Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs
Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs
复制标题
DOI：
10.1007/s12194-021-00630-6
复制
发表时间：
2021-07-12
影响因子：
1.6
通讯作者：
Shigematsu, Naoyuki
中科院分区：
文献类型：
--
作者：
Nemoto, Takafumi;Futakami, Natsumi;Shigematsu, Naoyuki
深度学习已证明在轮廓描绘中自动分割具有高效能，这对于放射治疗规划至关重要。然而，医学成像数据的收集、标记和管理可能具有挑战性。本研究旨在阐明样本大小和数据增强对使用深度学习方法 U-Net 自动分割计算机断层扫描图像的影响。对于胸部和骨盆区域，分别评估了 232 例和 556 例。我们通过在广泛的值范围内更改训练和验证数据集的总和来调查多种条件：胸部和骨盆区域分别为 10-200 和 10-500 例。构建了 U-Net，并在每个训练会话中将水平翻转数据增强与无增强进行比较，水平翻转数据增强会产生左右反转图像，从而使图像数量增加两倍。所有肺部病例以及 100 多个前列腺、膀胱和直肠病例表明，添加水平翻转数据增强几乎与病例数加倍一样有效。所有器官的 Dice 相似系数 (DSC) 的斜率在大约 100 例之前迅速下降，在 200 例后稳定，并随着病例数的进一步增加而显示出最小的变化。通过在除心脏之外的所有器官中加入数据增强，DSC 可以稳定在较小的样本量。这一发现适用于罕见癌症放射治疗的自动化，因为在这些癌症中可能很难获得大量数据集。
Deep learning has demonstrated high efficacy for automatic segmentation in contour delineation, which is crucial in radiation therapy planning. However, the collection, labeling, and management of medical imaging data can be challenging. This study aims to elucidate the effects of sample size and data augmentation on the automatic segmentation of computed tomography images using U-Net, a deep learning method. For the chest and pelvic regions, 232 and 556 cases are evaluated, respectively. We investigate multiple conditions by changing the sum of the training and validation datasets across a broad range of values: 10-200 and 10-500 cases for the chest and pelvic regions, respectively. A U-Net is constructed, and horizontal-flip data augmentation, which produces left and right inverse images resulting in twice the number of images, is compared with no augmentation for each training session. All lung cases and more than 100 prostate, bladder, and rectum cases indicate that adding horizontal-flip data augmentation is almost as effective as doubling the number of cases. The slope of the Dice similarity coefficient (DSC) in all organs decreases rapidly until approximately 100 cases, stabilizes after 200 cases, and shows minimal changes as the number of cases is increased further. The DSCs stabilize at a smaller sample size with the incorporation of data augmentation in all organs except the heart. This finding is applicable to the automation of radiation therapy for rare cancers, where large datasets may be difficult to obtain.