Multiple Resolution Residually Connected Feature Streams for Automatic Lung Tumor Segmentation From CT Images.
Multiple Resolution Residually Connected Feature Streams for Automatic Lung Tumor Segmentation From CT Images.
复制标题
DOI：
10.1109/tmi.2018.2857800
复制
发表时间：
2019-01
影响因子：
10.6
通讯作者：
Veeraraghavan H
中科院分区：
文献类型：
--
作者：
Jiang J;Hu YC;Liu CJ;Halpenny D;Hellmann MD;Deasy JO;Mageras G;Veeraraghavan H
体积肺肿瘤分割和准确的纵向跟踪肿瘤体积变化的计算机断层扫描（CT）图像是必不可少的监测肿瘤治疗反应。因此，我们开发了两个多分辨率剩余连接网络（MRRN）配方称为增量MRRN和密集MRRN。我们的网络同时通过残差连接将多个图像分辨率和特征级别的联合收割机特征组合起来，以检测和分割肺部肿瘤。我们对来自三个数据集的总共1210个非小细胞（NSCLC）肺肿瘤和结节进行了评估，这些数据集包括来自开源癌症成像档案（TCIA）的377个肿瘤，来自内部机构MSKCC数据集的304个接受抗PD-1检查点免疫治疗的晚期NSCLC，以及来自肺部图像数据库联盟（LIDC）的529个肺结节。该算法使用来自TCIA数据集的377个肿瘤进行训练，并在MSKCC上进行验证，并在LIDC数据集上进行测试。通过计算Dice相似系数（DSC）、Hausdorff距离、灵敏度和精确度指标，评价了与专家描述相比的分割准确性。我们性能最好的增量MRRN方法产生的最高DSC为TCIA的0.74±0.13，MSKCC的0.75±0.12和LIDC数据集的0.68±0.23。与专家分割相比，使用增量MRRN方法计算的体积肿瘤变化的估计值没有显著差异。总之，我们已经开发了一种多尺度CNN方法，用于体积分割肺肿瘤，该方法能够准确，自动识别和连续测量肺中的肿瘤体积。
Volumetric lung tumor segmentation and accurate longitudinal tracking of tumor volume changes from computed tomography (CT) images are essential for monitoring tumor response to therapy. Hence, we developed two multiple resolution residually connected network (MRRN) formulations called incremental-MRRN and dense-MRRN. Our networks simultaneously combine features across multiple image resolution and feature levels through residual connections to detect and segment lung tumors. We evaluated our method on a total of 1210 non-small cell (NSCLC) lung tumors and nodules from three datasets consisting of 377 tumors from the open-source Cancer Imaging Archive (TCIA), 304 advanced stage NSCLC treated with anti-PD-1 checkpoint immunotherapy from internal institution MSKCC dataset, and 529 lung nodules from the Lung Image Database Consortium (LIDC). The algorithm was trained using the 377 tumors from the TCIA dataset and validated on the MSKCC and tested on LIDC datasets. The segmentation accuracy compared to expert delineations was evaluated by computing the Dice Similarity Coefficient (DSC), Hausdorff distances, sensitivity and precision metrics. Our best performing incremental-MRRN method produced the highest DSC of 0.74±0.13 for TCIA, 0.75±0.12 for MSKCC and 0.68±0.23 for the LIDC datasets. There was no significant difference in the estimations of volumetric tumor changes computed using the incremental-MRRN method compared with expert segmentation. In summary, we have developed a multi-scale CNN approach for volumetrically segmenting lung tumors which enables accurate, automated identification of and serial measurement of tumor volumes in the lung.