Gifford Ryan, Jhawar Sachin R, Krening Samantha
Department of Integrated Systems Engineering, The Ohio State University, 1971 Neil Ave, Columbus, OH 43210, USA.
Comprehensive Cancer Center, Department of Radiation Oncology, The Ohio State University, 410 W 10th Ave, Columbus, OH 43210, USA.
Diagnostics (Basel). 2023 Jun 24;13(13):2159. doi: 10.3390/diagnostics13132159.
Deep learning (DL) methods have shown great promise in auto-segmentation problems. However, for head and neck cancer, we show that DL methods fail at the axial edges of the gross tumor volume (GTV) where the segmentation is dependent on information closer to the center of the tumor. These failures may decrease trust and usage of proposed auto-contouring systems. To increase performance at the axial edges, we propose the spatially adjusted recurrent convolution U-Net (SARC U-Net). Our method uses convolutional recurrent neural networks and spatial transformer networks to push information from salient regions out to the axial edges. On average, our model increased the Sørensen-Dice coefficient (DSC) at the axial edges of the GTV by 11% inferiorly and 19.3% superiorly over a baseline 2D U-Net, which has no inherent way to capture information between adjacent slices. Over all slices, our proposed architecture achieved a DSC of 0.613, whereas a 3D and 2D U-Net achieved a DSC of 0.586 and 0.540, respectively. SARC U-Net can increase accuracy at the axial edges of GTV contours while also increasing accuracy over baseline models, creating a more robust contour.
深度学习（DL）方法在自动分割问题上已展现出巨大潜力。然而，对于头颈癌，我们发现DL方法在大体肿瘤体积（GTV）的轴向边缘处表现不佳，在这些位置分割依赖于更靠近肿瘤中心的信息。这些失败可能会降低对所提出的自动轮廓系统的信任和使用。为了提高轴向边缘处的性能，我们提出了空间调整循环卷积U-Net（SARC U-Net）。我们的方法使用卷积循环神经网络和空间变换网络将来自显著区域的信息推送到轴向边缘。平均而言，相较于没有内在方法来捕捉相邻切片之间信息的基线二维U-Net，我们的模型在GTV轴向边缘处将索伦森-戴斯系数（DSC）在下方提高了11%，在上方提高了19.3%。在所有切片上，我们提出的架构实现了0.613的DSC，而三维和二维U-Net分别实现了0.586和0.540的DSC。SARC U-Net可以提高GTV轮廓轴向边缘处的准确性，同时相对于基线模型也提高了准确性，从而创建更稳健的轮廓。
