Meng Chang, Nagy James
Department of Mathematics, Emory University, 400 Dowman Drive, Atlanta, GA 30322 USA.
Numer Algorithms. 2023;92(1):831-847. doi: 10.1007/s11075-022-01451-3. Epub 2022 Dec 19.
Computed tomography (CT) techniques are well known for their ability to produce high-quality images needed for medical diagnostic purposes. Unfortunately, standard CT machines are extremely large, heavy, require careful and regular calibration, and are expensive, which can limit their availability in point-of-care situations. An alternative approach is to use portable machines, but parameters related to the geometry of these devices (e.g., distance between source and detector, orientation of source to detector) cannot always be precisely calibrated, and these parameters may change slightly when the machine is adjusted during the image acquisition process. In this work, we describe the non-linear inverse problem that models this situation, and discuss algorithms that can jointly estimate the geometry parameters and compute a reconstructed image. In particular, we propose a hybrid machine learning and block coordinate descent (ML-BCD) approach that uses an ML model to calibrate geometry parameters, and uses BCD to refine the predicted parameters and reconstruct the imaged object simultaneously. We show using numerical experiments that our new method can efficiently improve the accuracy of both the image and geometry parameters.
计算机断层扫描（CT）技术以其生成医学诊断所需高质量图像的能力而闻名。不幸的是，标准CT机器极其庞大、笨重，需要仔细且定期校准，并且价格昂贵，这可能会限制它们在即时医疗场景中的可用性。一种替代方法是使用便携式机器，但与这些设备几何形状相关的参数（例如，源与探测器之间的距离、源相对于探测器的方向）并不总是能够精确校准，并且在图像采集过程中调整机器时，这些参数可能会略有变化。在这项工作中，我们描述了对这种情况进行建模的非线性逆问题，并讨论了能够联合估计几何参数并计算重建图像的算法。特别是，我们提出了一种混合机器学习和块坐标下降（ML-BCD）方法，该方法使用机器学习模型来校准几何参数，并使用块坐标下降法同时细化预测参数并重建成像对象。我们通过数值实验表明，我们的新方法可以有效地提高图像和几何参数的准确性。
