Graduate School of Medicine, University of Tokyo, Tokyo, Japan.
Institute of Mathematics for Industry, Kyushu University, Motooka, Nishi-ku, Fukuoka, Japan.
Med Phys. 2022 Jun;49(6):3769-3782. doi: 10.1002/mp.15626. Epub 2022 Apr 17.
In recent years, deep learning-based image processing has emerged as a valuable tool for medical imaging owing to its high performance. However, the quality of deep learning-based methods heavily relies on the amount of training data; the high cost of acquiring a large data set is a limitation to their utilization in medical fields. Herein, based on deep learning, we developed a computed tomography (CT) modality conversion method requiring only a few unsupervised images.
The proposed method is based on cycle-consistency generative adversarial network (CycleGAN) with several extensions tailored for CT images, which aims at preserving the structure in the processed images and reducing the amount of training data. This method was applied to realize the conversion of megavoltage computed tomography (MVCT) to kilovoltage computed tomography (kVCT) images. Training was conducted using several data sets acquired from patients with head and neck cancer. The size of the data sets ranged from 16 slices (two patients) to 2745 slices (137 patients) for MVCT and 2824 slices (98 patients) for kVCT.
The required size of the training data was found to be as small as a few hundred slices. By statistical and visual evaluations, the quality improvement and structure preservation of the MVCT images converted by the proposed model were investigated. As a clinical benefit, it was observed by medical doctors that the converted images enhanced the precision of contouring.
We developed an MVCT to kVCT conversion model based on deep learning, which can be trained using only a few hundred unpaired images. The stability of the model against changes in data size was demonstrated. This study promotes the reliable use of deep learning in clinical medicine by partially answering commonly asked questions, such as "Is our data sufficient?" and "How much data should we acquire?"
近年来，基于深度学习的图像处理技术因其高性能而成为医学成像的一种有价值的工具。然而，深度学习方法的质量严重依赖于训练数据的数量；获取大量数据集的成本高，限制了它们在医学领域的应用。在此，我们基于深度学习，开发了一种仅需少量无监督图像的计算机断层扫描（CT）模式转换方法。
所提出的方法基于循环一致性生成对抗网络（CycleGAN），并针对 CT 图像进行了一些扩展，旨在保留处理图像中的结构并减少训练数据量。该方法应用于实现兆伏 CT（MVCT）到千伏 CT（kVCT）图像的转换。使用从头颈癌患者中获取的多个数据集进行了训练。MVCT 的数据集大小范围从 16 个切片（两个患者）到 2745 个切片（137 个患者），kVCT 的数据集大小为 2824 个切片（98 个患者）。
发现所需的训练数据大小小至几百个切片。通过统计和视觉评估，研究了所提出的模型转换的 MVCT 图像的质量提高和结构保留。作为临床益处，医生观察到转换后的图像提高了轮廓的精度。
我们开发了一种基于深度学习的 MVCT 到 kVCT 转换模型，仅需几百张未配对的图像即可进行训练。该模型对数据大小变化的稳定性得到了证明。本研究通过部分回答常见问题，如“我们的数据是否足够？”和“我们应该获取多少数据？”，促进了深度学习在临床医学中的可靠应用。
