Southeast University, Laboratory of Image Science and Technology, Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing, Centre de Recherche en Information Biomédicale Sino-français (CRIBs), Nanjing, P. R. China.
Department of Radiation Oncology Physics and Technology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, China.
Med Phys. 2022 Oct;49(10):6527-6537. doi: 10.1002/mp.15904. Epub 2022 Aug 17.
Radiomics has been considered an imaging marker for capturing quantitative image information (QII). The introduction of radiomics to image segmentation is desirable but challenging.
This study aims to develop and validate a radiomics-based framework for image segmentation (RFIS).
RFIS is designed using features extracted from volume (svfeatures) created by sliding window (swvolume). The 53 svfeatures are extracted from 11 phantom series. Outliers in the svfeature datasets are detected by isolation forest (iForest) and specified as the mean value. The percentage coefficient of variation (%COV) is calculated to evaluate the reproducibility of svfeatures. RFIS is constructed and applied to the gross target volume (GTV) segmentation from the peritumoral region (GTV with a 10 mm margin) to assess its feasibility. The 127 lung cancer images are enrolled. The test-retest method, correlation matrix, and Mann-Whitney U test (p < 0.05) are used to select non-redundant svfeatures of statistical significance from the reproducible svfeatures. The synthetic minority over-sampling technique is utilized to balance the minority group in the training sets. The support vector machine is employed for RFIS construction, which is tuned in the training set using 10-fold stratified cross-validation and then evaluated in the test sets. The swvolumes with the consistent classification results are grouped and merged. Mode filtering is performed to remove very small subvolumes and create relatively large regions of completely uniform character. In addition, RFIS performance is evaluated by the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, specificity, and Dice similarity coefficient (DSC).
30249 phantom and 145008 patient image swvolumes were analyzed. Forty-nine (92.45% of 53) svfeatures represented excellent reproducibility(%COV<15). Forty-five features (91.84% of 49) included five categories that passed test-retest analysis. Thirteen svfeatures (28.89% of 45) svfeatures were selected for RFIS construction. RFIS showed an average (95% confidence interval) sensitivity of 0.848 (95% CI:0.844-0.883), a specificity of 0.821 (95% CI: 0.818-0.825), an accuracy of 83.48% (95% CI: 83.27%-83.70%), and an AUC of 0.906 (95% CI: 0.904-0.908) with cross-validation. The sensitivity, specificity, accuracy, and AUC were equal to 0.762 (95% CI: 0.754-0.770), 0.840 (95% CI: 0.837-0.844), 82.29% (95% CI: 81.90%-82.60%), and 0.877 (95% CI: 0.873-0.881) in the test set, respectively. GTV was segmented by grouping and merging swvolume with identical classification results. The mean DSC after mode filtering was 0.707 ± 0.093 in the training sets and 0.688 ± 0.072 in the test sets.
Reproducible svfeatures can capture the differences in QII among swvolumes. RFIS can be applied to swvolume classification, which achieves image segmentation by grouping and merging the swvolume with similar QII.
放射组学被认为是一种捕获定量图像信息（QII）的成像标志物。将放射组学引入图像分割是可取的，但具有挑战性。
本研究旨在开发和验证一种基于放射组学的图像分割框架（RFIS）。
RFIS 是使用从滑动窗口（swvolume）创建的体积（svfeatures）中提取的特征设计的。从 11 个体模系列中提取了 53 个 svfeatures。离群值通过隔离森林（iForest）检测并指定为平均值。计算百分比变异系数（%COV）以评估 svfeatures 的可重复性。构建 RFIS 并将其应用于从肿瘤周围区域（带有 10mm 边界的 GTV）分割大体肿瘤体积（GTV），以评估其可行性。共纳入 127 例肺癌图像。使用测试-再测试方法、相关矩阵和曼-惠特尼 U 检验（p<0.05）从可重复的 svfeatures 中选择具有统计学意义的非冗余 svfeatures。利用合成少数过采样技术平衡训练集中的少数群体。支持向量机用于 RFIS 构建，在训练集中使用 10 折分层交叉验证进行调整，然后在测试集中进行评估。具有一致分类结果的 swvolume 被分组和合并。模式过滤用于去除非常小的子体积并创建具有完全一致特征的相对较大区域。此外，通过接收器操作特征（ROC）曲线下面积（AUC）、准确性、灵敏度、特异性和 Dice 相似系数（DSC）评估 RFIS 的性能。
分析了 30249 个体模和 145008 个患者图像 swvolume。有 49 个（53 个中的 92.45%）svfeatures 表现出极好的可重复性（%COV<15）。有 45 个特征（49 个中的 91.84%）包括通过测试-再测试分析的五类。有 13 个 svfeatures（45 个中的 28.89%）被选为 RFIS 构建。RFIS 显示平均（95%置信区间）灵敏度为 0.848（95%CI：0.844-0.883），特异性为 0.821（95%CI：0.818-0.825），准确性为 83.48%（95%CI：0.8327%-0.8370%），AUC 为 0.906（95%CI：0.904-0.908），交叉验证。在测试集中，灵敏度、特异性、准确性和 AUC 分别等于 0.762（95%CI：0.754-0.770）、0.840（95%CI：0.837-0.844）、82.29%（95%CI：81.90%-82.60%）和 0.877（95%CI：0.873-0.881）。通过分组和合并具有相同分类结果的 swvolume 对 GTV 进行分割。模式过滤后的平均 DSC 在训练集中为 0.707±0.093，在测试集中为 0.688±0.072。
可重复的 svfeatures 可以捕获 swvolume 之间 QII 的差异。RFIS 可应用于 swvolume 分类，通过分组和合并具有相似 QII 的 swvolume 来实现图像分割。
