Added value of radiomics analysis in MRI invisible early-stage cervical cancers

A combinatorial MRI sequence-based radiomics model for preoperative prediction of microsatellite instability status in rectal cancer

This study aimed to develop an optimal radiomics model for preoperatively predicting microsatellite instability (MSI) in patients with rectal cancer (RC) based on multiparametric magnetic resonance imaging. The retrospective study included 308 RC patients who did not receive preoperative antitumor therapy, among whom 51 had MSI. Radiomics features were extracted and dimensionally reduced from T2-weighted imaging (T2WI), T1-weighted imaging (T1WI), diffusion-weighted imaging (DWI), and T1-weighted contrast enhanced (T1CE) images for each patient, and the features of each sequence were combined. Multifactor logistic regression was used to screen the optimal feature set for each combination. Different machine learning methods were applied to construct predictive MSI status models. Relative standard deviation values were determined to evaluate model performance and select the optimal model. Receiver operating characteristic (ROC) curve, calibration curve, and decision curve analyses were performed to evaluate model performance. The model constructed using the k-nearest neighbor (KNN) method combined with T2WI and T1CE images performed best. The area under the curve values for prediction of MSI with this model were 0.849 (0.804-0.887), with a sensitivity of 0.784 and specificity of 0.805. The Delong test showed no significant difference in diagnostic efficacy between the KNN-derived model and the traditional logistic regression model constructed using T1WI + DWI + T1CE and T2WI + T1WI + DWI + T1CE data (P > 0.05) and the diagnostic efficiency of the KNN-derived model was slightly better than that of the traditional model. From ROC curve analysis, the KNN-derived model significantly distinguished patients at low- and high-risk of MSI with the optimal threshold of 0.2, supporting the clinical applicability of the model. The model constructed using the KNN method can be applied to noninvasively predict MSI status in RC patients before surgery based on radiomics features from T2WI and T1CE images. Thus, this method may provide a convenient and practical tool for formulating treatment strategies and optimizing individual clinical decision-making for patients with RC.

The Utility of Contrast-Enhanced Magnetic Resonance Imaging in Uterine Cervical Cancer: A Systematic Review

Correct staging of cervical cancer is essential to establish the best therapeutic procedure and prognosis for the patient. MRI is the best imaging modality for local staging and follow-up. According to the latest ESUR guidelines, T2WI and DWI-MR sequences are fundamental in these settings, and CE-MRI remains optional. This systematic review, according to the PRISMA 2020 checklist, aims to give an overview of the literature regarding the use of contrast in MRI in cervical cancer and provide more specific indications of when it may be helpful. Systematic searches on PubMed and Web Of Science (WOS) were performed, and 97 papers were included; 1 paper was added considering the references of included articles. From our literature review, it emerged that many papers about the use of contrast in cervical cancer are dated, especially about staging and detection of tumor recurrence. We did not find strong evidence suggesting that CE-MRI is helpful in any clinical setting for cervical cancer staging and detection of tumor recurrence. There is growing evidence that perfusion parameters and perfusion-derived radiomics models might have a role as prognostic and predictive biomarkers, but the lack of standardization and validation limits their use in a research setting.

Preliminary MRI Study of Extracellular Volume Fraction for Identification of Lymphovascular Space Invasion of Cervical Cancer

BACKGROUND

Lymphovascular space invasion (LVSI) is a risk factor for poor prognosis of cervical cancer. Preoperative identification of LVSI is very difficult.

PURPOSE

To evaluate the potential of extracellular volume (ECV) fraction based on T1 mapping in preoperative identification of LVSI in cervical cancer compared with dynamic contrast-enhanced MRI (DCE-MRI).

STUDY TYPE

Retrospective.

SUBJECTS

A total of 79 patients (median age 54 years) with cervical cancer were classified into LVSI group (n = 29) and without LVSI group (n = 50) according to postoperative pathology.

FIELD STRENGTH/SEQUENCE

A 3-T, noncontrast and contrast-enhanced T1 mapping performed with volume interpolated breath hold examination (VIBE) sequence, DCE-MRI applied with 3D T1-weighted VIBE sequence.

ASSESSMENT

Regions of interest along the medial edge of the lesion were drawn on slices depicting the maximum cross-section of the tumor. The noncontrast and contrast-enhanced T1 value of the tumor and arteries in the same slice were measured, and ECV was calculated from T1 values. The parametric maps (K^trans , k_ep , and v_e ) derived from DCE-MRI standard Toft's model were evaluated.

STATISTICAL TESTS

ECV, K^trans , k_ep , and v_e between groups with and without LVSI were compared using Student's t-test. The receiver operating characteristic (ROC) curve and DeLong test were used to evaluate and compare the diagnostic performance of ECV, K^trans , k_ep , and v_e for differentiating LVSI. P < 0.05 was considered statistically significant.

RESULTS

The ECV and K^trans of the LVSI group were significantly higher than that of non-LVSI group (52.86% vs. 36.77%, 0.239 vs. 0.176, respectively), and no significant differences in K_ep or v_e values were observed (P = 0.071 and P = 0.168, respectively). The ECV fraction showed significantly higher area under ROC curve than K^trans for differentiating LVSI (0.874 vs. 0.655, respectively).

DATA CONCLUSION

ECV measurements based on T1 mapping might improve the discrimination between patients with and without LVSI in cervical cancer, showing better performance for this purpose than DCE-MRI.

EVIDENCE LEVEL

2 TECHNICAL EFFICACY: Stage 2.

Invisible cervical cancers on MRI: Can the type of histology (SCC versus non-SCC) influence surgical planning?

Background

Invisible cervical cancers on MRI can indicate less invasive surgery. Cervical cancers consist of squamous cell carcinoma (SCC) and non-SCC, each with different long-term outcomes. It is still unclear if surgical planning should be changed according to the histologic type of cervical cancer when it is not visible on MRI.

Purpose

The purpose of the study was to determine if surgical planning for cervical cancer that is not visible on MRI is influenced by the histologic type.

Materials and methods

Between January 2007 and December 2016, 155 women had Federation of Gynecology and Obstetrics (FIGO) stage 1B1 cervical cancer that was not visible on preoperative MRI. They underwent radical hysterectomies and pelvic lymph node dissections. Among them, 88 and 67 were histologically diagnosed with SCC and non-SCC, respectively. The size of the residual tumor, depth of stromal invasion, parametrial invasion, vaginal invasion, lymphovascular invasion, and lymph node metastasis were compared between these patients using the t-test, Mann-Whitney U test, Chi-squared test, or Fisher's exact test. The recurrence-free and overall 10-year survival rates were compared between the groups by Kaplan-Meier analysis.

Results

The mean sizes of residual tumors were 8.4 ± 10.4 mm in the SCC group and 12.5 ± 11.9 mm in the non-SCC group (p = 0.024). The mean depth of stromal invasion in the SCC group was 12.4 ± 21.2% (0%-100%), whereas that in the non-SCC group was 22.4 ± 24.4 (0%-93%) (p = 0.016). However, there was no difference in parametrial or vaginal invasion, lymphovascular invasion, or lymph node metastasis (p = 0.504-1.000). The recurrence-free and overall 10-year survival rates were 98.9% (87/88) and 95.5% (64/67) (p = 0.246), and 96.6% (85/88) and 95.5% (64/67) (p = 0.872), respectively.

Conclusions

The non-SCC group tends to have larger residual tumors and a greater depth of stromal invasion than the SCC group, even though neither is visible on MRI. Therefore, meticulous care is necessary for performing parametrectomy in patients with non-SCC cervical cancer.

Preoperative Assessment of MRI-Invisible Early-Stage Endometrial Cancer With MRI-Based Radiomics Analysis

BACKGROUND

Radiomics-based analyses have demonstrated impact on studies of endometrial cancer (EC). However, there have been no radiomics studies investigating preoperative assessment of MRI-invisible EC to date.

PURPOSE

To develop and validate radiomics models based on sagittal T2-weighted images (T2WI) and T1-weighted contrast-enhanced images (T1CE) for the preoperative assessment of MRI-invisible early-stage EC and myometrial invasion (MI).

STUDY TYPE

Retrospective.

POPULATION

One hundred fifty-eight consecutive patients (mean age 50.7 years) with MRI-invisible endometrial lesions were enrolled from June 2016 to March 2022 and randomly divided into the training (n = 110) and validation cohort (n = 48) using a ratio of 7:3.

FIELD STRENGTH/SEQUENCE

3-T, T2WI, and T1CE sequences, turbo spin echo.

ASSESSMENT

Two radiologists performed image segmentation and extracted features. Endometrial lesions were histopathologically classified as benign, dysplasia, and EC with or without MI. In the training cohort, 28 and 20 radiomics features were selected to build Model 1 and Model 2, respectively, generating rad-score 1 (RS1) and rad-score 2 (RS2) for evaluating MRI-invisible EC and MI.

STATISTICAL TESTS

The least absolute shrinkage and selection operator logistic regression method was used to select radiomics features. Mann-Whitney U tests and Chi-square test were used to analyze continuous and categorical variables. Receiver operating characteristic curve (ROC) and decision curve analysis were used for performance evaluation. The area under the ROC curve (AUC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were calculated. A P-value <0.05 was considered statistically significant.

RESULTS

Model 1 had good performance for preoperative detecting of MRI-invisible early-stage EC in the training and validation cohorts (AUC: 0.873 and 0.918). In addition, Model 2 had good performance in assessment of MI of MRI-invisible endometrial lesions in the training and validation cohorts (AUC: 0.854 and 0.834).

DATA CONCLUSION

MRI-based radiomics models may provide good performance for detecting MRI-invisible EC and MI.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.