Quantitative assessment of diffusion kurtosis imaging depicting deep myometrial invasion: a comparative analysis with diffusion-weighted imaging

The Added Value of ADC-based Nomogram in Assessing the Depth of Myometrial Invasion of Endometrial Endometrioid Adenocarcinoma

RATIONALE AND OBJECTIVES

To explore the potential value of the apparent diffusion coefficient (ADC)-based nomogram models in preoperatively assessing the depth of myometrial invasion of endometrial endometrioid adenocarcinoma (EEA).

MATERIALS AND METHODS

Preoperative magnetic resonance imaging (MRI) of 210 EEA patients were retrospectively analyzed. ADC histogram metrics derive from the whole-tumor regions of interest. Univariate and multivariate analyses were used to screen the ADC histogram metrics and clinical characteristics for nomogram model building. The diagnostic sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) of two radiologists without and with the assistance of models were calculated and compared.

RESULTS

Two nomogram models were developed for predicting no myometrial invasion (NMI) and deep myometrial invasion (DMI) with area under the curves of 0.85 and 0.82, respectively. With the assistance of models, the overall accuracies were significantly improved [radiologist_1, 73.3% vs 86.2% (p = 0.001); radiologist_2, 80.0% vs 91.0% (p = 0.002)]. In determining NMI, the sensitivity and PPV were greatly improved but not significant for radiologist_1 (51.9% vs 77.8% and 46.7% vs 75.0%, p = 0.229 and 0.511), and under/near the significance level for radiologist_2 (59.3% vs 88.9% and 57.1% vs 82.8%, p = 0.041 and 0.065), while the specificity, accuracy, and NPV were significantly improved (all p < 0.001). In determining DMI, all sensitivity, specificity, accuracy, PPV, and NPV were significantly improved (all p < 0.001).

CONCLUSION

The ADC-based nomogram models can improve the diagnostic performance of radiologist in preoperatively assessing the depth of myometrial invasion and facilitate optimizing clinical individualized treatment decisions.

Diffusion kurtosis imaging with multiple quantitative parameters for predicting microsatellite instability status of endometrial carcinoma

PURPOSE

To explore the value of Diffusion kurtosis imaging (DKI) with multiple quantitative parameters in predicting microsatellite instability (MSI) status in endometrial carcinoma (EC).

METHODS

Data of 38 patients with EC were retrospectively analyzed, including 12 MSI and 26 microsatellite stability (MSS). All patients underwent preoperative 1.5T MR examination. The quantitative values of the DKI sequence in the tumor parenchyma of the two groups, including mean kurtosis (MK), axial kurtosis (Ka), radial kurtosis (Kr), fractional anisotropy (FA), fractional anisotropy of kurtosis (FAk), mean diffusivity (MD), axial diffusivity (Da), and radial diffusivity (Dr) were measured by two observers, respectively.

RESULTS

The MK, Ka, Kr, FA, FAk, MD, Da, and Dr values of the MSI group were 1.074 ± 0.162, 1.253 ± 0.229, 0.886 ± 0.205, 0.207 ± 0.041, 0.397 ± 0.129, 0.890 ± 0.158 μm2/ms, 1.083 ± 0.218 μm2/ms, and 0.793 ± 0.133 μm2/ms, and 0.956 (0.889,1.002), 1.048 ± 0.211, 0.831 ± 0.099, 0.188 ± 0.061, 0.334 (0.241,0.410), 1.043 ± 0.217 μm2/ms, 1.235 ± 0.229 μm2/ms, and 0.946 ± 0.215 μm2/ms in the MSS group. The MK and Ka values of the MSI group were higher than those of the MSS group (P<0.05), while the MD and Dr values were lower than those of the MSS group (P<0.05). The AUC of MK, Ka, MD, and Dr values in predicting MSI status of EC was 0.763, 0.729, 0.731, 0.748, respectively. The sensitivity was 58.3%, 50.0%, 65.4%, 61.5%, and the specificity was 96.2%, 92.3%, 75.0%, 83.3%, respectively.

CONCLUSION

DKI can provide multiple quantitative parameters for predicting the MSI status of EC, and assist gynecologist to optimize the treatment plan for the patients.

An MR-based radiomics nomogram including information from the peritumoral region to predict deep myometrial invasion in stage I endometrioid adenocarcinoma: a preliminary study

OBJECTIVE

To develop and validate an MR-based radiomics nomogram combining different imaging sequences (ADC mapping and T2 weighted imaging (T2WI)), different tumor regions (combined intra- and peritumoral regions), and different parameters (clinical features, tumor morphological features, and radiomics features) while considering different MR field strengths in predicting deep myometrial invasion (MI) in Stage I endometrioid adenocarcinoma (EEA).

METHODS

A total of 202 patients were retrospectively analyzed and divided into two cohorts (training cohort, 1.5 T MR, n = 131; validation cohort, 3.0 T MR, n = 71). Axial ADC mapping and T2WI were conducted. Radiomics features were extracted from intra- and peritumoral regions. Least absolute shrinkage and selection operator regression, univariate analysis, and multivariate logistic regression were used to select radiomics features and tumor morphological and clinical parameters. The area under the receiver operator characteristic curve (AUC) was calculated to evaluate the performance of the prediction model and radiomics nomogram.

RESULTS

Ten radiomics features, 4 morphological parameters and 1 clinical characteristic were selected. The radiomics nomogram achieved good discrimination between the superficial and deep MI cohorts. The AUC was 0.927 (95% confidence interval [CI]: 0.865, 0.967) in the training cohort and 0.921 (95% CI: 0.872, 0.948) in the validation cohort. The specificity and sensitivity were 92.0 and 78.9% in the training cohort and 83.0 and 77.8% in the validation cohort, respectively.

CONCLUSION

The radiomics nomogram showed good performance in predicting the depth of MI in Stage I EEA before surgery and might be useful for surgical patient management.

ADVANCES IN KNOWLEDGE

An MR-based radiomics nomogram was useful for predicting deep MI in Stage I EEA patients (AUCtrain = 0.927, AUCvalidation = 0.921). The intra- and peritumoral radiomics features complemented each other. The nomogram was developed and validated with different MR field strengths, suggesting that the model demonstrates good generalizability.

Comparison of ZOOMit-DWI sequence and conventional DWI sequence in endometrial cancer

OBJECTIVES

Magnetic resonance diffusion-weighted imaging (DWI) has important clinical value in diagnosis and curative effect evaluation on endometrial carcinoma. How to improve the detection rate of endometrial small lesions by DWI is the research focus of MRI technology. This study aims to analyze the image quality of small field MRI ZOOMit-DWI sequence and conventional single-shot echo-planar imaging (SS-EPI) DWI sequence in the scanning of endometrial carcinoma, and to explore the clinical value of ZOOMit-DWI sequence.

METHODS

A total of 37 patients with endometrial carcinoma diagnosed by operation and pathology in the Second Xiangya Hospital of Central South University from July 2019 to May 2021 were collected. All patients were scanned with MRI ZOOMit-DWI sequence and SS-EPI DWI sequence before operation. Two radiologists subjectively evaluated the anatomical details, artifacts, geometric deformation and focus definition of the 2 groups of DWI images. At the same time, the signal intensity were measured and the signal-to-noise ratio (SNR), contrast to noise ratio (CNR), and apparent diffusion coefficient (ADC) of the 2 DWI sequences were calculated for objective evaluation. The differences of subjective score, objective score and ADC value of the 2 DWI sequences were analyzed.

RESULTS

The SNR of the ZOOMit-DWI group was significantly higher than that of the SS-EPI DWI group (301.96±141.85 vs 94.66±41.26), and the CNR of the ZOOMit-DWI group was significantly higher than that of the SS-EPI DWI group (185.05±105.45 vs 57.91±31.54, P<0.05). There was no significant difference in noise standard deviation between the ZOOMit-DWI group and the SS-EPI DWI group (P>0.05). The subjective score of anatomical detail and focus definition in the ZOOMit-DWI group was significantly higher than that of the SS-EPI DWI group (both P<0.05). The subjective score of artifacts and geometric deformation of ZOOMit-DWI group was significantly lower than that of the SS-EPI DWI group (both P<0.05). ADC had no significant difference between the ZOOMit-DWI group and the SS-EPI DWI group (P>0.05).

CONCLUSIONS

The image quality of ZOOMit-DWI is significantly higher than that of conventional SS-EPI DWI. In the MRI DWI examination of endometrial carcinoma, ZOOMit-DWI can effectively reduce the geometric deformation and artifacts of the image, which is more conducive to clinical diagnosis and treatment.

Evaluation of Amide Proton Transfer-Weighted Imaging for Risk Factors in Stage I Endometrial Cancer: A Comparison With Diffusion-Weighted Imaging and Diffusion Kurtosis Imaging

Background

Endometrial cancer (EC) is one of the most common gynecologic malignancies in clinical practice. This study aimed to compare the value of diffusion-weighted imaging (DWI), diffusion kurtosis imaging (DKI), and amide proton transfer-weighted imaging (APTWI) in the assessment of risk stratification factors for stage I EC including histological subtype, grade, stage, and lymphovascular space invasion (LVSI).

Methods

A total of 72 patients with stage I EC underwent pelvic MRI. The apparent diffusion coefficient (ADC), mean diffusivity (MD), mean kurtosis (MK), and magnetization transfer ratio asymmetry (MTRasym at 3.5 ppm) were calculated and compared in risk groups with the Mann–Whitney U test or independent samples t-test. Spearman’s rank correlation was applied to depict the correlation of each parameter with risk stratification. The diagnostic efficacy was evaluated with receiver operating characteristic (ROC) curve analysis and compared using the DeLong test. A multivariate logistic regression was conducted to explore the optimal model for risk prediction.

Results

There were significantly greater MTRasym (3.5 ppm) and MK and significantly lower ADC and MD in the non-adenocarcinoma, stage IB, LVSI-positive, high-grade, and non-low-risk groups (all p < 0.05). The MK and MTRasym (3.5 ppm) were moderately positively correlated with risk stratification as assessed by the European Society for Medical Oncology (EMSO) clinical practice guidelines (r = 0.640 and 0.502, respectively), while ADC and MD were mildly negatively correlated with risk stratification (r = −0.358 and −0.438, respectively). MTRasym (3.5 ppm), MD, and MK were identified as independent risk predictors in stage I EC, and optimal predictive performance was obtained with their combinations (AUC = 0.906, sensitivity = 70.97%, specificity = 92.68%). The results of the validation model were consistent with the above results, and the calibration curve showed good accuracy and consistency.

Conclusions

Although similar performance was obtained with each individual parameter of APTWI, DWI, and DKI for the noninvasive assessment of aggressive behavior in stage I EC, the combination of MD, MK, and MTRasym (3.5 ppm) provided improved predictive power for non-low-risk stage I EC and may serve as a superior imaging marker.

Detection of deep myometrial invasion in endometrial cancer MR imaging based on multi-feature fusion and probabilistic support vector machine ensemble

The depth of myometrial invasion affects the treatment and prognosis of patients with endometrial cancer (EC), conventionally evaluated using MR imaging (MRI). However, only a few computer-aided diagnosis methods have been reported for identifying deep myometrial invasion (DMI) using MRI. Moreover, these existing methods exhibit relatively unsatisfactory sensitivity and specificity. This study proposes a novel computerized method to facilitate the accurate detection of DMI on MRI. This method requires only the corpus uteri region provided by humans or computers instead of the tumor region. We also propose a geometric feature called LS to describe the irregularity of the tissue structure inside the corpus uteri triggered by EC, which has not been leveraged for the DMI prediction model in other studies. Texture features are extracted and then automatically selected by recursive feature elimination. Utilizing a feature fusion strategy of strong and weak features devised in this study, multiple probabilistic support vector machines incorporate LS and texture features, which are then merged to form the ensemble model EPSVM. The model performance is evaluated via leave-one-out cross-validation. We make the following comparisons, EPSVM versus the commonly used classifiers such as random forest, logistic regression, and naive Bayes; EPSVM versus the models using LS or texture features alone. The results show that EPSVM attains an accuracy, sensitivity, specificity, and F1 score of 93.7%, 94.7%, 93.3%, and 87.8%, all of which are higher than those of the commonly used classifiers and the models using LS or texture features alone. Compared with the methods in existing studies, EPSVM exhibits high performance in terms of both sensitivity and specificity. Moreover, LS can achieve an accuracy, sensitivity, and specificity of 89.9%, 89.5%, and 90.0%. Thus, the devised geometric feature LS is significant for DMI detection. The fusion of LS and texture features in the proposed EPSVM can provide more reliable prediction. The computer-aided classification based on the proposed method can assist radiologists in accurately identifying DMI on MRI.