大脑MRI合成的生成对抗网络:训练集大小对临床应用的影响
M M Zoghby1, B J Erickson1, G M Conte2
1Department of Radiology, Mayo Clinic, Rochester, MN, USA.
Journal of imaging informatics in medicine
|February 17, 2024
概括
用于合成大脑MRI序列的生成对抗网络 (GAN) 显示出与训练集大小无关的类似性能. 这使得GAN成为罕见疾病和资源有限的环境中可行的工具.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
背景情况:
- 生成对抗网络 (GAN) 越来越多地用于医疗图像合成.
- 评估训练数据大小的影响对于优化临床应用中的GAN性能至关重要.
研究的目的:
- 评估训练集大小如何影响GAN在合成脑MRI序列 (前对比T1和FLAIR) 的性能.
- 将GAN生成的MRI与原始图像进行比较,并评估它们在下游细分任务中的实用性.
主要方法:
- 训练了三组GAN:基线 (135例),早期检查点 (1251例) 和晚期检查点 (1251例).
- 模型从后对比T1生成了前对比T1 (gT1),并从T2生成了FLAIR (gFLAIR).
- 使用结构相似性指数 (SSI) 和平均平方误差 (MSE) 评估了485个结质瘤的测试组的性能.
- 合成的MRI被用作细分模型的输入,结果与使用子相似系数 (DSC) 的原始细分相比较.
主要成果:
- 在较小的数据集 (135个案例) 上训练的GAN的表现与在显著更大的数据集 (1251个案例) 上训练的GAN相比.
- 对于gT1,中位数SSI范围从0.918到0.957,中位数MSE范围从0.006到0.014.
- 对于gFLAIR,中位数SSI在0.908到0.924之间,中位数MSE在0.016到0.019之间.
- 细分性能 (DSC) 显示了广泛的范围 (.420-.955),但在不同训练集大小中总体上是可比的.
结论:
- 训练组的大小对脑MRI合成GAN的性能影响有限.
- GAN是生成合成大脑MRI序列的实用和有效工具,即使训练数据有限.
- 这种方法对于罕见疾病和数据资源有限的机构尤其有价值.
相关概念视频
Imaging Studies I: CT and MRI
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
Brain Imaging
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).
Imaging Studies IV: Magnetic Resonance Imaging
Introduction:Magnetic Resonance Imaging, or MRI, can include a specialized imaging technique of the urinary system known as Magnetic Resonance Urography (MRU). This radiation-free technique uses strong magnetic fields and radio waves to produce detailed images with the help of a computer. MRU is particularly effective for visualizing fluid-filled structures like the kidneys, ureters, and bladder.Applications of MRI in the Genitourinary SystemKidneys and Ureters: MRI detects tumors, cysts,...


