Department of Electronics and Information Systems, Medical Image and Signal Processing (MEDISIP), Ghent University, Ghent, Belgium.
Phys Med Biol. 2021 Mar 23;66(7). doi: 10.1088/1361-6560/abebfc.
To detect gamma rays with good spatial, timing and energy resolution while maintaining high sensitivity we need accurate and efficient algorithms to estimate the first gamma interaction position from the measured light distribution. Furthermore, monolithic detectors are investigated as an alternative to pixelated detectors due to increased sensitivity, resolution and intrinsic DOI encoding. Monolithic detectors, however, are challenging because of complicated calibration setups and edge effects. In this work, we evaluate the use of neural networks to estimate the 3D first (Compton or photoelectric) interaction position. Using optical simulation data of a 50 × 50 × 16 mmLYSO crystal, performance is evaluated as a function of network complexity (two to five hidden layers with 64 to 1024 neurons) and amount of training data (1000-8000 training events per calibration position). We identify and address the potential pitfall of overfitting on the training grid through evaluation on intermediate positions that are not in the training set. Additionally, the performance of neural networks is directly compared with nearest neighbour positioning. Optimal performance was achieved with a network containing three hidden layers of 256 neurons trained on 1000 events/position. For more complex networks, the performance degrades at intermediate positions and overfitting starts to occur. A median 3D positioning error of 0.77 mm and a 2D FWHM of 0.46 mm is obtained. This is a 17% improvement in terms of FWHM compared to the nearest neighbour algorithm. Evaluation only on events that are not Compton scattered results in a 3D positioning error of 0.40 mm and 2D FWHM of 0.42 mm. This reveals that Compton scatter results in a considerable increase of 93% in positioning error. This study demonstrates that very good spatial resolutions can be achieved with neural networks, superior to nearest neighbour positioning. However, potential overfitting on the training grid should be carefully evaluated.
为了在保持高灵敏度的同时，实现对伽马射线的良好空间、时间和能量分辨率，我们需要准确且高效的算法来从测量的光分布中估计首次伽马相互作用的位置。此外，由于灵敏度、分辨率和固有 DOI 编码的提高，单片探测器被研究作为像素探测器的替代方案。然而，由于复杂的校准设置和边缘效应，单片探测器具有挑战性。在这项工作中，我们评估了使用神经网络来估计 3D 首次（康普顿或光电）相互作用位置。使用 50×50×16mmLYSO 晶体的光学模拟数据，作为网络复杂性（两个到五个隐藏层，具有 64 到 1024 个神经元）和训练数据量（每个校准位置 1000-8000 个训练事件）的函数来评估性能。我们通过评估不在训练集中的中间位置，识别并解决了在训练网格上过度拟合的潜在陷阱。此外，还直接比较了神经网络和最近邻定位的性能。使用包含三个隐藏层、每个位置训练 1000 个事件的 256 个神经元的网络可以实现最佳性能。对于更复杂的网络，中间位置的性能会下降，并且开始出现过拟合。获得的中位数 3D 定位误差为 0.77mm，2D FWHM 为 0.46mm。与最近邻算法相比，这在 FWHM 方面提高了 17%。仅对未发生康普顿散射的事件进行评估，得到的 3D 定位误差为 0.40mm，2D FWHM 为 0.42mm。这表明康普顿散射导致定位误差增加了 93%。这项研究表明，神经网络可以实现非常好的空间分辨率，优于最近邻定位。然而，应该仔细评估在训练网格上的潜在过拟合。
