T1-contrast enhanced MRI generation from multi-parametric MRI for glioma patients with latent tumor conditioning

IF 3.2 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Medical physics Pub Date : 2024-12-23 DOI:10.1002/mp.17600

Zach Eidex, Mojtaba Safari, Richard L. J. Qiu, David S. Yu, Hui-Kuo Shu, Hui Mao, Xiaofeng Yang

{"title":"T1-contrast enhanced MRI generation from multi-parametric MRI for glioma patients with latent tumor conditioning","authors":"Zach Eidex, Mojtaba Safari, Richard L. J. Qiu, David S. Yu, Hui-Kuo Shu, Hui Mao, Xiaofeng Yang","doi":"10.1002/mp.17600","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Gadolinium-based contrast agents (GBCAs) are commonly used in MRI scans of patients with gliomas to enhance brain tumor characterization using T1-weighted (T1W) MRI. However, there is growing concern about GBCA toxicity. This study develops a deep-learning framework to generate T1-postcontrast (T1C) from pre-contrast multiparametric MRI.</p>\n </section>\n \n <section>\n \n <h3> Purpose</h3>\n \n <p>We propose the tumor-aware vision transformer (TA-ViT) model that predicts high-quality T1C images. The predicted tumor region is significantly improved (<i>p</i> < 0.001) by conditioning the transformer layers from predicted segmentation maps through the adaptive layer norm zero mechanism. The predicted segmentation maps were generated with the multi-parametric residual (MPR) ViT model and transformed into a latent space to produce compressed, feature-rich representations. The TA-ViT model was applied to T1w and T2-FLAIR to predict T1C MRI images of 501 glioma cases from an open-source dataset. Selected patients were split into training (<i>N</i> = 400), validation (<i>N</i> = 50), and test (<i>N</i> = 51) sets. Model performance was evaluated with the peak-signal-to-noise ratio (PSNR), normalized cross-correlation (NCC), and normalized mean squared error (NMSE).</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>Both qualitative and quantitative results demonstrate that the TA-ViT model performs superior against the benchmark MPR-ViT model. Our method produces synthetic T1C MRI with high soft tissue contrast and more accurately synthesizes both the tumor and whole brain volumes. The synthesized T1C images achieved remarkable improvements in both tumor and healthy tissue regions compared to the MPR-ViT model. For healthy tissue and tumor regions, the results were as follows: NMSE: 8.53 ± 4.61E-4; PSNR: 31.2 ± 2.2; NCC: 0.908 ± 0.041 and NMSE: 1.22 ± 1.27E-4, PSNR: 41.3 ± 4.7, and NCC: 0.879 ± 0.042, respectively.</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>The proposed method generates synthetic T1C images that closely resemble real T1C images. Future development and application of this approach may enable contrast-agent-free MRI for brain tumor patients, eliminating the risk of GBCA toxicity and simplifying the MRI scan protocol.</p>\n </section>\n </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 4","pages":"2064-2073"},"PeriodicalIF":3.2000,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical physics","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/mp.17600","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Gadolinium-based contrast agents (GBCAs) are commonly used in MRI scans of patients with gliomas to enhance brain tumor characterization using T1-weighted (T1W) MRI. However, there is growing concern about GBCA toxicity. This study develops a deep-learning framework to generate T1-postcontrast (T1C) from pre-contrast multiparametric MRI.

Purpose

We propose the tumor-aware vision transformer (TA-ViT) model that predicts high-quality T1C images. The predicted tumor region is significantly improved (p < 0.001) by conditioning the transformer layers from predicted segmentation maps through the adaptive layer norm zero mechanism. The predicted segmentation maps were generated with the multi-parametric residual (MPR) ViT model and transformed into a latent space to produce compressed, feature-rich representations. The TA-ViT model was applied to T1w and T2-FLAIR to predict T1C MRI images of 501 glioma cases from an open-source dataset. Selected patients were split into training (N = 400), validation (N = 50), and test (N = 51) sets. Model performance was evaluated with the peak-signal-to-noise ratio (PSNR), normalized cross-correlation (NCC), and normalized mean squared error (NMSE).

Results

Both qualitative and quantitative results demonstrate that the TA-ViT model performs superior against the benchmark MPR-ViT model. Our method produces synthetic T1C MRI with high soft tissue contrast and more accurately synthesizes both the tumor and whole brain volumes. The synthesized T1C images achieved remarkable improvements in both tumor and healthy tissue regions compared to the MPR-ViT model. For healthy tissue and tumor regions, the results were as follows: NMSE: 8.53 ± 4.61E-4; PSNR: 31.2 ± 2.2; NCC: 0.908 ± 0.041 and NMSE: 1.22 ± 1.27E-4, PSNR: 41.3 ± 4.7, and NCC: 0.879 ± 0.042, respectively.

Conclusion

The proposed method generates synthetic T1C images that closely resemble real T1C images. Future development and application of this approach may enable contrast-agent-free MRI for brain tumor patients, eliminating the risk of GBCA toxicity and simplifying the MRI scan protocol.

查看原文本刊更多论文

具有潜伏性肿瘤条件的胶质瘤患者的多参数MRI t1增强MRI生成。

背景：钆基对比剂（gbca）通常用于胶质瘤患者的MRI扫描，以增强t1加权（T1W） MRI对脑肿瘤的表征。然而，人们越来越关注GBCA的毒性。本研究开发了一个深度学习框架，从对比前的多参数MRI生成t1 -对比后（T1C）。目的：我们提出肿瘤感知视觉变压器（TA-ViT）模型来预测高质量的T1C图像。通过自适应层范数零机制调节来自预测分割图的变压器层，可显著改善预测的肿瘤区域（p < 0.001）。使用多参数残差（MPR） ViT模型生成预测的分割图，并将其转换为潜在空间以产生压缩的、特征丰富的表示。将TA-ViT模型应用于T1w和T2-FLAIR，预测来自开源数据集的501例胶质瘤病例的T1C MRI图像。所选患者分为训练组（N = 400）、验证组（N = 50）和测试组（N = 51）。通过峰值信噪比（PSNR）、归一化相互关系（NCC）和归一化均方误差（NMSE）来评估模型的性能。结果：定性和定量结果表明，TA-ViT模型优于基准MPR-ViT模型。我们的方法产生的合成T1C MRI具有较高的软组织对比度，更准确地合成肿瘤和全脑体积。与MPR-ViT模型相比，合成的T1C图像在肿瘤和健康组织区域均取得了显着改善。正常组织和肿瘤区NMSE: 8.53±4.61E-4；Psnr: 31.2±2.2；NCC: 0.908±0.041,NMSE: 1.22±1.27E-4, PSNR: 41.3±4.7,NCC: 0.879±0.042。结论：该方法生成的T1C合成图像与真实的T1C图像接近。该方法的未来发展和应用可能使脑肿瘤患者无需造影剂的MRI，消除GBCA毒性的风险，简化MRI扫描方案。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Medical physics 医学-核医学

CiteScore

6.80

自引率

15.80%

发文量

660

审稿时长

1.7 months

期刊介绍： Medical Physics publishes original, high impact physics, imaging science, and engineering research that advances patient diagnosis and therapy through contributions in 1) Basic science developments with high potential for clinical translation 2) Clinical applications of cutting edge engineering and physics innovations 3) Broadly applicable and innovative clinical physics developments Medical Physics is a journal of global scope and reach. By publishing in Medical Physics your research will reach an international, multidisciplinary audience including practicing medical physicists as well as physics- and engineering based translational scientists. We work closely with authors of promising articles to improve their quality.