Search

Your search keyword '"Zhu, Zhenyu"' showing total 873 results
Start Over Author "Zhu, Zhenyu" Publication Type Academic Journals
873 results on '"Zhu, Zhenyu"'

5. Contrast-Enhanced Liver Magnetic Resonance Image Synthesis Using Gradient Regularized Multi-Modal Multi-Discrimination Sparse Attention Fusion GAN.

Author

Jiao, Changzhe, Ling, Diane, Bian, Shelly, Vassantachart, April, Cheng, Karen, Mehta, Shahil, Lock, Derrick, Zhu, Zhenyu, Feng, Mary, Thomas, Horatio, Sheng, Ke, Fan, Zhaoyang, Scholey, Jessica, and Yang, Wensha

Subjects
GAN, MR synthesis, contrast enhancement, multi-modal fusion, tumor monitoring
Abstract

PURPOSES: To provide abdominal contrast-enhanced MR image synthesis, we developed an gradient regularized multi-modal multi-discrimination sparse attention fusion generative adversarial network (GRMM-GAN) to avoid repeated contrast injections to patients and facilitate adaptive monitoring. METHODS: With IRB approval, 165 abdominal MR studies from 61 liver cancer patients were retrospectively solicited from our institutional database. Each study included T2, T1 pre-contrast (T1pre), and T1 contrast-enhanced (T1ce) images. The GRMM-GAN synthesis pipeline consists of a sparse attention fusion network, an image gradient regularizer (GR), and a generative adversarial network with multi-discrimination. The studies were randomly divided into 115 for training, 20 for validation, and 30 for testing. The two pre-contrast MR modalities, T2 and T1pre images, were adopted as inputs in the training phase. The T1ce image at the portal venous phase was used as an output. The synthesized T1ce images were compared with the ground truth T1ce images. The evaluation metrics include peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE). A Turing test and experts contours evaluated the image synthesis quality. RESULTS: The proposed GRMM-GAN model achieved a PSNR of 28.56, an SSIM of 0.869, and an MSE of 83.27. The proposed model showed statistically significant improvements in all metrics tested with p-values < 0.05 over the state-of-the-art model comparisons. The average Turing test score was 52.33%, which is close to random guessing, supporting the models effectiveness for clinical application. In the tumor-specific region analysis, the average tumor contrast-to-noise ratio (CNR) of the synthesized MR images was not statistically significant from the real MR images. The average DICE from real vs. synthetic images was 0.90 compared to the inter-operator DICE of 0.91. CONCLUSION: We demonstrated the function of a novel multi-modal MR image synthesis neural network GRMM-GAN for T1ce MR synthesis based on pre-contrast T1 and T2 MR images. GRMM-GAN shows promise for avoiding repeated contrast injections during radiation therapy treatment.

Published
2023

9. Numerical simulation of high-pressure CO2 pipeline venting and safe release

Author

LIU Xin, WANG Haifeng, YANG Teng, HU Qihui, YIN Buze, LI Yuxing, ZHU Jianlu, and ZHU Zhenyu

Subjects
co2 pipeline, ccus, venting simulation, safety relief, Oils, fats, and waxes, TP670-699, Gas industry, TP751-762
Abstract

[Objective] Carbon capture, utilization and storage(CCUS) is an indispensable technology for achieving carbon neutrality,and CO2 pipeline transmission is a significant component of this technology. In the process of supercritical CO2 pipeline transmission,unintentional pipeline leakage or venting operations may cause localized low temperatures in the trunk pipelines and vent piping due to the strong throttling effect caused by CO2, resulting in dry ice that blocks the pipeline and makes it brittle. [Methods] In the study, the OLGA software was utilized to develop a high-pressure CO2 pipeline relief model. The simulation results obtained from the model were then compared against foreign experimental data. The comparative analysis indicated that the OLGA software provided relatively accurate calculations for pressure drop and tended to be more conservative in calculating temperature drop. These findings supported the software's suitability for performing calculations related to the design of CO2 pipelines. Building upon this foundation, a long-distance high-pressure CO2 pipeline venting model was established to simulate and analyze the effects of different valve openings, initial temperatures, and initial pressures on temperature decrease, phase state changes, and venting duration during the CO2 pipeline venting process. [Results] It was revealed that reducing the vent valve opening effectively prevented excessively low temperatures within the pipeline during venting. Under the venting simulation conditions selected for this study, 13.5% valve opening effectively prevented dry ice formation, and the valve opening below 4.5% could maintain the pipeline temperature at higher than-30 ℃. The venting process of the high-pressure CO2 pipeline exhibited low convective heat transfer intensity and significant temperature drops, predominantly observed away from the relief port. The initial temperature had a substantial impact on the temperature in the pipeline during venting. More specifically, a lower initial temperature resulted in a decrease in the temperature in the pipeline during venting, increasing the likelihood of dry ice formation. [Conclusion] Therefore, in engineering practice, it is crucial to focus on fuid temperature in sections far from the relief port along the trunk pipelines and automatically reduce the vent valve opening in response to temperature drops, aiming to slow down the temperature drop rate during the venting process. Special attention should be paid to protecting CO2 pipelines, especially when operating under low-temperature dense phase conditions.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results