Department of Physical Examination Center, The Affifiliated Lianyungang Hospital of Xuzhou Medical University, No. 182, Tongguan North Road, Lianyungang 222000, Jiangsu, China.
Department of Obstetrics and Gynecology, Zhangjiagang First People's Hospital, No. 68 Jiyang West Road, Zhangjiagang, Suzhou 215600, Jiangsu, China.
Contrast Media Mol Imaging. 2022 Jun 15;2022:2432291. doi: 10.1155/2022/2432291. eCollection 2022.
A case-control study was conducted to explore the application and clinical value of machine learning-based cervical cancer (CC) diagnosis and prediction model in adjuvant chemotherapy of CC.
From August 2019 to August 2021, 46 patients with stage IA CC (study group) and 55 patients with high-grade squamous intraepithelial lesions (HSIL) (control group) were retrospectively analyzed. All patients completed routine MRI examinations, the ADC values of diseased CC and normal cervix and cervical tissues in different stages were compared, and the changes of ADC values in CC tissues before and after chemotherapy were analyzed. The training set (IA = 37, HSIL = 44) and test set (IA = 9, HSIL = 11) are set in a ratio of 4 : 1. The preoperative MRI images were collected and uploaded to the radiomics cloud platform after preprocessing, and the cervix was manually delineated layer by layer on OSag-T2WI, OAx-T1WI, and OAx-T2FS, respectively, to obtain a three-dimensional volume of interest (VOI) of the cervix to extract omics features. Variance Threshold analysis, univariate feature selection (SelectKBest), and least absolute shrinkage and selection operator (LASSO) are adopted to reduce the dimension of data and enroll features. The arbitrary forest model was adopted for machine learning, the ROC curve was drawn, and the diagnostic performance of different sequence omics models was analyzed.
Compared with ADC of stage A CC and HSIL, the ADC value of CC was remarkably lower than that of normal CC ( < 0.05). The ROC curve analysis of ADC value to differentiate CC and normal cervix indicated that the AUC was 0.838 and the 95% confidence interval was 0.721-0.955. According to the maximum Youden index of 0.848, the optimal critical value of ADC was 1.267 × 10 mm/s and the sensitivity and specificity were 92.21% and 9.48%, respectively. All results are indicated in Table 2. After CC treatment, 12 patients were effective (CR + PR) and 4 patients were ineffective (PD + SD). When the value was 1000 s/mm, the ADC value of the effective patients after the second chemotherapy was significantly higher than that of the first chemotherapy and before treatment ( < 0.05). There was no significant difference between the ADC value after the first chemotherapy and before treatment, compared with before treatment ( > 0.05). There was no significant difference in ADC value between the ineffective patients before treatment and after the first and second chemotherapy ( > 0.05). A total of 8 omics features were extracted based on OSag-T2WI, all of which were wavelet features, including 7 texture features and 1 first-order feature. A total of 10 omics features were extracted based on OAx-T1WI, including 6 wavelet first-order features, 2 gradient first-order features, and 2 wavelet texture features. Based on OAx-T2FS, 6 omics features were extracted, including 3 wavelet texture features, 2 original shape features, and 1 logarithmic first-order feature. Based on OSag-T2WI&OAx-T2FS, 9 histological features were extracted, 4 from OSag-T2WI and 5 from OAx-T2FS. The diagnostic performance of the four arbitrary forest models is indicated in Table 1, and the ROC curve is indicated in Figure 6. The diagnostic performance of the omics model based on OSag-T2WI&OAx-T2FS was the best in both the training set and the test set. The AUC of the training set was 0.991 (95% CI (0.94, 1.00)), and the accuracy rate was 0.925. The AUC of the test set was 0.894 (95% CI (0.75, 1.00)), and the accuracy rate was 0.835. On the other hand, the diagnostic efficiency of the group model based on OAx-T1WI was the worst in both the training set and the test set. The AUC of the training set was 0.713 (95% CI (0.52, 0.92)), and the accuracy rate was 0.71. The AUC of test set is 0.513 (95% CI (0.24, 0.77)), and the accuracy rate was 0.56, which has no practical clinical significance.
A CC diagnosis and prediction model based on machine learning can better distinguish stage IA CC from HSIL in the absence of clear lesions, which is of great significance for reducing invasive examination before surgery, guiding surgical procedures and adjuvant chemotherapy for CC.
采用病例对照研究探讨基于机器学习的宫颈癌（CC）诊断和预测模型在 CC 辅助化疗中的应用及临床价值。
回顾性分析 2019 年 8 月至 2021 年 8 月间 46 例 IA 期 CC 患者（研究组）和 55 例高级别鳞状上皮内病变（HSIL）患者（对照组）的临床资料。所有患者均完成常规 MRI 检查，比较病变 CC 和正常宫颈及不同阶段宫颈组织的 ADC 值，分析 CC 组织化疗前后 ADC 值的变化。将训练集（IA=37，HSIL=44）和测试集（IA=9，HSIL=11）按 4︰1 的比例设置。预处理后采集术前 MRI 图像并上传至放射组学云平台，分别在 OSag-T2WI、OAx-T1WI 和 OAx-T2FS 上手动逐层勾画宫颈，获得宫颈的三维感兴趣区（VOI）以提取组学特征。采用方差阈值分析、单变量特征选择（SelectKBest）和最小绝对值收缩和选择算子（LASSO）进行降维，对数据进行特征选择，采用随机森林模型进行机器学习，绘制 ROC 曲线，分析不同序列组学模型的诊断性能。
与 A 期 CC 和 HSIL 的 ADC 值相比，CC 的 ADC 值显著降低（<0.05）。ADC 值鉴别 CC 和正常宫颈的 ROC 曲线分析表明，AUC 为 0.838，95%置信区间为 0.721~0.955。根据最大 Youden 指数 0.848，ADC 值的最佳临界值为 1.267×10-3mm/s，敏感度和特异度分别为 92.21%和 9.48%。表 2 中列出了所有结果。CC 治疗后，12 例患者有效（CR+PR），4 例患者无效（PD+SD）。当 值为 1000s/mm 时，第二次化疗后有效患者的 ADC 值明显高于第一次化疗和治疗前（<0.05）。第一次化疗与治疗前比较，ADC 值差异无统计学意义（>0.05）。治疗前无效患者与第一次和第二次化疗后的 ADC 值比较，差异无统计学意义（>0.05）。基于 OSag-T2WI 共提取 8 个组学特征，均为小波特征，包括 7 个纹理特征和 1 个一阶特征。基于 OAx-T1WI 提取了 10 个组学特征，包括 6 个小波一阶特征、2 个梯度一阶特征和 2 个小波纹理特征。基于 OAx-T2FS，提取了 6 个组学特征，包括 3 个小波纹理特征、2 个原始形状特征和 1 个对数一阶特征。基于 OSag-T2WI&OAx-T2FS 提取了 9 个组织学特征，其中 4 个来自 OSag-T2WI，5 个来自 OAx-T2FS。表 1 列出了四个任意森林模型的诊断性能，图 6 显示了 ROC 曲线。在训练集和测试集中，基于 OSag-T2WI&OAx-T2FS 的组学模型的诊断性能最佳。训练集的 AUC 为 0.991（95%CI（0.94，1.00）），准确率为 0.925。测试集的 AUC 为 0.894（95%CI（0.75，1.00）），准确率为 0.835。另一方面，在训练集和测试集中，基于 OAx-T1WI 的组模型的诊断效率最差。训练集的 AUC 为 0.713（95%CI（0.52，0.92）），准确率为 0.71。测试集的 AUC 为 0.513（95%CI（0.24，0.77）），准确率为 0.56，没有实际的临床意义。
基于机器学习的 CC 诊断和预测模型可以更好地区分无明显病变的 IA 期 CC 和 HSIL，对于减少术前侵袭性检查、指导 CC 的手术程序和辅助化疗具有重要意义。
