Combination Analysis of a Radiomics-Based Predictive Model With Clinical Indicators for the Preoperative Assessment of Histological Grade in Endometrial Carcinoma.

Tao Zheng,Xiaohan Wang,Juan Du,Shuo Wu,Qinglei Shi,Linsha Yang,Yanchao Dong,Lanxiang Liu

doi:10.3389/fonc.2021.582495

Tao Zheng, Xiaohan Wang + Show 6 more

Open Access

https://doi.org/10.3389/fonc.2021.582495

Copy DOI

Abstract

BackgroundHistological grade is one of the most important prognostic factors of endometrial carcinoma (EC) and when selecting preoperative treatment methods, conducting accurate preoperative grading is of great significance.PurposeTo develop a magnetic resonance imaging (MRI) radiomics-based nomogram for discriminating histological grades 1 and 2 (G1 and G2) from grade 3 (G3) EC.MethodsThis was a retrospective study included 358 patients with histologically graded EC, stratified as 250 patients in a training cohort and 108 patients in a test cohort. T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI) and a dynamic contrast-enhanced three-dimensional volumetric interpolated breath-hold examination (3D-VIBE) were performed via 1.5-Tesla MRI. To establish ModelADC, the region of interest was manually outlined on the EC in an apparent diffusion coefficient (ADC) map. To establish the radiomic model (ModelR), EC was manually segmented by two independent radiologists and radiomic features were extracted. The Radscore was calculated based on the least absolute shrinkage and selection operator regression. We combined the Radscore with carbohydrate antigen 125 (CA125) and body mass index (BMI) to construct a mixed model (ModelM) and develop the predictive nomogram. Receiver operator characteristic (ROC) and calibration curves were assessed to verify the prediction ability and the degree of consistency, respectively.ResultsAll three models showed some amount of predictive ability. Using ADC alone to predict the histological risk of EC was limited in both the cohort [area under the curve (AUC), 0.715; 95% confidence interval (CI), 0.6509–0.7792] and test cohorts (AUC, 0.621; 95% CI, 0.515–0.726). In comparison with ModelADC, the discrimination ability of ModelR showed improvement (Delong test, P < 0.0001 for both the training and test cohorts). ModelM, established based on the combination of radiomic and clinical indicators, showed the best level of predictive ability in both the training (AUC, 0.925; 95% CI, 0.898–0.951) and test cohorts (AUC, 0.915; 95% CI, 0.863–0.968). Calibration curves suggested a good fit for probability (Hosmer–Lemeshow test, P = 0.673 and P = 0.804 for the training and test cohorts, respectively).ConclusionThe described radiomics-based nomogram can be used to predict EC histological classification preoperatively.

Highlights

Endometrial carcinoma (EC) ranks sixth in terms of both morbidity and mortality amongst malignancies that affect women worldwide, with 320,000 new cases and 90,000 deaths occurring per year [1]
The ADC value of the high-risk group was lower than that of the low-risk group in this study, it was found by receiver operator characteristic (ROC) analysis that ModelADC, which was constructed by applying the ADC value alone, exhibited only limited efficiency in predicting the EC histological grade
The ADC value is a functional imaging indicator commonly employed clinically to reflect the diffusion of water molecules in tissues and it has been widely adopted for the assessment of pathological grades of breast cancer, rectal cancer and other tumors [25, 26]

Summary

Introduction

Endometrial carcinoma (EC) ranks sixth in terms of both morbidity and mortality amongst malignancies that affect women worldwide, with 320,000 new cases and 90,000 deaths occurring per year [1]. While dilatation and curettage (D&C) or hysteroscopy can suggest the histological grade before surgery, such invasive examinations are painful, carry risks of bleeding and infection and still exhibit a certain probability of missed diagnosis or misdiagnosis; the final accurate degree of tumor pathological differentiation is determined surgically [8,9,10]. Developing non-invasive methods to accurately determine tumor grade before surgery would be of great significance, helping to alleviate patients’ pain, facilitate surgical planning in advance and reduce rates of underand overtreatment. Histological grade is one of the most important prognostic factors of endometrial carcinoma (EC) and when selecting preoperative treatment methods, conducting accurate preoperative grading is of great significance.

Methods

Results

Conclusion