The value of the apparent diffusion coefficient in differentiating type II from type I endometrial carcinoma

Construction and validation of a prediction model for preoperative prediction of Ki-67 expression in endometrial cancer patients by apparent diffusion coefficient

AIM

Ki-67 is a marker of cell proliferation and is increasingly being used as a primary outcome measure in preoperative window studies of endometrial cancer (EC). This study explored the feasibility of using apparent diffusion coefficient (ADC) values in noninvasive prediction of Ki-67 expression levels in EC patients before surgery, and constructs a nomogram by combining clinical data.

MATERIAL AND METHODS

This study retrospectively analyzed 280 EC patients who underwent preoperative magnetic resonance imaging (MRI) diffusion-weighted imaging (DWI) in our hospital from January 2017 to February 2023. Evaluate the potential nonlinear relationship between ADC values and Ki-67 expression using the nomogram. The included patients were randomized into a training set (n = 186) and a validation set (n = 84). Using a combination of logistic regression and LASSO regression results, from which the four best predictors were identified for the construction of the nomogram. The accuracy and clinical applicability of the nomogram were assessed using the receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA).

RESULTS

The results of this study showed a nonlinear correlation between ADCmin and Ki-67 expression (nonlinear P = 0.019), and the nonlinear correlation between ADCmean and Ki-67 expression (nonlinear P = 0.019). In addition, this study constructed the nomogram by incorporating ADCmax, International Federation of Gynecology and Obstetrics (FIGO), and chemotherapy. The area under the curve (AUC) values of the ROC for nomogram, ADCmax, FIGO, chemotherapy and grade in the training set were 0.783, 0.718, 0.579, 0.636, and 0.654, respectively. In the validation set, the AUC values for nomogram, ADCmax, FIGO, chemotherapy, and grade were 0.820, 0.746, 0.558, 0.542, and 0.738, respectively. In addition, the calibration curves and the DCA curves suggested a better predictive efficacy of the model.

CONCLUSION

A nomogram prediction model constructed on the basis of ADCmax values combined with clinical data can be used as an effective method to noninvasively assess Ki-67 expression in EC patients before surgery.

Diagnostic utility of apparent diffusion coefficient in preoperative assessment of endometrial cancer: are we ready for the 2023 FIGO staging?

BACKGROUND

Although endometrial cancer (EC) is staged surgically, magnetic resonance imaging (MRI) plays a critical role in assessing and selecting the most appropriate treatment planning. We aimed to assess the diagnostic performance of quantitative analysis of diffusion-weighted imaging (DWI) in preoperative assessment of EC.

METHODS

Prospective analysis was done for sixty-eight patients with pathology-proven endometrial cancer who underwent MRI and DWI. Apparent diffusion coefficient (ADC) values were measured by two independent radiologists and compared with the postoperative pathological results.

RESULTS

There was excellent inter-observer reliability in measuring ADCmean values. There were statistically significant lower ADCmean values in patients with deep myometrial invasion (MI), cervical stromal invasion (CSI), type II EC, and lympho-vascular space involvement (LVSI) (AUC = 0.717, 0.816, 0.999, and 0.735 respectively) with optimal cut-off values of ≤ 0.84, ≤ 0.84, ≤ 0.78 and ≤ 0.82 mm2/s respectively. Also, there was a statistically significant negative correlation between ADC values and the updated 2023 FIGO stage and tumor grade (strong association), and the 2009 FIGO stage (medium association).

CONCLUSIONS

The preoperative ADCmean values of EC were significantly correlated with main prognostic factors including depth of MI, CSI, EC type, grade, nodal involvement, and LVSI.

Multiparameter MRI-based radiomics analysis for preoperative prediction of type II endometrial cancer

Objectives

This study aimed to develop and validate a radiomics nomogram based on multiparameter MRI for preoperative differentiation of type II and type I endometrial carcinoma (EC).

Methods

A total of 403 EC patients from two centers were retrospectively recruited (training cohort, 70 %; validation cohort, 30 %). Radiomics features were extracted from T2-weighted imaging, dynamic contrast-enhanced T1-weighted imaging at delayed phase(DCE4), and apparent diffusion coefficient (ADC) maps. Following dimensionality reduction, radiomics models were developed by logistic regression (LR), random forest (RF), bootstrap aggregating (Bagging), support vector machine (SVM), artificial neural network (ANN), and naive bayes (NB) algorithms. The diagnostic performance of each radiomics model was evaluated using the ROC curve. A nomogram was constructed by incorporating the optimal radiomics signatures with significant clinical-radiological features and immunohistochemistry (IHC) markers obtained from preoperative curettage specimens. The diagnostic performance and clinical value of the nomogram were evaluated using ROC curves, calibration curves, and decision curve analysis (DCA).

Results

Among the radiomics models, the NB model, developed from 12 radiomics features derived from ADC and DCE4 sequences, exhibited strong performance in both training and validation sets, with the AUC values of 0.927 and 0.869, respectively. The nomogram, incorporating the radiomics model with significant clinical-radiological features and IHC markers, demonstrated superior performance in both the training (AUC = 0.951) and the validation sets (AUC = 0.915). Additionally, it exhibited excellent calibration and clinical utility.

Conclusions

The radiomics nomogram has great potential to differentiate type II from type I EC, which may be an effective tool to guide clinical decision-making for EC patients.

Determination of p53abn endometrial cancer: a multitask analysis using radiological-clinical nomogram on MRI

OBJECTIVES

We aimed to differentiate endometrial cancer (EC) between TP53mutation (P53abn) and Non-P53abn subtypes using radiological-clinical nomogram on EC body volume MRI.

METHODS

We retrospectively recruited 227 patients with pathologically proven EC from our institution. All these patients have undergone molecular pathology diagnosis based on the Cancer Genome Atlas. Clinical characteristics and histological diagnosis were recorded from the hospital information system. Radiomics features were extracted from online Pyradiomics processors. The diagnostic performance across different acquisition protocols was calculated and compared. The radiological-clinical nomogram was established to determine the nonendometrioid, high-risk, and P53abn EC group.

RESULTS

The best MRI sequence for differentiation P53abn from the non-P53abn group was contrast-enhanced T1WI (test AUC: 0.8). The best MRI sequence both for differentiation endometrioid cancer from nonendometrioid cancer and high-risk from low- and intermediate-risk groups was apparent diffusion coefficient map (test AUC: 0.665 and 0.690). For all 3 tasks, the combined model incorporating all the best discriminative features from each sequence yielded the best performance. The combined model achieved an AUC of 0.845 in the testing cohorts for P53abn cancer identification. The MR-based radiomics diagnostic model performed better than the clinical-based model in determining P53abn EC (AUC: 0.834 vs 0.682).

CONCLUSION

In the present study, the diagnostic model based on the combination of both radiomics and clinical features yielded a higher performance in differentiating nonendometrioid and P53abn cancer from other EC molecular subgroups, which might help design a tailed treatment, especially for patients with high-risk EC.

ADVANCES IN KNOWLEDGE

(1) The contrast-enhanced T1WI was the best MRI sequence for differentiation P53abn from the non-P53abn group (test AUC: 0.8). (2) The radiomics-based diagnostic model performed better than the clinical-based model in determining P53abn EC (AUC: 0.834 vs 0.682). (3) The proposed model derived from multi-parametric MRI images achieved a higher accuracy in P53abn EC identification (AUC: 0.845).

MRI-based radiomics model for distinguishing Stage I endometrial carcinoma from endometrial polyp: a multicenter study

BACKGROUND

Patients with early endometrial carcinoma (EC) have a good prognosis, but it is difficult to distinguish from endometrial polyps (EPs).

PURPOSE

To develop and assess magnetic resonance imaging (MRI)-based radiomics models for discriminating Stage I EC from EP in a multicenter setting.

MATERIAL AND METHODS

Patients with Stage I EC (n = 202) and EP (n = 99) who underwent preoperative MRI scans were collected in three centers (seven devices). The images from devices 1-3 were utilized for training and validation, and the images from devices 4-7 were utilized for testing, leading to three models. They were evaluated by the area under the receiver operating characteristic curve (AUC) and metrics including accuracy, sensitivity, and specificity. Two radiologists evaluated the endometrial lesions and compared them with the three models.

RESULTS

The AUCs of device 1, 2_ada, device 1, 3_ada, and device 2, 3_ada for discriminating Stage I EC from EP were 0.951, 0.912, and 0.896 for the training set, 0.755, 0.928, and 1.000 for the validation set, and 0.883, 0.956, and 0.878 for the external validation set, respectively. The specificity of the three models was higher, but the accuracy and sensitivity were lower than those of radiologists.

CONCLUSION

Our MRI-based models showed good potential in differentiating Stage I EC from EP and had been validated in multiple centers. Their specificity was higher than that of radiologists and may be used for computer-aided diagnosis in the future to assist clinical diagnosis.

Radiomics nomogram in aiding preoperatively dilatation and curettage in differentiating type II and type I endometrial cancer

AIM

To established a radiomics nomogram for improving the dilatation and curettage (D&C) result in differentiating type II from type I endometrial cancer (EC) preoperatively.

MATERIAL AND METHODS

EC patients (n=875) were enrolled retrospectively and divided randomly into a training cohort (n=437) and a test cohort (n=438), according to the ratio of 1:1. Radiomics signatures were extracted and selected from apparent diffusion coefficient (ADC) maps. A multivariate logistic regression analysis was used to identify the independent clinical risk factors. An ADC based-radiomics nomogram was built by integrating the selected radiomics signatures and the independent clinical risk factors. Decision curve analysis (DCA) was conducted to determine the clinical usefulness of the radiomics nomogram. The net reclassification index (NRI) and total integrated discrimination index (IDI) were calculated to compare the discrimination performances between the radiomics nomogram and the D&C result.

RESULTS

Receiver operating characteristic (ROC) curves showed that the clinical risk factors, the D&C, and the ADC based-radiomics nomogram yielded areas under the ROC curves (AUCs) of 0.70 (95% CI: 0.64-0.76), 0.85 (95% CI: 0.80-0.89), and 0.93 (95% CI: 0.90-0.96) in the training cohort and 0.64 (95% CI: 0.57-0.71), 0.82 (95% CI: 0.77-0.87) and 0.91 (95% CI: 0.87-0.95) in the test cohort, respectively. The DCA, NRI, and IDI demonstrated the clinically usefulness of the ADC based-radiomics nomogram.

CONCLUSION

The ADC-based radiomics nomogram could be used to improve the D&C result in differentiating type II from type I EC preoperatively.

The Preeminent Value of the Apparent Diffusion Coefficient in Assessing High-Risk Factors and Prognosis for Stage I Endometrial Carcinoma Patients

Objectives

To evaluate the role of the apparent diffusion coefficient (ADC) value in the individualized management of stage I endometrial carcinoma (EC).

Methods

A retrospective analysis was performed on 180 patients with stage I EC who underwent 1.5-T magnetic resonance imaging. The mean ADC (mADC), minimum ADC (minADC), and maximum ADC (maxADC) values of each group were measured and compared. We analyzed the relationship between ADC values and stage I EC prognosis by Kaplan-Meier method and Cox proportional hazards analysis.

Results

Patients with lower ADC values were more likely to be characterized by higher grades, specific histological subtypes and deeper myometrial invasion. The mADC, minADC and maxADC values (×10^-3 mm²/s) were 1.045, 0.809 and 1.339, respectively, in grade 1/2 endometrioid carcinoma with superficial myometrial invasion, which significantly differed from those in grade 3 or nonendometrioid carcinoma or with deep myometrial invasion (0.929, 0.714 and 1.215) (P=<0.001, <0.001 and <0.001). ADC values could be used to predict these clinicopathological factors. Furthermore, the group with higher ADC values showed better disease-free survival and overall survival.

Conclusions

The present study indicated that ADC values were associated with the high-risk factors for stage I EC and to assess whether fertility-sparing, ovarian preservation or omission of lymphadenectomy represent viable treatment options. Moreover, this information may be applied to predict prognosis. Thus, ADC values could contribute to managing individualized therapeutic schedules to improve quality of life.

MRI-based radiomics and ADC values are related to recurrence of endometrial carcinoma: a preliminary analysis

Background

To identify predictive value of apparent diffusion coefficient (ADC) values and magnetic resonance imaging (MRI)-based radiomics for all recurrences in patients with endometrial carcinoma (EC).

Methods

One hundred and seventy-four EC patients who were treated with operation and followed up in our institution were retrospectively reviewed, and the patients were divided into training and test group. Baseline clinicopathological features and mean ADC (ADC_mean), minimum ADC (ADC_min), and maximum ADC (ADC_max) were analyzed. Radiomic parameters were extracted on T2 weighted images and screened by logistic regression, and then a radiomics signature was developed to calculate the radiomic score (radscore). In training group, Kaplan–Meier analysis was performed and a Cox regression model was used to evaluate the correlation between clinicopathological features, ADC values and radscore with recurrence, and verified in the test group.

Results

ADC_mean showed inverse correlation with recurrence, while radscore was positively associated with recurrence. In univariate analyses, FIGO stage, pathological types, myometrial invasion, ADC_mean, ADC_min and radscore were associated with recurrence. In the training group, multivariate Cox analysis showed that pathological types, ADC_mean and radscore were independent risk factors for recurrence, which were verified in the test group.

Conclusions

ADC_mean value and radscore were independent predictors of recurrence of EC, which can supplement prognostic information in addition to clinicopathological information and provide basis for individualized treatment and follow-up plan.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-021-08988-x.

Nomograms of Combining Apparent Diffusion Coefficient Value and Radiomics for Preoperative Risk Evaluation in Endometrial Carcinoma

Objectives

To evaluate the value of nomogram models combining apparent diffusion coefficient (ADC) value and radiomic features on magnetic resonance imaging (MRI) in predicting the type, grade, deep myometrial invasion (DMI), lymphovascular space invasion (LVSI), and lymph node metastasis (LNM) of endometrial carcinoma (EC) preoperatively.

Methods

This study included 210 EC patients. ADC value was calculated, and radiomic features were measured on T2-weighted images. The univariate and multivariate logistic regressions and cross-validations were performed to reduce valueless features, then radiomics signatures were developed. Nomogram models using ADC combined with radiomic features were developed in the training cohort. The receiver operating characteristic (ROC) curve was performed to estimate the diagnostic efficiency of nomogram models by the area under the curve (AUC) in the training and validation cohorts.

Results

The ADC value was significantly different between each subgroup. Radiomic features were ultimately limited to four features for type, six features for grade, six features for DMI, four features for LVSI, and eight features for LNM for the nomogram models. The AUC of the nomogram model combining ADC value and radiomic features in the training and validation cohorts was 0.851 and 0.867 for type, 0.959 and 0.880 for grade, 0.839 and 0.766 for DMI, 0.816 and 0.746 for LVSI, and 0.910 and 0.897 for LNM.

Conclusions

The nomogram models of ADC value combined with radiomic features were associated with the type, grade, DMI, LVSI, and LNM of EC, and provide an effective, non-invasive method to evaluate preoperative risk stratification for EC.