A deep learning algorithm to generate synthetic computed tomography images for brain treatments from 0.35 T magnetic resonance imaging

IF 3.4 Q2 ONCOLOGY

Physics and Imaging in Radiation Oncology Pub Date : 2025-01-01 DOI:10.1016/j.phro.2025.100708

Luca Vellini , Flaviovincenzo Quaranta , Sebastiano Menna , Elisa Pilloni , Francesco Catucci , Jacopo Lenkowicz , Claudio Votta , Michele Aquilano , Andrea D’Aviero , Martina Iezzi , Francesco Preziosi , Alessia Re , Althea Boschetti , Danila Piccari , Antonio Piras , Carmela Di Dio , Alessandro Bombini , Gian Carlo Mattiucci , Davide Cusumano

{"title":"A deep learning algorithm to generate synthetic computed tomography images for brain treatments from 0.35 T magnetic resonance imaging","authors":"Luca Vellini , Flaviovincenzo Quaranta , Sebastiano Menna , Elisa Pilloni , Francesco Catucci , Jacopo Lenkowicz , Claudio Votta , Michele Aquilano , Andrea D’Aviero , Martina Iezzi , Francesco Preziosi , Alessia Re , Althea Boschetti , Danila Piccari , Antonio Piras , Carmela Di Dio , Alessandro Bombini , Gian Carlo Mattiucci , Davide Cusumano","doi":"10.1016/j.phro.2025.100708","DOIUrl":null,"url":null,"abstract":"<div><h3>Background and Purpose</h3><div>The development of Magnetic Resonance Imaging (MRI)-only Radiotherapy (RT) represents a significant advancement in the field. This study introduces a Deep Learning (DL) algorithm designed to quickly generate synthetic CT (sCT) images from low-field MR images in the brain, an area not yet explored.</div></div><div><h3>Methods</h3><div>Fifty-six patients were divided into training (32), validation (8), and test (16) groups. A conditional Generative Adversarial Network (cGAN) was trained on pre-processed axial paired images. sCTs were validated using mean absolute error (MAE) and mean error (ME) calculated within the patient body. Intensity Modulated Radiation Therapy (IMRT) plans were optimised on simulation MRI and calculated considering sCT and original CT as electron density (ED) map. Dose distributions using sCT and CT were compared using global gamma analysis at different tolerance criteria (2 %/2mm and 3 %/3mm) and evaluating the difference in estimating different Dose Volume Histogram (DVH) parameters for target and organs at risk (OARs).</div></div><div><h3>Results</h3><div>The network generated sCTs of each single patient in less than two minutes (mean time = 103 ± 41 s). For test patients, the MAE was 62.1 ± 17.7 HU, and the ME was −7.3 ± 13.4 HU. Dose parameters on sCTs were within 0.5 Gy of those on original CTs. Gamma passing rates 2 %/2mm, and 3 %/3mm criteria were 99.5 %±0.5 %, and 99.7 %±0.3 %, respectively.</div></div><div><h3>Conclusion</h3><div>The proposed DL algorithm generates in less than 2 min accurate sCT images in the brain for online adaptive radiotherapy, potentially eliminating the need for CT simulation in MR-only workflows for brain treatments.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"33 ","pages":"Article 100708"},"PeriodicalIF":3.4000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Physics and Imaging in Radiation Oncology","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2405631625000132","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background and Purpose

The development of Magnetic Resonance Imaging (MRI)-only Radiotherapy (RT) represents a significant advancement in the field. This study introduces a Deep Learning (DL) algorithm designed to quickly generate synthetic CT (sCT) images from low-field MR images in the brain, an area not yet explored.

Methods

Fifty-six patients were divided into training (32), validation (8), and test (16) groups. A conditional Generative Adversarial Network (cGAN) was trained on pre-processed axial paired images. sCTs were validated using mean absolute error (MAE) and mean error (ME) calculated within the patient body. Intensity Modulated Radiation Therapy (IMRT) plans were optimised on simulation MRI and calculated considering sCT and original CT as electron density (ED) map. Dose distributions using sCT and CT were compared using global gamma analysis at different tolerance criteria (2 %/2mm and 3 %/3mm) and evaluating the difference in estimating different Dose Volume Histogram (DVH) parameters for target and organs at risk (OARs).

Results

The network generated sCTs of each single patient in less than two minutes (mean time = 103 ± 41 s). For test patients, the MAE was 62.1 ± 17.7 HU, and the ME was −7.3 ± 13.4 HU. Dose parameters on sCTs were within 0.5 Gy of those on original CTs. Gamma passing rates 2 %/2mm, and 3 %/3mm criteria were 99.5 %±0.5 %, and 99.7 %±0.3 %, respectively.

Conclusion

The proposed DL algorithm generates in less than 2 min accurate sCT images in the brain for online adaptive radiotherapy, potentially eliminating the need for CT simulation in MR-only workflows for brain treatments.

查看原文本刊更多论文

一种深度学习算法，从0.35 T磁共振成像中生成用于脑治疗的合成计算机断层扫描图像

背景与目的磁共振成像（MRI）放射治疗（RT）的发展代表了该领域的重大进步。本研究引入了一种深度学习（DL）算法，旨在从大脑中的低场MR图像快速生成合成CT （sCT）图像，这是一个尚未探索的领域。方法56例患者分为训练组（32例）、验证组（8例）和试验组（16例）。在预处理的轴对图像上训练条件生成对抗网络（cGAN）。使用患者体内计算的平均绝对误差（MAE）和平均误差（ME）验证sct。在模拟MRI上优化强度调制放射治疗（IMRT）方案，并考虑sCT和原始CT作为电子密度（ED）图进行计算。在不同容限标准（2% /2mm和3% /3mm）下，使用全局伽玛分析比较sCT和CT的剂量分布，并评估靶器官和危险器官（OARs）不同剂量体积直方图（DVH）参数估算的差异。结果该网络在不到2分钟的时间内（平均时间= 103±41 s）生成每位患者的sct，对于测试患者，MAE为62.1±17.7 HU， ME为−7.3±13.4 HU。sCTs的剂量参数与原始ct的剂量参数在0.5 Gy以内。Gamma通过率2% /2mm为99.5%±0.5%，3% /3mm为99.7%±0.3%。本文提出的DL算法在不到2分钟的时间内生成准确的脑部sCT图像，用于在线自适应放疗，潜在地消除了在仅mr的脑部治疗工作流程中对CT模拟的需要。

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