Prediction of Postoperative Pathologic Risk Factors in Cervical Cancer Patients Treated with Radical Hysterectomy by Machine Learning

Pretherapeutic serological parameters play a predictive role in pathologic risk factors (PRF), which correlate with treatment and prognosis in cervical cancer (CC). However, the method of pre-operative prediction to PRF is limited and the clinical availability of machine learning methods remains unknown in CC. Overall, 1260 early-stage CC patients treated with radical hysterectomy (RH) were randomly split into training and test cohorts. Six machine learning classifiers, including Gradient Boosting Machine, Support Vector Machine with Gaussian kernel, Random Forest, Conditional Random Forest, Naive Bayes, and Elastic Net, were used to derive diagnostic information from nine clinical factors and 75 parameters readily available from pretreatment peripheral blood tests. The best results were obtained by RF in deep stromal infiltration prediction with an accuracy of 70.8% and AUC of 0.767. The highest accuracy and AUC for predicting lymphatic metastasis with Cforest were 64.3% and 0.620, respectively. The highest accuracy of prediction for lymphavascular space invasion with EN was 59.7% and the AUC was 0.628. Blood markers, including D-dimer and uric acid, were associated with PRF. Machine learning methods can provide critical diagnostic prediction on PRF in CC before surgical intervention. The use of predictive algorithms may facilitate individualized treatment options through diagnostic stratification.

MRI- and Histologic-Molecular-Based Radio-Genomics Nomogram for Preoperative Assessment of Risk Classes in Endometrial Cancer

High- and low-risk endometrial carcinoma (EC) differ in whether or not a lymphadenectomy is performed. We aimed to develop MRI-based radio-genomic models able to preoperatively assess lymph-vascular space invasion (LVSI) and discriminate between low- and high-risk EC according to the ESMO-ESGO-ESTRO 2020 guidelines, which include molecular risk classification proposed by "ProMisE". This is a retrospective, multicentric study that included 64 women with EC who underwent 3T-MRI before a hysterectomy. Radiomics features were extracted from T2WI images and apparent diffusion coefficient maps (ADC) after manual segmentation of the gross tumor volume. We constructed a multiple logistic regression approach from the most relevant radiomic features to distinguish between low- and high-risk classes under the ESMO-ESGO-ESTRO 2020 guidelines. A similar approach was taken to assess LVSI. Model diagnostic performance was assessed via ROC curves, accuracy, sensitivity and specificity on training and test sets. The LVSI predictive model used a single feature from ADC as a predictor; the risk class model used two features as predictors from both ADC and T2WI. The low-risk predictive model showed an AUC of 0.74 with an accuracy, sensitivity, and specificity of 0.74, 0.76, 0.94; the LVSI model showed an AUC of 0.59 with an accuracy, sensitivity, and specificity of 0.60, 0.50, 0.61. MRI-based radio-genomic models are useful for preoperative EC risk stratification and may facilitate therapeutic management.

Lymph Node Involvement in Early-Stage Cervical Cancer: Is Lymphangiogenesis a Risk Factor? Results from the MICROCOL Study

Simple Summary

The prognosis of cervical cancer is significantly influenced by lymph node involvement. The lymphatic system is the primary way of metastasis for cervical carcinoma, and lymph-vascular space invasion (LVSI) is considered the most important risk factor for pelvic lymph node metastasis (PLNM). Previous studies have not clarified the correlation between lymphangiogenesis and an increased risk of metastasis and tumor recurrence. The evaluation and identification of several markers of lymphangiogenesis may identify patients with high risk of PLNM. Our findings suggest that the lymphatic spread does not required the proliferation of new lymphatic endothelial cells. These results emphasize the importance of pre-existing peritumoral lymphatic vessels in the metastatic process in early cervical cancer.

Abstract

Background: In patients with cervical cancer, the presence of tumoral lymph-vascular space invasion (LVSI) is the main risk factor for pelvic lymph node metastasis (PLNM). The objective of this study was to evaluate the presence of several markers of lymphangiogenesis in early-stage cervical cancer and their correlation with PLNM and tumoral recurrence. Materials and Methods: Seventy-five patients with early-stage cervical carcinoma underwent sentinel lymph node (SLN) sampling in association with complete pelvic lymph node dissection. Primary tumors were stained with the following markers: Ki67, D2-40, CD31 and VEGF-C. A 3-year follow-up was performed to evaluate the disease-free survival. Results: Overall, 14 patients (18.6%) had PLNM. Positive LVSI was seen in 29 patients (38.6%). There was a significant correlation between LVSI evidenced by H/E staining and PLNM (p < 0.001). There was no correlation between high Ki67, CD31, D2-40, and VEGF-C staining with PLNM or tumor recurrence. Conclusions: Our data support that lymphatic spread does not require the proliferation of new lymphatic endothelial cells in early-stage cervical cancer. These results emphasize the importance of pre-existing peritumoral lymphatic vessels in the metastatic process in early cervical cancer. None of the markers of lymphangiogenesis and proliferation assessed in this study were predictive of PLNM or recurrence.

Lymph-Vascular Space Invasion in Patients with Stages IA2-IIA2 Cervical Cancer Treated with Laparoscopic versus Open Radical Hysterectomy

Objective

To explore the relationship between laparoscopic radical hysterectomy (LRH) and cervical cancer lymph-vascular space invasion (LVSI) by comparing the prevalence of LVSI in cervical cancer patients who underwent LRH versus open radical hysterectomy (ORH).

Methods

The study participants were 1087 cervical cancer patients (FIGO 2009 stages IA2-IIA2) with pathologically confirmed with or without LVSI who underwent radical hysterectomy at Shengjing Hospital of China Medical University from 2013 through 2018. The patients were divided according to the type of surgical procedure into an LRH group (n=148) and an ORH group (n=939).

Results

In the LRH group, 31.76% of patients (47/148) had LVSI-positive tumors compared to 33.23% of patients (312/939) in the ORH group; the difference was not significant (p=0.724). No between-group differences in LVSI prevalence according to lymph node metastasis, interstitial infiltration depth, differentiation degree, and parametrial infiltration were found. However, the number of LVSI-positive patients whose cervical cancer lesions >4 cm (stage I B2 and II A2) was significantly higher in the LRH group than in the ORH group (Odds Ratio [OR] 0.333, 95% confidence interval [CI] 0.157–0.706, p=0.005). The 3-Year disease-free survival (DFS) in the LRH group is lower than that in the ORH group (94.75% vs 97.27%), but there was no significance (P=0.187). Furthermore, the percentage of LVSI-positive tumors in patients with lymph node metastases was significantly higher than those without lymph node metastases (OR 2.897, 95% CI 2.129–3.942, p=0.000). The 3-Year DFS were 98.22% in the LVSI negative patients and 93.78% in the LVSI positive patients, the difference was significant (P=0.002).

Conclusion

A higher risk of lymph node metastasis and a lower 3-Year DFS was found in the LVSI-positive patients. In case of LVSI, it would be dangerous to treat patient in laparoscopy, especially in case of cervical cancer lesions >4cm.

MR-Based Radiomics Nomogram of Cervical Cancer in Prediction of the Lymph-Vascular Space Invasion preoperatively

Background

Lymph‐vascular space invasion (LVSI) is an unfavorable prognostic factor in cervical cancer. Unfortunately, there are no current clinical tools for the preoperative prediction of LVSI.

Purpose

To develop and validate an axial T₁ contrast‐enhanced (CE) MR‐based radiomics nomogram that incorporated a radiomics signature and some clinical parameters for predicting LVSI of cervical cancer preoperatively.

Study Type

Retrospective.

Population

In all, 105 patients were randomly divided into two cohorts at a 2:1 ratio.

Field Strength/Sequence

T₁ CE MRI sequences at 1.5T.

Assessment

Univariate analysis was performed on the radiomics features and clinical parameters. Multivariate analysis was performed to determine the optimal feature subset. The receiver operating characteristic (ROC) analysis was performed to evaluate the performance of prediction model and radiomics nomogram.

Statistical Tests

The Mann–Whitney U‐test and the chi‐square test were used to evaluate the performance of clinical characteristics and LVSI status by pathology. The minimum‐redundancy/maximum‐relevance and recursive feature elimination methods were applied to select the features. The radiomics model was constructed using logistic regression.

Results

Three radiomics features and one clinical characteristic were selected. The radiomics nomogram showed favorable discrimination between LVSI and non‐LVSI groups. The AUC was 0.754 (95% confidence interval [CI], 0.6326–0.8745) in the training cohort and 0.727 (95% CI, 0.5449–0.9097) in the validation cohort. The specificity and sensitivity were 0.756 and 0.828 in the training cohort and 0.773 and 0.692 in the validation cohort.

Data Conclusion

T₁ CE MR‐based radiomics nomogram serves as a noninvasive biomarker in the prediction of LVSI in patients with cervical cancer preoperatively.

Level of Evidence: 4

Technical Efficacy: Stage 2

J. Magn. Reson. Imaging 2019;49:1420–1426.