Dear Editor, Cervical cancer is one of the most frequently diagnosed cancers in women and has a high mortality rate worldwide.1 Lymph node metastasis (LNM) is an important prognostic factor in patients with cervical cancer.2-4 The assessment of LNM before treatment is essential to guide and tailor the treatment.5, 6 The morphological examination of lymph nodes via medical images is commonly used for diagnosing LNM. However, it depends mainly on radiologists’ experience and has relatively low accuracy. Thus, we collected a multi-center dataset and developed a deep learning-based nomogram (DLN) to improve the accuracy of LNM diagnosis in cervical cancer. In total, 1123 cervical cancer patients with computed tomography (CT) examination were enrolled from 13 centers in our study (Table S1 and Supplementary A1). As shown in Supplementary A2 and Figure S1, we divided these patients into four cohorts: training cohort, validation cohort, external testing cohort 1, and external testing cohort 2. Detailed information on the four cohorts is presented in Table S2. The clinical characteristics included age, gravidity, histological type, FIGO stage, etc. Moreover, two experienced gynecologists, who were blinded to the pathological report, were invited to diagnose the status of LNM together using only CT images. Additionally, a follow-up cohort including 148 patients from one center was used for survival analysis. The workflow of this study is described in Figure 1, including region of interest (ROI) segmentation, data preprocessing (Supplementary A3), model construction, and model evaluation (Supplementary A4). We invited experienced gynecologists to segment ROIs in normalized CT images. Before model construction, data augmentations, including flipping, rotating, and random cropping, were used to generate new training samples to avoid overfitting. Oversampling methods were used to balance the ratio of LNM-positive patients and LNM-negative patients in the training cohort. Three state-of-the-art deep learning methods, including ResNet18,7 ResNet50,7 and SE-Net,8 were used to construct three candidate models (Supplementary A5). As shown in Table S3, ResNet18 showed the best performance in the validation cohort, and thus it was selected to build the final deep learning signature (Sig_DL). As shown in Supplementary A6, a total of 1407 handcrafted radiomic features were extracted, and three key radiomic features were selected via a series of feature selection methods and integrated them into a radiomic signature (Sig_radiomic).9, 10 As shown in Table 1 and Figure S2, the AUCs of Sig_DL performed better than Sig_radiomic in all the cohorts. Additionally, univariate analysis was used to screen for significant clinical features. We noticed that the FIGO stage was significantly associated with LNM (P < 0.01). After multivariable logistic regression, we selected the FIGO stage and age as key clinical features and used them to construct a clinical signature (Sig_clin). The area under the receiver operating characteristic curve (AUCs) of Sig_clin reached 0.678 and 0.597 in training and validation cohorts, respectively. Finally, we integrated Sig_DL, diagnoses of gynecologists, and all significant clinical features into a DLN via multivariate linear regress analysis (Table S4 and Figure 2A). Compared with other models, DLN had the best predictive ability (Figure S3), with AUCs of 0.867, 0.807, 0.781, and 0.804 in the training cohort, validation cohort, external testing cohort1 and external testing cohort2 (Figure 2B–E). As shown in Table 1, the accuracy also indicated the good performance of DLN in these four cohorts. Meanwhile, the decision curves showed that the patients could benefit more from DLN than both Sig_DL and Sig_clin (Figure 2F). As shown in Figure 2G, the calibration curves demonstrated that the DLN had good consistency with the gold standard of LNM. It is worth noting that the diagnoses of the gynecologists had high specificity but low sensitivity in our cohorts. Therefore, we modified the cutoff value so that DLN could have the same specificity as the gynecologists’ diagnoses. Then, we found that DLN had better accuracy and sensitivity than the gynecologists (Table S5). The Venn diagrams also showed that DLN had more true positive cases than the gynecologists (Figure S4). Four typical cases are shown in Figure 3, which indicates that DLN could help the clinician reduce the risk of misdiagnosis. Subgroup analysis was performed on the data of the enrolled patients, including their clinical characteristics, the CT manufacturers, and the centers. As shown in Figure S5A–F, the subgroup analysis indicates that the DLN was not affected by age, times of pregnancy, human papillomavirus (HPV) testing result, and histological type. Especially, we selected 614 cervical cancer patients for human papillomavirus (HPV) testing. Subgroup analysis revealed that our DLN showed good performance in both HPV-positive subgroup and HPV-negative subgroup (Figure S5G–H). Our model also was minimally affected by the CT manufacturers and centers (Figure S6A,B). Besides, 148 cervical cancer patients with follow-up from Center 2 were used for exploring the association between DLN score and overall survival (OS) using Kaplan-Meier curves (Supplementary A7). We divided them into low-risk and high-risk groups using the mean value of DLN score as a cutoff. As shown in Figure 2H, we found that the high-risk group exhibited shorter OS (log-rank test: P = 0.0012). Furthermore, we stratified patients via the FIGO stage for comparison, however, the FIGO stage showed no significant association with OS (Figure S7). Hence, DLN could serve as a significant prognostic factor for cervical cancer. In conclusion, we developed a deep learning model for the preoperative prediction of LNM in cervical cancer and validated it in a large-scale and multicenter dataset. The performance of DLN surpassed the diagnosis of experienced gynecologists. Therefore, DLN can serve as a non-invasive tool for LNM determination and thus assist treatment decision-making. This work was supported by Strategic Priority Research Program of Chinese Academy of Sciences (XDB 38040200), National Key R&D Program of China (2017YFA0205200), National Natural Science Foundation of China (82022036, 91959130, 81971776, 81771924, 62027901, 81930053, 81227901), the Beijing Natural Science Foundation (Z20J00105), Chinese Academy of Sciences under Grant No. GJJSTD20170004 and QYZDJ-SSW-JSC005, the Project of High-Level Talents Team Introduction in Zhuhai City (Zhuhai HLHPTP201703), and the Youth Innovation Promotion Association CAS (Y2021049). The authors would like to acknowledge the instrumental and technical support of Multi-modal biomedical imaging experimental platform, Institute of Automation, Chinese Academy of Sciences. The authors declare no conflict of interest. Supplementary A1. The inclusion and exclusion criteria of this study Supplementary A2. The dataset partition and sample size estimation Supplementary A3. Region of interest segmentation and data preprocessing Supplementary A4. Evaluation of the models Supplementary A5. Training details of the three deep learning networks Supplementary A6. Handcrafted features extraction and Sig_radiomic building Supplementary A7. The prognostic analysis of DLN Table S1. Detailed information of the data in each center Table S2. Clinical characteristics in the training cohort, validation cohort and external testing cohorts Table S3. Performance of deep learning and radiomic signatures in all cohorts Table S4. The logistic linear regression of features in DLN Table S5. Performance of the DLN and the diagnoses of gynecologists in all cohorts. Figure S1. The Flowchart of this multicenter study. Figure S2. The ROC curves of different signatures in all cohorts. Figure S3. The performance of the constructed models in all cohorts. Figure S4. Venn diagram comparing the performance of DLN with the diagnoses of gynecologists. Figure S5. Subgroup analysis of clinical characteristics. Figure S6. Subgroup analysis on (A)different centers and (B) different CT manufacturers. Figure S7. Kaplan-Meier curve of overall survival for FIGO stage in follow-up cohort. Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.

Background Current opinions on whether surgical patients with cervical cancer should undergo para-aortic lymphadenectomy at the same time are inconsistent. The present study examined differences in survival outcomes with or without para-aortic lymphadenectomy in surgical patients with stage IB1-IIA2 cervical cancer. Methods We retrospectively compared the survival outcomes of 8802 stage IB1-IIA2 cervical cancer patients (FIGO 2009) who underwent abdominal radical hysterectomy + pelvic lymphadenectomy ( n = 8445) or abdominal radical hysterectomy + pelvic lymphadenectomy + para-aortic lymphadenectomy ( n = 357) from 37 hospitals in mainland China. Results Among the 8802 patients with stage IB1-IIA2 cervical cancer, 1618 (18.38%) patients had postoperative pelvic lymph node metastases, and 37 (10.36%) patients had para-aortic lymph node metastasis. When pelvic lymph nodes had metastases, the para-aortic lymph node simultaneous metastasis rate was 30.00% (36/120). The risk of isolated para-aortic lymph node metastasis was 0.42% (1/237). There were no significant differences in the survival outcomes between the para-aortic lymph node unresected and resected groups. No differences in the survival outcomes were found before or after matching between the two groups regardless of pelvic lymph node negativity/positivity. Conclusion Para-aortic lymphadenectomy did not improve 5-year survival outcomes in surgical patients with stage IB1-IIA2 cervical cancer. Therefore, when pelvic lymph node metastasis is negative, the risk of isolated para-aortic lymph node metastasis is very low, and para-aortic lymphadenectomy is not recommended. When pelvic lymph node metastasis is positive, para-aortic lymphadenectomy should be carefully selected because of the high risk of this procedure.

PURPOSE:Radiomic models have been demonstrated to have acceptable discrimination capability for detecting lymph node metastasis (LNM). We aimed to develop a computed tomography-based radiomic model and validate its usefulness in the prediction of normal-sized LNM at node level in cervical cancer.METHODS:A total of 273 LNs of 219 patients from 10 centers were evaluated in this study. We randomly divided the LNs from the 2 centers with the largest number of LNs into the training and internal validation cohorts, and the rest as the external validation cohort. Radiomic features were extracted from the arterial and venous phase images. We trained an artificial neural network (ANN) to develop two single-phase models. A radiomic model reflecting the features of two-phase images was also built for directly predicting LNM in cervical cancer. Moreover, four state-of-the-art methods were used for comparison. The performance of all models was assessed using the area under the receiver operating characteristic curve (AUC).RESULTS:Among the models we built, the models combining the features of two phases surpassed the single-phase models, and the models generated by ANN had better performance than the others. We found that the radiomic model achieved the highest AUCs of 0.912 and 0.859 in the training and internal validation cohorts, respectively. In the external validation cohort, the AUC of the radiomic model was 0.800.CONCLUSION:We constructed a radiomic model that exhibited great ability in the prediction of LNM. The application of the model could optimize clinical staging and decision-making.

Objective: To build and validate a CT radiomic model for pre-operatively predicting lymph node metastasis in early cervical carcinoma. Methods and materials: A data set of 150 patients with Stage IB1 to IIA2 cervical carcinoma was retrospectively collected from the Nanfang hospital and separated into a training cohort (n = 104) and test cohort (n = 46). A total of 348 radiomic features were extracted from the delay phase of CT images. Mann-Whitney U test, recursive feature elimination, and backward elimination were used to select key radiomic features. Ridge logistics regression was used to build a radiomic model for prediction of lymph node metastasis (LNM) status by combining radiomic and clinical features. The area under the receiver operating characteristic curve (AUC) and kappa test were applied to verify the model. Results: Two radiomic features from delay phase CT images and one clinical feature were associated with LNM status: log-sigma-2-Omm-3D_glcm_Idn (p 0.01937), wavelet-HL_firstorder_Median (p = 0.03592), and Stage IB (p = 0.03608). Radiomic model was built consisting of the three features, and the AUCs were 0.80 (95% confidence interval: 0.70 - 0.90) and 0.75 (95% confidence intervall: 0.53 - 0.93) in training and test cohorts, respectively. The kappa coefficient was 0.84, showing excellent consistency. Conclusion: A non-invasive radiomic model, combining two radiomic features and a International Federation of Gynecology and Obstetrics stage, was built for prediction of LNM status in early cervical carcinoma. This model could serve as a pre-operative tool. Advances in knowledge: A noninvasive CT radiomic model, combining two radiomic features and the International Federation of Gynecology and Obstetrics stage, was built for prediction of LNM status in early cervical carcinoma.

目的 应用大数据探讨中国ⅠB2期子宫颈癌患者腹腔镜与开腹手术的长期肿瘤学结局差异.方法 基于中国子宫颈癌临床诊疗大数据库,回顾性分析2009-2016年国内部分地区Ⅰ B2期子宫颈癌腹腔镜与开腹手术病例,通过真实世界研究(RWS)和倾向评分匹配(PSM)的方法,分析2种手术途径5年总体生存率(OS)和无病生存率(DFS)的差异.结果 (1)初始入组共纳入2176例病例,其中腹腔镜组646例,开腹组1530例.匹配前两组5年OS差异无统计学意义(82.5％ vs.88.4％,P=0.060),但5年DFS腹腔镜组低于开腹组(77.6％ vs.83.9％,P=0.001),Cox比例风险模型分析显示腹腔镜手术是患者5年死亡和复发/死亡的独立危险因素(OS:HR=1.398,95％CI 1.029～ 1.898,P=0.032;DFS:HR=1.540,95％CI 1.220～1.943,P＜0.001).1:2 PSM匹配后共纳入1575例病例,其中腹腔镜组525例,开腹组1050例;腹腔镜组的5年OS和DFS均低于开腹组(OS:82.4％ vs.89.2％,P=0.042;DFS:77.6％ vs.85.0％,P=0.001),Cox比例风险模型分析显示腹腔镜手术是患者5年死亡和复发/死亡的独立危险因素(OS:HR=1.457,95％CI 1.022～2.077,P=0.037;DFS:HR=1.569,95％CI 1.198 ～ 2.054,P=0.001).(2)进一步限定手术类型为QM-B型或QM-C型子宫切除为纳入条件,共入组2066例病例,其中腹腔镜组627例,开腹组1439例;匹配前两组的5年OS差异无统计学意义(82.1％ vs.88.2％,P=0.056),但5年DFS腹腔镜组低于开腹组(77.5％ vs.83.6％,P=0.001),Cox比例风险模型分析显示腹腔镜手术是患者5年死亡和复发/死亡的独立危险因素(OS:HR=1.421,95％CI 1.044～ 1.935,P=0.025;DFS:HR=1.529,95％CI 1.207～1.938,P＜0.001).1∶2 PSM匹配后共纳入1470例病例,其中腹腔镜组490例,开腹组980例;两组的5年OS差异无统计学意义(83.2％vs.88.8％,P=0.126),但5年DFS腹腔镜组低于开腹组(77.5％vs.84.7％,P=0.001),Cox比例风险模型显示腹腔镜手术仅是患者5年复发/死亡的独立危险因素(HR=1.575,95％CI 1.191 ～ 2.081,P=0.001).结论 Ⅰ B2期子宫颈癌患者腹腔镜手术与开腹手术相比,接受腹腔镜手术的患者具有更低的DFS,腹腔镜手术是该期患者复发/死亡的独立危险因素.

Objective. To determine the associations between the presence and depth of uterine corpus invasion and survival in patients with cervical cancer. Methods. Clinical data of patients with stage IA2-IIB cervical cancer who underwent radical hysterectomy between 2004 and 2016 were retrospectively reviewed. Uterine corpus invasion was identified from a review of uterine pathology. Independent prognostic factors for 5-year disease-free survival (DFS) and overall survival (OS) were identified using multivariate forward stepwise Cox proportional hazards regression models. Results. A total of 1414 patients with stage IA2-IIB cervical cancer from 11 medical institutions in China were included. Retrospective review of the original pathology reports revealed a missed diagnosis of uterine corpus invasion in 38 (13.4%) patients and a misdiagnosis in 20 (1.8%) patients. Therefore, 284 patients with cervical cancer and uterine corpus invasion (90 [31.7%1 patients had endometrial invasion, 105 137.0%] patients had myometrial invasion <50%), and 89 [31.3%] patients had myometrial invasion >= 50%), and 1130 patients with cervical cancer without uterine corpus invasion were included in the analysis. The 5-year DFS and OS were significantly shorter for patients with uterine corpus invasion compared to patients with no uterine corpus invasion. Myometrial invasion >= 50% was an independent prognostic factor associated with decreased 5-year DFS (aHR. 2307, 95% CI, 1.588-3.351) and 5-year OS (aHR, 2.736, 95% CI, 1.813-4.130), while myometrial invasion <50% or endometrial invasion had no effect on patient outcomes. Conclusions. Diagnosis of uterine corpus invasion is frequently missed. Myometrial invasion >= 50% within the uterine corpus was an independent factor associated with worse prognosis in patients with cervical cancer, while myometrial invasion <50% or endometrial invasion had no effect on outcomes. (C) 2020 Elsevier Inc. All rights reserved.

目的 在真实世界研究条件下分析接受腹腔镜或开腹手术的ⅡA2期子宫颈癌长期肿瘤学结局.方法 基于中国子宫颈癌临床诊疗大数据库,筛选接受腹腔镜和开腹手术的ⅡA2期子宫颈癌患者,采用真实世界研究及倾向评分匹配的方法,通过K-M生存分析和Cox多因素分析对两组的长期肿瘤学结局进行比较.结果 (1)初步筛选纳入ⅡA2期子宫颈癌1575例,腹腔镜组394例,开腹组1181例.匹配前,腹腔镜组与开腹组的5年总生存率(OS)和5年无瘤生存率(DFS)差异均无统计学意义(OS:75.48％ vs.83.33％,P=0.505;DFS:78.02％ vs.78.76％,P=0.578);Cox分析显示腹腔镜手术并非患者死亡或者复发/死亡的独立危险因素(P＞ 0.050).1:2 PSM匹配后腹腔镜组和开腹组分别纳入389例和744例,腹腔镜组与开腹组的5年OS和5年DFS差异均无统计学意义(OS:75.62％ vs.83.79％,P=0.612;DFS:78.52％ vs.79.25％,P=0.772);Cox分析显示腹腔镜手术并非患者死亡或者复发/死亡的独立危险因素(P＞ 0.050).(2)进一步限制纳入手术类型为QM-B型或QM-C型子宫切除的病例后,腹腔镜组379例,开腹组1067例.匹配前腹腔镜组与开腹组的5年OS和5年DFS差异均无统计学意义(OS:77.11％vs.84.53％,P=0.573;DFS:79.02％vs.79.81％,P=0.585),Cox分析显示腹腔镜手术并非患者死亡或者复发/死亡的独立危险因素(P＞ 0.050).1:2 PSM匹配后腹腔镜组和开腹组分别纳入371例和713例,腹腔镜组与开腹组的5年OS和5年DFS差异均无统计学意义(OS:77.27％ vs.86.00％,P=0.382;DFS:79.48％ vs.81.89％,P=0.365);Cox分析显示腹腔镜手术并非子宫颈癌患者死亡以及复发/死亡的独立危险因素(P＞ 0.050).结论 从手术途径方面进行多层次对比分析显示,ⅡA2期子宫颈癌患者腹腔镜组与开腹组的长期肿瘤学结局无差异.

Background: We aimed to investigate whether pre-therapeutic radiomic features based on magnetic resonance imaging (MRI) can predict the clinical response to neoadjuvant chemotherapy (NACT) in patients with locally advanced cervical cancer (LACC). Methods: A total of 275 patients with LACC receiving NACT were enrolled in this study from eight hospitals, and allocated to training and testing sets (2:1 ratio). Three radiomic feature sets were extracted from the intratumoural region of T1-weighted images, intratumoural region of T2-weighted images, and peritumoural region T2-weighted images before NACT for each patient. With a feature selection strategy, three single sequence radiomic models were constructed, and three additional combined models were constructed by combining the features of different regions or sequences. The performance of all models was assessed using receiver operating characteristic curve. Findings: The combined model of the intratumoural zone of T1-weighted images, intratumoural zone of T2-weighted images,and peritumoural zone of T2-weighted images achieved an AUC of 0.998 in training set and 0.999 in testing set, which was significantly better (p < .05) than the other radiomic models. Moreover, no significant variation in performance was found if different training sets were used. Interpretation: This study demonstrated that MRI-based radiomic features hold potential in the pretreatment prediction of response to NACT in LACC, which could be used to identify rightful patients for receiving NACT avoiding unnecessary treatment. (C) 2019 The Authors. Published by Elsevier B.V.