Pathologic Risk Factors and Oncologic Outcomes in Early-stage Cervical Cancer Patients Treated by Radical Hysterectomy and Pelvic Lymphadenectomy at a Thai University Hospital: A 7 year Retrospective Review

Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre study

OBJECTIVES

To develop and validate a magnetic resonance imaging-based (MRI) deep multiple instance learning (D-MIL) model and combine it with clinical parameters for preoperative prediction of lymph node metastasis (LNM) in operable cervical cancer.

METHODS

A total of 392 patients with cervical cancer were retrospectively enrolled. Clinical parameters were analysed by logistical regression to construct a clinical model (M1). A ResNet50 structure is applied to extract features at the instance level without using manual annotations about the tumour region and then construct a D-MIL model (M2). A hybrid model (M3) was constructed by M1 and M2 scores. The diagnostic performance of each model was evaluated by the area under the receiver operating characteristic curve (AUC) and compared using the Delong method. Disease-free survival (DFS) was evaluated by the Kaplan‒Meier method.

RESULTS

SCC-Ag, maximum lymph node short diameter (LNmax), and tumour volume were found to be independent predictors of M1 model. For the diagnosis of LNM, the AUC of the training/internal/external cohort of M1 was 0.736/0.690/0.732, the AUC of the training/internal/external cohort of M2 was 0.757/0.714/0.765, and the AUC of the training/internal/external cohort of M3 was 0.838/0.764/0.835. M3 showed better performance than M1 and M2. Through the survival analysis, patients with higher hybrid model scores had a shorter time to reach DFS.

CONCLUSION

The proposed hybrid model could be used as a personalised non-invasive tool, which is helpful for predicting LNM in operable cervical cancer. The score of the hybrid model could also reflect the DFS of operable cervical cancer.

CRITICAL RELEVANCE STATEMENT

Lymph node metastasis is an important factor affecting the prognosis of cervical cancer. Preoperative prediction of lymph node status is helpful to make treatment decisions, improve prognosis, and prolong survival time.

KEY POINTS

• The MRI-based deep-learning model can predict the LNM in operable cervical cancer. • The hybrid model has the highest diagnostic efficiency for the LNM prediction. • The score of the hybrid model can reflect the DFS of operable cervical cancer.

Novel prognostic nomograms in cervical cancer based on analysis of 1075 patients

OBJECTIVE

To explore the factors affecting the prognosis of cervical cancer (CC), and to construct and evaluate predictive nomograms to guide individualized clinical treatment.

METHODS

The clinicopathological and follow-up data of CC patients from June 2013 to December 2019 in Sun Yat-sen Memorial Hospital of Sun Yat-sen University were retrospectively analyzed. Log-rank test was used for univariate survival analysis, and Cox multivariate regression was used to identify independent prognostic factors, based on which nomogram models were established and evaluated in multiple aspects.

RESULTS

Patients were randomly assigned into the training (n = 746) and validation sets (n = 329). Survival analysis of the training set identified cervical myometrial invasion, parametrial involvement, and malignant tumor history as prognosticators of postoperative DFS and pathological type, cervical myometrial invasion, and history of STD for OS. C-index was 0.799 and 0.839 for the nomograms for DFS and OS, respectively. Calibration curves and Brier scores also indicated high performance. Importantly, decision curve analysis suggested great clinical applicability of these nomograms.

CONCLUSIONS

In this study, we analyzed a cohort of 1075 CC patients and identified DFS- or OS-associated clinicohistologic characteristics. Two nomograms were subsequently constructed for DFS and OS prognostication, respectively, and showed high performance in terms of discrimination, calibration, and clinical applicability. These models may facilitate individualized treatment and patient selection for clinical trials. Future investigations with larger cohorts and prospective designs are warranted for validating these prognostic models.

Machine learning applied to MRI evaluation for the detection of lymph node metastasis in patients with locally advanced cervical cancer treated with neoadjuvant chemotherapy

PURPOSE

Concurrent cisplatin-based chemotherapy and radiotherapy (CCRT) plus brachytherapy is the standard treatment for locally advanced cervical cancer (LACC). Platinum-based neoadjuvant chemotherapy (NACT) followed by radical hysterectomy is an alternative for patients with stage IB2-IIB disease. Therefore, the correct pre-treatment staging is essential to the proper management of this disease. Pelvic magnetic resonance imaging (MRI) is the gold standard examination but studies about MRI accuracy in the detection of lymph node metastasis (LNM) in LACC patients show conflicting data. Machine learning (ML) is emerging as a promising tool for unraveling complex non-linear relationships between patient attributes that cannot be solved by traditional statistical methods. Here we investigated whether ML might improve the accuracy of MRI in the detection of LNM in LACC patients.

METHODS

We analyzed retrospectively LACC patients who underwent NACT and radical hysterectomy from 2015 to 2020. Demographic, clinical and MRI characteristics before and after NACT were collected, as well as information about post-surgery histopathology. Random features elimination wrapper was used to determine an attribute core set. A ML algorithm, namely Extreme Gradient Boosting (XGBoost) was trained and validated with tenfold cross-validation. The performances of the algorithm were assessed.

RESULTS

Our analysis included n.92 patients. FIGO stage was IB2 in n.4/92 (4.3%), IB3 in n.42/92 (45%), IIA1 in n.1/92 (1.1%), IIA2 in n.16/92 (17.4%) and IIB in n.29/92 (31.5%). Despite detected neither at pre-treatment and post-treatment MRI in any patients, LNM occurred in n.16/92 (17%) patients. The attribute core set used to train ML algorithms included grading, histotypes, age, parity, largest diameter of lesion at either pre- and post-treatment MRI, presence/absence of fornix infiltration at pre-treatment MRI and FIGO stage. XGBoost showed a good performance (accuracy 89%, precision 83%, recall 78%, AUROC 0.79).

CONCLUSIONS

We developed an accurate model to predict LNM in LACC patients in NACT, based on a ML algorithm requiring few easy-to-collect attributes.

Is the pathologic tumor size associated with survival in early cervical cancer treated with radical hysterectomy and adjuvant radiotherapy?

OBJECTIVE

In 2018 International Federation of Gynecology and Obstetrics (FIGO) staging system of uterine cervix cancer, size criteria of primary tumor has been revised. This study aimed to evaluate the validity of this new size criteria (<2, 2-4, and ≧4 cm) in patients who underwent radical hysterectomy and adjuvant radiation therapy (RT) for early cervical cancer.

MATERIALS AND METHODS

We retrospectively examined 312 patients who underwent radical hysterectomy and adjuvant RT for early cervical cancer (IB-IIA) from 2001 to 2014. The effects of clinical and pathological factors on disease-free survival (DFS) and overall survival (OS) were evaluated in univariate and multivariate analyses.

RESULTS

After a median follow-up of 71.5 months, the 5-year DFS and OS rates were 89.5% and 94.7%, respectively. The primary tumor size was not a significant factor for DFS (p = 0.382) or OS (p = 0.725) in all patients.

CONCLUSION

Primary tumor size was not a significant factor for survival in patients who received hysterectomy and adjuvant RT for early cervical cancer. Adequacy of new tumor size criteria (<2, 2-4, and ≧4 cm) in new 2018 FIGO stage needs to be validated in further studies.

Clinical value of MRI, serum SCCA, and CA125 levels in the diagnosis of lymph node metastasis and para-uterine infiltration in cervical cancer

Background

Cervical cancer shows great differences in depth of invasion, metastasis, and other biological behaviors. The location of the lesion is special, so it is usually difficult to determine the clinical stage. This study aimed to explore the clinical value of magnetic resonance imaging (MRI) and tumor serum markers for the preoperative diagnosis of cervical cancer lymph node metastasis and para-uterine invasion.

Methods

A total of 200 patients with cervical cancer admitted to our hospital from January 2019 to January 2020 were collected as the research subjects. Comparing the diagnosis results of preoperative MRI scan, serum tumor markers, and postoperative pathological examination using single factor comparison, we determined the MRI scan results, the comprehensive matching rate between serum tumor markers (squamous cell carcinoma antigen (SCCA), carbohydrate antigen 125 (CA125)) and postoperative pathological results, and the differences of sensitivity, specificity, and accuracy in the prediction of lymph node metastasis and para-uterine infiltration of cervical cancer.

Results

The levels of SCCA and CA125 in patients with para-uterine invasion and lymph node metastasis were higher than those of patients without invasion and metastasis. Among them, the level of SCCA was significantly different (P<0.05). The level of CA125 was not statistically significant (P>0.05), so MRI combined with serum SCCA was selected for combined diagnosis in the later period. The sensitivity, specificity, and accuracy of MRI diagnosis of cervical cancer and para-uterine infiltrating lymph node metastasis and metastasis were 55.2, 91.6, and 89.5% and 55.2, 91.6, and 89.5%, respectively. These data in MRI combined with serum SCCA were 76.3, 95.3, and 94.3% and 63.2, 96.0, and 95.1%, respectively. The accuracy of tumor markers combined with MRI in the diagnosis of cervical cancer lymph node metastasis and para-uterine invasion was higher than that of MRI.

Conclusions

MRI combined with serum SCCA can more accurately identify cervical cancer lymph node metastasis and para-uterine invasion compared with MRI alone. Tumor marker combined with MRI diagnosis is an important auxiliary method for cervical cancer treatment and can provide comprehensive and reliable clinical evidence for evaluation before cervical cancer surgery.

The feasibility of 18F-FDG PET/CT for predicting pathologic risk status in early-stage uterine cervical squamous cancer

Background

Postoperative pathologic risk factors (PRFs) could increase the recurrence rate in early-stage uterine cervical squamous cancer (ECSC). Our study intended to explore the efficiency of ¹⁸F-FDG PET/CT for assessing the pathologic risk status (PRS) in ECSC patients.

Methods

This retrospective study was performed in 240 ECSC patients with stage IA2-IIA2 (FIGO 2009), who underwent preoperative PET/CT scans and subsequent radical surgery between January 2010 and July 2015. Intermediate-risk (tumour diameter ≥ 4 cm, stromal invasion depth ≥ 1/2, lymphovascular space invasion (LVSI)), and high-risk factors (parametria involvement, positive surgery margin, pelvic lymph node metastasis) were confirmed by postoperative pathology. Patients with none of these PRFs were at a low risk for relapse. One of these PRFs was defined as positive risk. The relationship between each PRF and ¹⁸F-FDG uptake was analysed by t-test. Chi-square tests and logistic regression analyses were used to determine the efficiency of PET/CT parameters for assessing the PRS. The area under the curve (AUC) was used as an indicator for predictive efficiency.

Results

Patients with higher SUVmax (p < 0.001), MTV (p < 0.001) and TLG (p < 0.001) had larger tumour sizes and deeper stromal invasion. Further multivariate analyses showed SUVmax and TLG were independent predictors for positive- and intermediate-risk status. In high-risk group, MTV and TLG were associated with pelvic lymph node metastasis and parametria involvement. However, only MTV was a significant indicator.

Conclusions

Preoperative ¹⁸F-FDG PET/CT had an independent predictive value for PRS in ECSC.

Radiomics Analysis of Multiparametric MRI for the Preoperative Prediction of Lymph Node Metastasis in Cervical Cancer

Objective: To develop and validate a radiomics predictive model based on multiparameter MR imaging features and clinical features to predict lymph node metastasis (LNM) in patients with cervical cancer.

Material and Methods: A total of 168 consecutive patients with cervical cancer from two centers were enrolled in our retrospective study. A total of 3,930 imaging features were extracted from T2-weighted (T2W), ADC, and contrast-enhanced T1-weighted (cT1W) images for each patient. Four-step procedures, mainly minimum redundancy maximum relevance (MRMR) and least absolute shrinkage and selection operator (LASSO) regression, were applied for feature selection and radiomics signature building in the training set from center I (n = 115). Combining clinical risk factors, a radiomics nomogram was then constructed. The models were then validated in the external validation set comprising 53 patients from center II. The predictive performance was determined by its calibration, discrimination, and clinical usefulness.

Results: The radiomics signature derived from the combination of T2W, ADC, and cT1W images, composed of six LN-status-related features, was significantly associated with LNM and showed better predictive performance than signatures derived from either of them alone in both sets. Encouragingly, the radiomics signature also showed good discrimination in the MRI-reported LN-negative subgroup, with AUC of 0.825 (95% CI: 0.732–0.919). The radiomics nomogram that incorporated radiomics signature and MRI-reported LN status also showed good calibration and discrimination in both sets, with AUCs of 0.865 (95% CI: 0.794–0.936) and 0.861 (95% CI: 0.733–0.990), respectively. Decision curve analysis confirmed its clinical usefulness.

Conclusion: The proposed MRI-based radiomics nomogram has good performance for predicting LN metastasis in cervical cancer and may be useful for improving clinical decision making.

Feasibility of an ADC-based radiomics model for predicting pelvic lymph node metastases in patients with stage IB-IIA cervical squamous cell carcinoma

OBJECTIVES

To investigate the prediction value of a radiomics model based on apparent diffusion coefficient (ADC) maps for pelvic lymph node metastasis (PLNM) in patients with stage IB-IIA cervical squamous cell carcinoma (CSCC).

METHODS

A total of 153 stage IB-IIA CSCC patients who underwent preoperative MRI including DWI from January 2015 to October 2017 were retrospectively studied and divided into a training cohort ( n = 102) and a validation cohort ( n = 51). Radiomics features were extracted from the ADC maps. The one-way ANOVA method, Mann-Whitney U test and Pearson's correlation analysis were used for selecting radiomics features. Logistic regression analyses were used to develop the model. ROC analyses were used to evaluate the prediction performance of the model.

RESULTS

Clinical stage, tumor diameter, and MR-reported lymph node (LN) status were significantly associated with LN status ( p < 0.05 for both the training and validation cohorts). The radiomics model, which incorporated clinical stage, MR-reported LN status, and grey-level non-uniformity, showed good predictive performance in the training group (AUC 0.864; 95% CI, 0.782 - 0.924) and the validation group (AUC 0.870; 95% CI, 0.747 - 0.948). The performance of the radiomics model was significantly better than that of each predictive factor alone.

CONCLUSION

The presented radiomics model, a non-invasive preoperative prediction tool, has the potential to have more predictive efficacy than clinical and radiological factors for differentiating between metastatic and non-metastatic lymph nodes.

ADVANCES IN KNOWLEDGE

A radiomics model derived from the ADC maps of primary lesions demonstrated good performance for predicting PLNM in stage IB-IIA CSCC patients and may help to improve clinical decision-making.