Zaffino Paolo, Raggio Ciro Benito, Thummerer Adrian, Marmitt Gabriel Guterres, Langendijk Johannes Albertus, Procopio Anna, Cosentino Carlo, Seco Joao, Knopf Antje Christin, Both Stefan, Spadea Maria Francesca
Department of Experimental and Clinical Medicine, Magna Graecia University, viale Europa, 88100 Catanzaro, Italy.
Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, 9712 CP Groningen, The Netherlands.
J Imaging. 2024 Dec 10;10(12):316. doi: 10.3390/jimaging10120316.
In recent years, synthetic Computed Tomography (CT) images generated from Magnetic Resonance (MR) or Cone Beam Computed Tomography (CBCT) acquisitions have been shown to be comparable to real CT images in terms of dose computation for radiotherapy simulation. However, until now, there has been no independent strategy to assess the quality of each synthetic image in the absence of ground truth. In this work, we propose a Deep Learning (DL)-based framework to predict the accuracy of synthetic CT in terms of Mean Absolute Error (MAE) without the need for a ground truth (GT). The proposed algorithm generates a volumetric map as an output, informing clinicians of the predicted MAE slice-by-slice. A cascading multi-model architecture was used to deal with the complexity of the MAE prediction task. The workflow was trained and tested on two cohorts of head and neck cancer patients with different imaging modalities: 27 MR scans and 33 CBCT. The algorithm evaluation revealed an accurate HU prediction (a median absolute prediction deviation equal to 4 HU for CBCT-based synthetic CTs and 6 HU for MR-based synthetic CTs), with discrepancies that do not affect the clinical decisions made on the basis of the proposed estimation. The workflow exhibited no systematic error in MAE prediction. This work represents a proof of concept about the feasibility of synthetic CT evaluation in daily clinical practice, and it paves the way for future patient-specific quality assessment strategies.
近年来，由磁共振（MR）或锥束计算机断层扫描（CBCT）采集生成的合成计算机断层扫描（CT）图像，在放疗模拟剂量计算方面已被证明与真实CT图像相当。然而，到目前为止，在没有地面真值的情况下，还没有独立的策略来评估每个合成图像的质量。在这项工作中，我们提出了一个基于深度学习（DL）的框架，用于在不需要地面真值（GT）的情况下，根据平均绝对误差（MAE）预测合成CT的准确性。所提出的算法生成一个体积图作为输出，逐片向临床医生告知预测的MAE。使用了一种级联多模型架构来处理MAE预测任务的复杂性。该工作流程在两组具有不同成像模式的头颈癌患者中进行了训练和测试：27例MR扫描和33例CBCT。算法评估显示HU预测准确（基于CBCT的合成CT的中位数绝对预测偏差等于4 HU，基于MR的合成CT的中位数绝对预测偏差等于6 HU），其差异不影响基于所提出估计做出的临床决策。该工作流程在MAE预测中没有表现出系统误差。这项工作证明了在日常临床实践中进行合成CT评估的可行性，为未来针对患者的质量评估策略铺平了道路。
