.
- Department of Biostatistics, School of Global Public Health, New York University, New York, NY, 10003, United States.
- Department of Information, the Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou 510515, China.
- Department of Medical Imaging Center, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China. Electronic address: ripleyor@126.com.
- School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Guangzhou 510515, China. Electronic address: weiyanggm@gmail.com.
Zitieren
APA
Zhong, L., Huang, P., Shu, H., Li, Y., Zhang, Y., Feng, Q., Wu, Y., & Yang, W. (2023). United multi-task learning for abdominal contrast-enhanced CT synthesis through joint deformable registration. Computer Methods and Programs in Biomedicine, 231, 107391. https://doi.org/10.1016/j.cmpb.2023.107391
Vancouver
Zhong L, Huang P, Shu H, Li Y, Zhang Y, Feng Q, et al. United multi-task learning for abdominal contrast-enhanced CT synthesis through joint deformable registration. Computer Methods and Programs in Biomedicine. 2023;231:107391. doi:10.1016/j.cmpb.2023.107391
BibTeX
@article{Zhong2023,
author = {Zhong, Liming and Huang, Pinyu and Shu, Hai and Li, Yin and Zhang, Yiwen and Feng, Qianjin and Wu, Yuankui and Yang, Wei},
title = {United multi-task learning for abdominal contrast-enhanced CT synthesis through joint deformable registration},
journal = {Computer Methods and Programs in Biomedicine},
year = {2023},
volume = {231},
pages = {107391},
doi = {10.1016/j.cmpb.2023.107391}
}
EUVIMED