College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110004, People's Republic of China.
Department of Electrical and Computer Engineering, Steven Institute of Technology, Hoboken, NJ 07102, United States of America.
Phys Med Biol. 2023 Sep 12;68(18). doi: 10.1088/1361-6560/acede6.
. Whole-body positron emission tomography/computed tomography (PET/CT) scans are an important tool for diagnosing various malignancies (e.g. malignant melanoma, lymphoma, or lung cancer), and accurate segmentation of tumors is a key part of subsequent treatment. In recent years, convolutional neural network based segmentation methods have been extensively investigated. However, these methods often give inaccurate segmentation results, such as oversegmentation and undersegmentation. To address these issues, we propose a postprocessing method based on a graph convolutional network (GCN) to refine inaccurate segmentation results and improve the overall segmentation accuracy.. First, nnU-Net is used as an initial segmentation framework, and the uncertainty in the segmentation results is analyzed. Certain and uncertain pixels are used to establish the nodes of a graph. Each node and its 6 neighbors form an edge, and 32 nodes are randomly selected as uncertain nodes to form edges. The highly uncertain nodes are used as the subsequent refinement targets. Second, the nnU-Net results of the certain nodes are used as labels to form a semisupervised graph network problem, and the uncertain part is optimized by training the GCN to improve the segmentation performance. This describes our proposed nnU-Net + GCN segmentation framework.We perform tumor segmentation experiments with the PET/CT dataset from the MICCIA2022 autoPET challenge. Among these data, 30 cases are randomly selected for testing, and the experimental results show that the false-positive rate is effectively reduced with nnU-Net + GCN refinement. In quantitative analysis, there is an improvement of 2.1% for the average Dice score, 6.4 for the 95% Hausdorff distance (HD95), and 1.7 for the average symmetric surface distance.. The quantitative and qualitative evaluation results show that GCN postprocessing methods can effectively improve the tumor segmentation performance.
. 全身正电子发射断层扫描/计算机断层扫描（PET/CT）扫描是诊断各种恶性肿瘤（如恶性黑色素瘤、淋巴瘤或肺癌）的重要工具，而肿瘤的准确分割是后续治疗的关键部分。近年来，基于卷积神经网络的分割方法得到了广泛的研究。然而，这些方法往往给出不准确的分割结果，如过分割和欠分割。为了解决这些问题，我们提出了一种基于图卷积网络（GCN）的后处理方法，以细化不准确的分割结果，提高整体分割准确性。首先，nnU-Net 被用作初始分割框架，并分析分割结果的不确定性。确定性和不确定性像素用于建立图的节点。每个节点及其 6 个邻居形成一个边，随机选择 32 个节点作为不确定节点形成边。高度不确定的节点被用作后续细化的目标。其次，确定性节点的 nnU-Net 结果被用作标签，形成一个半监督图网络问题，通过训练 GCN 优化不确定部分，以提高分割性能。这描述了我们提出的 nnU-Net + GCN 分割框架。我们使用 MICCIA2022 自动 PET 挑战赛的 PET/CT 数据集进行肿瘤分割实验。在这些数据中，随机选择 30 个病例进行测试，实验结果表明，nnU-Net + GCN 细化可以有效降低假阳性率。在定量分析中，平均 Dice 评分提高了 2.1%，95% Hausdorff 距离（HD95）提高了 6.4，平均对称面距离提高了 1.7。定量和定性评估结果表明，GCN 后处理方法可以有效提高肿瘤分割性能。
