1
|
Jiao C, Ling D, Bian S, Vassantachart A, Cheng K, Mehta S, Lock D, Zhu Z, Feng M, Thomas H, Scholey JE, Sheng K, Fan Z, Yang W. Contrast-Enhanced Liver Magnetic Resonance Image Synthesis Using Gradient Regularized Multi-Modal Multi-Discrimination Sparse Attention Fusion GAN. Cancers (Basel) 2023; 15:3544. [PMID: 37509207 PMCID: PMC10377331 DOI: 10.3390/cancers15143544] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2023] [Revised: 07/03/2023] [Accepted: 07/05/2023] [Indexed: 07/30/2023] Open
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 model's 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.
Collapse
Affiliation(s)
- Changzhe Jiao
- Department of Radiation Oncology, Keck School of Medicine of USC, Los Angeles, CA 90033, USA (A.V.); (S.M.)
- Department of Radiation Oncology, UC San Francisco, San Francisco, CA 94143, USA
| | - Diane Ling
- Department of Radiation Oncology, Keck School of Medicine of USC, Los Angeles, CA 90033, USA (A.V.); (S.M.)
| | - Shelly Bian
- Department of Radiation Oncology, Keck School of Medicine of USC, Los Angeles, CA 90033, USA (A.V.); (S.M.)
| | - April Vassantachart
- Department of Radiation Oncology, Keck School of Medicine of USC, Los Angeles, CA 90033, USA (A.V.); (S.M.)
| | - Karen Cheng
- Department of Radiation Oncology, Keck School of Medicine of USC, Los Angeles, CA 90033, USA (A.V.); (S.M.)
| | - Shahil Mehta
- Department of Radiation Oncology, Keck School of Medicine of USC, Los Angeles, CA 90033, USA (A.V.); (S.M.)
| | - Derrick Lock
- Department of Radiation Oncology, Keck School of Medicine of USC, Los Angeles, CA 90033, USA (A.V.); (S.M.)
| | - Zhenyu Zhu
- Guangzhou Institute of Technology, Xidian University, Guangzhou 510555, China;
| | - Mary Feng
- Department of Radiation Oncology, UC San Francisco, San Francisco, CA 94143, USA
| | - Horatio Thomas
- Department of Radiation Oncology, UC San Francisco, San Francisco, CA 94143, USA
| | - Jessica E. Scholey
- Department of Radiation Oncology, UC San Francisco, San Francisco, CA 94143, USA
| | - Ke Sheng
- Department of Radiation Oncology, UC San Francisco, San Francisco, CA 94143, USA
| | - Zhaoyang Fan
- Department of Radiology, Keck School of Medicine of USC, Los Angeles, CA 90033, USA
| | - Wensha Yang
- Department of Radiation Oncology, Keck School of Medicine of USC, Los Angeles, CA 90033, USA (A.V.); (S.M.)
- Department of Radiation Oncology, UC San Francisco, San Francisco, CA 94143, USA
| |
Collapse
|
2
|
Kraus RD, Weil CR, Abdel-Wahab M. Benefits of Adopting Hypofractionated Radiotherapy as a Standard of Care in Low-and Middle-Income Countries. JCO Glob Oncol 2022; 8:e2200215. [PMID: 36525619 PMCID: PMC10166538 DOI: 10.1200/go.22.00215] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022] Open
Affiliation(s)
- Ryan D Kraus
- Department of Radiation Oncology, Huntsman Cancer Institute, University of Utah, Salt Lake City, UT
| | - Christopher R Weil
- Department of Radiation Oncology, Huntsman Cancer Institute, University of Utah, Salt Lake City, UT
| | - May Abdel-Wahab
- Division of Human Health, International Atomic Energy Agency, Vienna, Austria
| |
Collapse
|