Department of Radiation Oncology and Winship Cancer Institute, Emory University, School of Medicine, Atlanta, Georgia, USA.
Med Phys. 2023 Jan;50(1):274-283. doi: 10.1002/mp.16001. Epub 2022 Oct 13.
Multimodality positron emission tomography/computed tomography (PET/CT) imaging combines the anatomical information of CT with the functional information of PET. In the diagnosis and treatment of many cancers, such as non-small cell lung cancer (NSCLC), PET/CT imaging allows more accurate delineation of tumor or involved lymph nodes for radiation planning.
In this paper, we propose a hybrid regional network method of automatically segmenting lung tumors from PET/CT images.
The hybrid regional network architecture synthesizes the functional and anatomical information from the two image modalities, whereas the mask regional convolutional neural network (R-CNN) and scoring fine-tune the regional location and quality of the output segmentation. This model consists of five major subnetworks, that is, a dual feature representation network (DFRN), a regional proposal network (RPN), a specific tumor-wise R-CNN, a mask-Net, and a score head. Given a PET/CT image as inputs, the DFRN extracts feature maps from the PET and CT images. Then, the RPN and R-CNN work together to localize lung tumors and reduce the image size and feature map size by removing irrelevant regions. The mask-Net is used to segment tumor within a volume-of-interest (VOI) with a score head evaluating the segmentation performed by the mask-Net. Finally, the segmented tumor within the VOI was mapped back to the volumetric coordinate system based on the location information derived via the RPN and R-CNN. We trained, validated, and tested the proposed neural network using 100 PET/CT images of patients with NSCLC. A fivefold cross-validation study was performed. The segmentation was evaluated with two indicators: (1) multiple metrics, including the Dice similarity coefficient, Jacard, 95th percentile Hausdorff distance, mean surface distance (MSD), residual mean square distance, and center-of-mass distance; (2) Bland-Altman analysis and volumetric Pearson correlation analysis.
In fivefold cross-validation, this method achieved Dice and MSD of 0.84 ± 0.15 and 1.38 ± 2.2 mm, respectively. A new PET/CT can be segmented in 1 s by this model. External validation on The Cancer Imaging Archive dataset (63 PET/CT images) indicates that the proposed model has superior performance compared to other methods.
The proposed method shows great promise to automatically delineate NSCLC tumors on PET/CT images, thereby allowing for a more streamlined clinical workflow that is faster and reduces physician effort.
正电子发射断层扫描/计算机断层扫描（PET/CT）成像将 CT 的解剖信息与 PET 的功能信息结合在一起。在许多癌症的诊断和治疗中，如非小细胞肺癌（NSCLC），PET/CT 成像可以更准确地勾画肿瘤或受累淋巴结以进行放射规划。
本文提出了一种从 PET/CT 图像中自动分割肺肿瘤的混合区域网络方法。
混合区域网络架构综合了两种图像模态的功能和解剖信息，而掩模区域卷积神经网络（R-CNN）和评分则对输出分割的区域位置和质量进行微调。该模型由五个主要子网组成，即双特征表示网络（DFRN）、区域建议网络（RPN）、特定肿瘤的 R-CNN、掩模网络和评分头。给定一个 PET/CT 图像作为输入，DFRN 从 PET 和 CT 图像中提取特征图。然后，RPN 和 R-CNN 一起工作，通过去除不相关区域来定位肺肿瘤并减小图像大小和特征图大小。掩模网络用于在感兴趣体积（VOI）内分割肿瘤，并使用评分头评估掩模网络执行的分割。最后，根据 RPN 和 R-CNN 得出的位置信息，将 VOI 内分割的肿瘤映射回体积坐标系。我们使用 100 例 NSCLC 患者的 PET/CT 图像对所提出的神经网络进行了训练、验证和测试。进行了五折交叉验证研究。使用两个指标评估分割：（1）多个指标，包括 Dice 相似系数、Jacard、95%Hausdorff 距离、平均表面距离（MSD）、残差均方距离和质心距离；（2）Bland-Altman 分析和体积 Pearson 相关分析。
在五折交叉验证中，该方法的 Dice 和 MSD 分别达到 0.84±0.15 和 1.38±2.2mm。通过该模型可以在 1s 内分割新的 PET/CT。在 The Cancer Imaging Archive 数据集（63 个 PET/CT 图像）上的外部验证表明，与其他方法相比，所提出的模型具有更好的性能。
该方法有望自动勾画 NSCLC 肿瘤的 PET/CT 图像，从而允许更流畅的临床工作流程，速度更快，减少医生的工作量。
