Abstract：
OBJECTIVE: Use a conference challenge format to compare machine learning-based gamma-aminobutyric acid (GABA)-edited magnetic resonance spectroscopy (MRS) reconstruction models using one-quarter of the transients typically acquired during a complete scan.
METHODS: There were three tracks: Track 1: simulated data, Track 2: identical acquisition parameters with in vivo data, and Track 3: different acquisition parameters with in vivo data. The mean squared error, signal-to-noise ratio, linewidth, and a proposed shape score metric were used to quantify model performance. Challenge organizers provided open access to a baseline model, simulated noise-free data, guides for adding synthetic noise, and in vivo data.
RESULTS: Three submissions were compared. A covariance matrix convolutional neural network model was most successful for Track 1. A vision transformer model operating on a spectrogram data representation was most successful for Tracks 2 and 3. Deep learning (DL) reconstructions with 80 transients achieved equivalent or better SNR, linewidth and fit error compared to conventional 320 transient reconstructions. However, some DL models optimized linewidth and SNR without actually improving overall spectral quality, indicating a need for more robust metrics.
CONCLUSIONS: DL-based reconstruction pipelines have the promise to reduce the number of transients required for GABA-edited MRS.
METHODS: There were three tracks: Track 1: simulated data, Track 2: identical acquisition parameters with in vivo data, and Track 3: different acquisition parameters with in vivo data. The mean squared error, signal-to-noise ratio, linewidth, and a proposed shape score metric were used to quantify model performance. Challenge organizers provided open access to a baseline model, simulated noise-free data, guides for adding synthetic noise, and in vivo data.
RESULTS: Three submissions were compared. A covariance matrix convolutional neural network model was most successful for Track 1. A vision transformer model operating on a spectrogram data representation was most successful for Tracks 2 and 3. Deep learning (DL) reconstructions with 80 transients achieved equivalent or better SNR, linewidth and fit error compared to conventional 320 transient reconstructions. However, some DL models optimized linewidth and SNR without actually improving overall spectral quality, indicating a need for more robust metrics.
CONCLUSIONS: DL-based reconstruction pipelines have the promise to reduce the number of transients required for GABA-edited MRS.
摘要：
目的：使用会议挑战格式来比较基于机器学习的γ-氨基丁酸（GABA）编辑的磁共振波谱（MRS）重建模型，该模型使用通常在完整扫描期间获得的瞬态的四分之一。
方法：有三条轨迹：轨迹1：模拟数据，轨道2：与体内数据相同的采集参数，和轨道3:具有体内数据的不同采集参数。均方误差，信噪比，线宽,并使用提出的形状得分度量来量化模型性能。挑战组织者提供了对基线模型的开放访问，模拟无噪声数据，添加合成噪声的指南，和体内数据。
结果：比较了三个提交。协方差矩阵卷积神经网络模型对于轨道1最为成功。在频谱图数据表示上运行的视觉变压器模型对于轨道2和3最为成功。具有80个瞬态的深度学习（DL）重建实现了等效或更好的SNR，与传统的320瞬态重建相比，线宽和拟合误差。然而,一些DL模型优化了线宽和信噪比，而实际上没有提高整体频谱质量，表明需要更稳健的指标。
结论：基于DL的重建管道有望减少GABA编辑的MRS所需的瞬态数量。
方法：有三条轨迹：轨迹1：模拟数据，轨道2：与体内数据相同的采集参数，和轨道3:具有体内数据的不同采集参数。均方误差，信噪比，线宽,并使用提出的形状得分度量来量化模型性能。挑战组织者提供了对基线模型的开放访问，模拟无噪声数据，添加合成噪声的指南，和体内数据。
结果：比较了三个提交。协方差矩阵卷积神经网络模型对于轨道1最为成功。在频谱图数据表示上运行的视觉变压器模型对于轨道2和3最为成功。具有80个瞬态的深度学习（DL）重建实现了等效或更好的SNR，与传统的320瞬态重建相比，线宽和拟合误差。然而,一些DL模型优化了线宽和信噪比，而实际上没有提高整体频谱质量，表明需要更稳健的指标。
结论：基于DL的重建管道有望减少GABA编辑的MRS所需的瞬态数量。
