斯温皮克斯:基于斯温变压器的Pix2Pix框架,用于低剂量PET排泄,使用多级输入来实现标准剂量质量
Mohammad Saber Azimi1,2, Vahid Felfelian3, Habibollah Dadgar4
1Doctoral School of Applied Informatics and Applied Mathematics, Óbuda University, Budapest, Hungary.
Journal of imaging informatics in medicine
|March 10, 2026
概括
一个新的网络SwinPix有效地使用多层低剂量PET图像来改善标准剂量PET图像的预测. 多输入的SwinPix模型显著提高图像质量和病变量化,以获得精确的PET成像.
科学领域:
- 医疗成像医学成像
- 医疗保健中的人工智能
- 辐射物理学 辐射物理学
背景情况:
- 低剂量 (LD) 阳离子发射断层扫描 (PET) 图像提供了减少的辐射暴露,但往往遭受图像质量差.
- 从LD输入中重建标准剂量 (SD) PET图像对于提高诊断准确性和患者安全至关重要.
- 现有的方法可能无法充分利用多层次LD PET数据中的信息.
研究的目的:
- 引入和评估SwinPix,一个新的网络架构用于PET图像预测,使用多级LD PET输入.
- 为了比较单输入与多输入的SwinPix模型在不同LD级别 (4%,6%,10%) 的性能.
- 评估SwinPix与Pix2Pix和PET重建的Swin变压器等既有模型的有效性.
主要方法:
- 开发了基于混合变压器的生成对抗网络 (GAN) 架构SwinPix.
- 训练并评估了六种模型:单输入 (4%,6%,10% LD) 和多输入 (结合三个 LD 级别) SwinPix.
- 在头部区域和恶性病变中使用SSIM,PSNR,SUV平均偏差,SUVmax偏差和RMSE量化评估性能.
主要成果:
- 多输入的SwinPix模型在所有LD级别中始终优于单输入模型.
- 在4%的LD,SwinPix表现出显著的改善:PSNR增加13%,RMSE减少82-86%,SUV偏差大幅减少.
- 与Pix2Pix和Swin Transformer相比,SwinPix实现了优越的重建质量,具有统计学上显著的改进 (p < 0.01).
结论:
- 多级LD PET输入在SwinPix架构中使用时,显著提高SD PET图像预测的准确性和质量.
- 斯温皮克斯为LD PET重建提供了强大且计算效率高的解决方案,改善了病变量化.
- 这些发现支持SwinPix的临床潜力,用于更准确,更安全的PET成像.
相关概念视频
01:20Deconvolution
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
01:20Downsampling
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
01:22Upsampling
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...