Wang Yiang, Wang Mandi, Cao Peng, Wong Esther M F, Ho Grace, Lam Tina P W, Han Lujun, Lee Elaine Y P
Department of Diagnostic Radiology, The University of Hong Kong, Hong Kong, China.
Department of Radiology, Shenzhen People's Hospital (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, China.
Quant Imaging Med Surg. 2023 Aug 1;13(8):5218-5229. doi: 10.21037/qims-22-1135. Epub 2023 Jun 13.
Radiomics analysis could provide complementary tissue characterization in ovarian cancer (OC). However, OC segmentation required in radiomics analysis is time-consuming and labour-intensive. In this study, we aim to evaluate the performance of deep learning-based segmentation of OC on contrast-enhanced CT images and the stability of radiomics features extracted from the automated segmentation.
Staging abdominopelvic CT images of 367 patients with OC were retrospectively recruited. The training and cross-validation sets came from center A (n=283), and testing set (n=84) came from centers B and C. The tumours were manually delineated by a board-certified radiologist. Four model architectures provided by no-new-Net (nnU-Net) method were tested in this task. The segmentation performance evaluated by Dice score, Jaccard score, sensitivity and precision were compared among 4 architectures. The Pearson correlation coefficient (), concordance correlation coefficient () and Bland-Altman plots were used to evaluate the volumetric assessment of OC between manual and automated segmentations. The stability of extracted radiomics features was evaluated by intraclass correlation coefficient (ICC).
The 3D U-Net cascade architecture achieved highest median Dice score, Jaccard score, sensitivity and precision for OC segmentation in the testing set, 0.941, 0.890, 0.973 and 0.925, respectively. Tumour volumes of manual and automated segmentations were highly correlated (=0.944 and =0.933). 85.0% of radiomics features had high correlation with ICC >0.8.
The presented deep-learning segmentation could provide highly accurate automated segmentation of OC on CT images with high stability of the extracted radiomics features, showing the potential as a batch-processing segmentation tool.
放射组学分析可为卵巢癌（OC）提供补充性的组织特征描述。然而，放射组学分析所需的OC分割既耗时又费力。在本研究中，我们旨在评估基于深度学习的OC在对比增强CT图像上的分割性能以及从自动分割中提取的放射组学特征的稳定性。
回顾性招募了367例OC患者的腹部盆腔分期CT图像。训练集和交叉验证集来自中心A（n = 283），测试集（n = 84）来自中心B和C。肿瘤由一名获得委员会认证的放射科医生手动勾勒。在此任务中测试了no-new-Net（nnU-Net）方法提供的四种模型架构。比较了四种架构之间通过Dice分数、Jaccard分数、敏感性和精确性评估的分割性能。使用Pearson相关系数（）、一致性相关系数（）和Bland-Altman图来评估手动分割和自动分割之间OC的体积评估。通过组内相关系数（ICC）评估提取的放射组学特征的稳定性。
3D U-Net级联架构在测试集中实现了最高的OC分割中位数Dice分数、Jaccard分数、敏感性和精确性，分别为0.941、0.890、0.973和0.925。手动分割和自动分割的肿瘤体积高度相关（= 0.944和 = 0.933）。85.0%的放射组学特征与ICC>0.8具有高度相关性。
所提出的深度学习分割可以在CT图像上提供高度准确的OC自动分割，且提取的放射组学特征具有高稳定性，显示出作为批量处理分割工具的潜力。
