Whole-tumor texture model based on diffusion kurtosis imaging for assessing cervical cancer: a preliminary study

Whole-tumor histogram analysis of multiple non-Gaussian diffusion models at high b values for assessing cervical cancer

PURPOSE

To assess the diagnostic potential of whole-tumor histogram analysis of multiple non-Gaussian diffusion models for differentiating cervical cancer (CC) aggressive status regarding of pathological types, differentiation degree, stage, and p16 expression.

METHODS

Patients were enrolled in this prospective single-center study from March 2022 to July 2023. Diffusion-weighted images (DWI) were obtained including 15 b-values (0 ~ 4000 s/mm2). Diffusion parameters derived from four non-Gaussian diffusion models including continuous-time random-walk (CTRW), diffusion-kurtosis imaging (DKI), fractional order calculus (FROC), and intravoxel incoherent motion (IVIM) were calculated, and their histogram features were analyzed. To select the most significant features and establish predictive models, univariate analysis and multivariate logistic regression were performed. Finally, we evaluated the diagnostic performance of our models by using receiver operating characteristic (ROC) analyses.

RESULTS

89 women (mean age, 55 ± 11 years) with CC were enrolled in our study. The combined model, which incorporated the CTRW, DKI, FROC, and IVIM diffusion models, offered a significantly higher AUC than that from any individual models (0.836 vs. 0.664, 0.642, 0.651, 0.649, respectively; p < 0.05) in distinguishing cervical squamous cell cancer from cervical adenocarcinoma. To distinguish tumor differentiation degree, except the combined model showed a better predictive performance compared to the DKI model (AUC, 0.839 vs. 0.697, respectively; p < 0.05), no significant differences in AUCs were found among other individual models and combined model. To predict the International Federation of Gynecology and Obstetrics (FIGO) stage, only DKI and FROC model were established and there was no significant difference in predictive performance among different models. In terms of predicting p16 expression, the predictive ability of DKI model is significantly lower than that of FROC and combined model (AUC, 0.693 vs. 0.850, 0.859, respectively; p < 0.05).

CONCLUSION

Multiple non-Gaussian diffusion models with whole-tumor histogram analysis show great promise to assess the aggressive status of CC.

Prediction of cervix cancer stage and grade from diffusion weighted imaging using EfficientNet

Purpose. This study aims to introduce an innovative noninvasive method that leverages a single image for both grading and staging prediction. The grade and the stage of cervix cancer (CC) are determined from diffusion-weighted imaging (DWI) in particular apparent diffusion coefficient (ADC) maps using deep convolutional neural networks (DCNN).Methods. datasets composed of 85 patients having annotated tumor stage (I, II, III, and IV), out of this, 66 were with grade (II and III) and the remaining patients with no reported grade were retrospectively collected. The study was IRB approved. For each patient, sagittal and axial slices containing the gross tumor volume (GTV) were extracted from ADC maps. These were computed using the mono exponential model from diffusion weighted images (b-values = 0, 100, 1000) that were acquired prior to radiotherapy treatment. Balanced training sets were created using the Synthetic Minority Oversampling Technique (SMOTE) and fed to the DCNN. EfficientNetB0 and EfficientNetB3 were transferred from the ImageNet application to binary and four-class classification tasks. Five-fold stratified cross validation was performed for the assessment of the networks. Multiple evaluation metrics were computed including the area under the receiver operating characteristic curve (AUC). Comparisons with Resnet50, Xception, and radiomic analysis were performed.Results. for grade prediction, EfficientNetB3 gave the best performance with AUC = 0.924. For stage prediction, EfficientNetB0 was the best with AUC = 0.931. The difference between both models was, however, small and not statistically significant EfficientNetB0-B3 outperformed ResNet50 (AUC = 0.71) and Xception (AUC = 0.89) in stage prediction, and demonstrated comparable results in grade classification, where AUCs of 0.89 and 0.90 were achieved by ResNet50 and Xception, respectively. DCNN outperformed radiomic analysis that gave AUC = 0.67 (grade) and AUC = 0.66 (stage).Conclusion.the prediction of CC grade and stage from ADC maps is feasible by adapting EfficientNet approaches to the medical context.

T1 mapping as a quantitative imaging biomarker for diagnosing cervical cancer: a comparison with diffusion kurtosis imaging

BACKGROUND

T1 mapping can potentially quantitatively assess the intrinsic properties of tumors. This study was conducted to explore the ability of T1 mapping in distinguishing cervical cancer type, grade, and stage and compare the diagnostic performance of T1 mapping with diffusion kurtosis imaging (DKI).

METHODS

One hundred fifty-seven patients with pathologically confirmed cervical cancer were enrolled in this prospectively study. T1 mapping and DKI were performed. The native T1, difference between native and postcontrast T1 (T1diff), mean kurtosis (MK), mean diffusivity (MD), and apparent diffusion coefficient (ADC) were calculated. Cervical squamous cell carcinoma (CSCC) and adenocarcinoma (CAC), low- and high-grade carcinomas, and early- and advanced-stage groups were compared using area under the receiver operating characteristic (AUROC) curves.

RESULTS

The native T1 and MK were higher, and the MD and ADC were lower for CSCC than for CAC (all p < 0.05). Compared with low-grade CSCC, high-grade CSCC had decreased T1diff, MD, ADC, and increased MK (p < 0.05). Compared with low-grade CAC, high-grade CAC had decreased T1diff and increased MK (p < 0.05). Native T1 was significantly higher in the advanced-stage group than in the early-stage group (p < 0.05). The AUROC curves of native T1, MK, ADC and MD were 0,772, 0.731, 0.715, and 0.627, respectively, for distinguishing CSCC from CAC. The AUROC values were 0.762 between high- and low-grade CSCC and 0.835 between high- and low-grade CAC, with T1diff and MK showing the best discriminative values, respectively. For distinguishing between advanced-stage and early-stage cervical cancer, only the AUROC of native T1 was statistically significant (AUROC = 0.651, p = 0.002).

CONCLUSIONS

Compared with DKI-derived parameters, native T1 exhibits better efficacy for identifying cervical cancer subtype and stage, and T1diff exhibits comparable discriminative value for cervical cancer grade.

Multimodal magnetic resonance imaging in the diagnosis of cervical cancer and its correlation with the differentiation process of cervical cancer

PURPOSE

This study seeks to evaluate the value of MRI (Magnetic resonance imaging) diffusion weighted images (DWI), diffusion kurtosis imaging (DKI) and intravoxel incoherent motion (IVIM) in the diagnosis of cervical carcinoma.

METHODS

Seventy-nine cases of cervical cancer (CC group) (39 cases of squamous carcinoma (SCC group) and 40 cases of adenocarcinoma (ACC group)) and 30 cases of healthy controls (HC group) were included in this study. All the subjects were informed of the purpose of this study. The study was approved by the Ethics Committee of Beihua University Hospital, Jinlin, China. In this study, images were acquired based on a 3T MR scanner (Ingenia; Philips, Best, the Netherlands) and measured the imaging parameters by DWI, IVIM and DKI techniques. The parameters were obtained by Philips post-processing workstation, DKE and IVIM. These ROIs (region of interest) were manually drawn on each parameter mapping image by MRI physicians. Finally, SPSS 23.0 statistical software was used for data analysis.

RESULTS

The ADC (apparent diffusion coefficient) value of M group was lower than that of N group, and the difference was statistically significant (P < 0.05). The D (true diffusion coefficient) value, D*(pseudo diffusion coefficient) value, f (perfusion fraction) value, MD (mean diffusivity) value, and ADC value in the SCC group were lower than those in the ACC group with statistically significant differences (P < 0.05). The MK (mean kurtosis) value was higher than that of the ACC group, and the difference was statistically significant (P < 0.05). Compared with the HC group, the ADC values, D values, MD values of group CC group were lower, and the D* values, f values, MK values were higher; all the parameters were statistically significant (P < 0.05). The higher the differentiation degree of cervical cancer, the higher ADC values, D values, MD values, and the smaller D* values, f values, MK values. The difference of ADC values, D values and MK values was statistically significant (P < 0.05). MK value had the best diagnostic efficiency in the differential diagnosis of cervical cancer with low and medium differentiation, high and low differentiation (P < 0.05). There was no significant difference in the f value between high and low differentiation cervical cancer (P > 0.05). There was no significant difference in the MD value between low and high differentiation cervical cancer (P > 0.05). The strongest correlation between MK values (r = 0.796) and the degree of pathological differentiation of cervical cancer is positively correlated. The D values, MD values, and ADC values are negatively correlated with the degree of pathological differentiation of cervical cancer.

CONCLUSION

The ADC value of DWI parameters has important diagnostic value for different menstrual states of cervical cancer. The parameter values of DWI, IVIM, and DKI can be used to differentiate cervical cancer from normal cervical tissue, and thus have important diagnostic value for differentiating pathological types of cervical cancer. This means that these parameter values may have great significance in the differential diagnosis of cervical cancer with different degrees of pathological differentiation. The pathological differentiation degree of cervical cancer is significantly positively correlated with the MK value in the parameter values of DWI, IVIM, and DKI, while negatively correlated with the D value, MD value, and ADC value.

Evaluation of Whole-Tumor Texture Analysis Based on MRI Diffusion Kurtosis and Biparametric VI-RADS Model for Staging and Grading Bladder Cancer

BACKGROUND

to evaluate the feasibility of texture analysis (TA) based on diffusion kurtosis imaging (DKI) in staging and grading bladder cancer (BC) and to compare it with apparent diffusion coefficient (ADC) and biparametric vesical imaging reporting and data system (VI-RADS).

MATERIALS AND METHODS

In this retrospective study, 101 patients with pathologically confirmed BC underwent MRI with multiple-b values ranging from 0 to 2000 s/mm². ADC- and DKI-derived parameters, including mean kurtosis (MK) and mean diffusivity (MD), were obtained. First-order texture histogram parameters of MK and MD, including the mean; 5th, 25th, 50th, 75th, and 90th percentiles; inhomogeneity; skewness: kurtosis; and entropy; were extracted. The VI-RADS score was evaluated based on the T2WI and DWI. The Mann-Whitney U-test was used to compare the texture parameters and ADC values between non-muscle-invasive bladder cancer (NMIBC) and muscle-invasive bladder cancer (MIBC), as well as between low and high grades. Receiver operating characteristic analysis was used to evaluate the diagnostic performance of each significant parameter and their combinations.

RESULTS

The NMIBC and low-grade group had higher MDmean, MD5th, MD25th, MD50th, MD75th, MD90th, and ADC values than those of the MIBC and the high-grade group. The NMIBC and low-grade group yielded lower MKmean, MK25th, MK50th, MK75th, and MK90th than the MIBC and high-grade group. Among all histogram parameters, MD75th and MD90th yielded the highest AUC in differentiating MIBC from NMIBC (both AUCs were 0.87), while the AUC for ADC was 0.86. The MK75th and MK90th had the highest AUC (both 0.79) in differentiating low- from high-grade BC, while ADC had an AUC of 0.68. The AUC (0.92) of the combination of DKI histogram parameters (MD75th, MD90th, and MK90th) with biparametric VI-RADS in staging BC was higher than that of the biparametric VI-RADS (0.89).

CONCLUSIONS

Texture-analysis-derived DKI is useful in evaluating both the staging and grading of bladder cancer; in addition, the histogram parameters of the DKI (MD75th, MD90th, and MK90th) can provide additional value to VI-RADS.

T1 mapping and multimodel diffusion-weighted imaging in the assessment of cervical cancer: a preliminary study

OBJECTIVE

To evaluate the clinical feasibility of T1 mapping and multimodel diffusion-weighted imaging (DWI) for assessing the histological type, grade, and lymphovascular space invasion (LVSI) of cervical cancer.

METHODS

Eighty patients with cervical cancer and 43 patients with a normal cervix underwent T1 mapping and DWI with 11 b-values (0-2000 s/mm²). Monoexponential, biexponential, and kurtosis models were fitted to calculate the apparent diffusion coefficient (ADC), pure molecular diffusion (D), pseudo-diffusion (D*), perfusion fraction (f), mean diffusivity (MD), and mean kurtosis (MK). Native T1 and DWI-derived parameters (ADC_mean, ADC_min, D_mean, D_min, D*, f, MD_mean, MD_min, MK_mean, and MK_max) were compared based on histological type, grade, and LVSI status.

RESULTS

Native T1 and DWI-derived parameters differed significantly between cervical cancer and normal cervix (all p < 0.05), except D* (p = 0.637). Native T1 and MK_mean varied significantly between squamous cell carcinoma (SCC) and adenocarcinoma (both p < 0.05). ADC_min, D_min, and MD_min were significantly lower while MK_max was significantly higher in the high-grade SCC group than in the low-grade SCC group (all p < 0.05). LVSI-positive SCC had a significantly higher MK_mean than LVSI-negative SCC (p < 0.05).

CONCLUSION

Both T1 mapping and multimodel DWI can effectively differentiate cervical cancer from a normal cervix and cervical adenocarcinoma from SCC. Furthermore, multimodel DWI may provide quantitative metrics for non-invasively predicting histological grade and LVSI status in SCC patients.

ADVANCES IN KNOWLEDGE

Combined use of T1 mapping and multimodel DWI may provide more comprehensive information for non-invasive pre-operative evaluation of cervical cancer.

WHO/ISUP grade and pathological T stage of clear cell renal cell carcinoma: value of ZOOMit diffusion kurtosis imaging and chemical exchange saturation transfer imaging

OBJECTIVES

To evaluate the value of ZOOMit diffusion kurtosis imaging (DKI) and chemical exchange saturation transfer (CEST) imaging in predicting WHO/ISUP grade and pathological T stage in clear cell renal cell carcinoma (ccRCC).

METHODS

Forty-six patients with ccRCC were included in this retrospective study. All participants underwent MRI including ZOOMit DKI and CEST. The non-Gaussian mean kurtosis (MK), mean diffusivity (MD), magnetization transfer ratio asymmetry (MTRasym (3.5 ppm)), and S_sat (3.5 ppm)/S₀ were analyzed based on different WHO/ISUP grades and pT stages. Binary logistic regression was used to identify the best combination of the parameters. Pearson's correlation coefficients were calculated between CEST and diffusion-related parameters.

RESULTS

The ADC, MD, and S_sat (3.5 ppm)/S₀ values were significantly lower for higher WHO/ISUP grade tumors, whereas the MK and MTRasym (3.5 ppm) were higher in higher WHO/ISUP grade and higher pT stage tumors. MTRasym (3.5 ppm) combined with MD (AUC, 0.930; 95% CI, 0.858-1.000) showed the best diagnostic efficacy in evaluating the WHO/ISUP grade. MTRasym (3.5 ppm) and MK were mildly positively correlated (r = 0.324, p = 0.028). S_sat (3.5 ppm)/S₀ was moderately positively correlated with ADC (r = 0.580, p < 0.001), mildly positively correlated with MD (r = 0.412, p = 0.005), and moderately negatively correlated with MK (r = -0.575, p < .001).

CONCLUSION

The microstructural and biochemical assessment of ZOOMit DKI and CEST allowed for the characterization of different WHO/ISUP grades and pT stages in ccRCC. MTRasym (3.5 ppm) combined with MD showed the best diagnostic performance for WHO/ISUP grading.

KEY POINTS

• Both diffusion kurtosis imaging (DKI) and chemical exchange saturation transfer (CEST) can be used to predict the WHO/ISUP grade and pathological T stage. • MTRasym (3.5 ppm) combined with MD showed the highest AUC (0.930; 95% CI, 0.858-1.000) in WHO/ISUP grading. • MTRasym at 3.5 ppm showed a positive correlation with mean kurtosis.

The value of HPV genotypes combined with clinical indicators in the classification of cervical squamous cell carcinoma and adenocarcinoma

Background

To investigate the differences in HPV genotypes and clinical indicators between cervical squamous cell carcinoma and adenocarcinoma and to identify independent predictors for differentiating cervical squamous cell carcinoma and adenocarcinoma.

Methods

A total of 319 patients with cervical cancer, including 238 patients with squamous cell carcinoma and 81 patients with adenocarcinoma, were retrospectively analysed. The clinical characteristics and laboratory indicators, including HPV genotypes, SCCAg, CA125, CA19-9, CYFRA 21–1 and parity, were analysed by univariate and multivariate analyses, and a classification model for cervical squamous cell carcinoma and adenocarcinoma was established. The model was validated in 96 patients with cervical cancer.

Results

There were significant differences in SCCAg, CA125, CA19-9, CYFRA 21–1, HPV genotypes and clinical symptoms between cervical squamous cell carcinoma and adenocarcinoma (P < 0.05). Logistic regression analysis showed that SCCAg and HPV genotypes (high risk) were independent predictors for differentiating cervical squamous cell carcinoma from adenocarcinoma. The AUC value of the established classification model was 0.854 (95% CI: 0.804–0.904). The accuracy, sensitivity and specificity of the model were 0.846, 0.691 and 0.899, respectively. The classification accuracy was 0.823 when the model was verified.

Conclusion

The histological type of cervical cancer patients with persistent infection of high-risk HPV subtypes and low serum SCCAg levels was more prone to being adenocarcinoma. When the above independent predictors occur, the occurrence and development of cervical adenocarcinoma should be anticipated, and early active intervention treatment should be used to improve the prognosis and survival of patients.

Fully Automatic Whole-Volume Tumor Segmentation in Cervical Cancer

Simple Summary

Uterine cervical cancer (CC) is a leading cause of cancer-related deaths in women worldwide. Pelvic magnetic resonance imaging (MRI) allows the assessment of local tumor extent and guides the choice of primary treatment. MRI tumor segmentation enables whole-volume radiomic tumor profiling, which is potentially useful for prognostication and individualization of therapy in CC. Manual tumor segmentation is, however, labor intensive and thus not part of routine clinical workflow. In the current work, we trained a deep learning (DL) algorithm to automatically segment the primary tumor in CC patients. Although the achieved segmentation performance of the trained DL algorithm is slightly lower than that for human experts, it is still relatively good. This study suggests that automated MRI primary tumor segmentations by DL algorithms without any human interaction is possible in patients with CC.

Abstract

Uterine cervical cancer (CC) is the most common gynecologic malignancy worldwide. Whole-volume radiomic profiling from pelvic MRI may yield prognostic markers for tailoring treatment in CC. However, radiomic profiling relies on manual tumor segmentation which is unfeasible in the clinic. We present a fully automatic method for the 3D segmentation of primary CC lesions using state-of-the-art deep learning (DL) techniques. In 131 CC patients, the primary tumor was manually segmented on T2-weighted MRI by two radiologists (R1, R2). Patients were separated into a train/validation (n = 105) and a test- (n = 26) cohort. The segmentation performance of the DL algorithm compared with R1/R2 was assessed with Dice coefficients (DSCs) and Hausdorff distances (HDs) in the test cohort. The trained DL network retrieved whole-volume tumor segmentations yielding median DSCs of 0.60 and 0.58 for DL compared with R1 (DL-R1) and R2 (DL-R2), respectively, whereas DSC for R1-R2 was 0.78. Agreement for primary tumor volumes was excellent between raters (R1-R2: intraclass correlation coefficient (ICC) = 0.93), but lower for the DL algorithm and the raters (DL-R1: ICC = 0.43; DL-R2: ICC = 0.44). The developed DL algorithm enables the automated estimation of tumor size and primary CC tumor segmentation. However, segmentation agreement between raters is better than that between DL algorithm and raters.

Cervical Carcinoma: Evaluation Using Diffusion MRI With a Fractional Order Calculus Model and its Correlation With Histopathologic Findings

Objective

The objective of the study is to investigate the feasibility of using the fractional order calculus (FROC) model to reflect tumor subtypes and histological grades of cervical carcinoma.

Methods

Sixty patients with untreated cervical carcinoma underwent multi-b-value diffusion-weighted imaging (DWI) at 3.0T magnetic resonance imaging (MRI). The mono-exponential and the FROC models were fitted. The differences in the histological subtypes and grades were evaluated by the Mann–Whitney U test. Receiver operating characteristic (ROC) analyses were performed to assess the diagnostic performance and to determine the best predictor for both univariate analysis and multivariate analysis. Differences between ROC curves were tested using the Hanley and McNeil test, while the sensitivity, specificity, and accuracy were compared using the McNemar test. P-value <0.05 was considered as significant difference. The Bonferroni corrections were applied to reduce problems associated with multiple comparisons.

Results

Only the parameter β, derived from the FROC model could differentiate cervical carcinoma subtypes (P = 0.03) and the squamous cell carcinoma (SCC) lesions exhibited significantly lower β than that in the adenocarcinoma (ACA) lesions. All the individual parameters, namely, ADC, β, D, and μ derived from the FROC model, could differentiate low-grade cervical carcinomas from high-grade ones (P = 0.022, 0.009, 0.004, and 0.015, respectively). The combination of all the FROC parameters showed the best overall performance, providing the highest sensitivity (81.2%) and AUC (0.829).

Conclusion

The parameters derived from the FROC model were able to differentiate the subtypes and grades of cervical carcinoma.

Noninvasive assessment of clinical and pathological characteristics of patients with IgA nephropathy by diffusion kurtosis imaging

Objectives

To explore the diagnostic performance of diffusion kurtosis imaging (DKI) in evaluating the clinical and pathological characteristics of patients with immunoglobulin A nephropathy (IgAN) compared with conventional DWI.

Materials and methods

A total of 28 IgAN patients and 14 healthy volunteers prospectively underwent MRI examinations including coronal T2WI, axial T1WI, T2WI, and DWI sequences from September 2020 to August 2021. We measured mean kurtosis (MK), mean diffusivity (MD), and apparent diffusion coefficient (ADC) by using MR Body Diffusion Toolbox v1.4.0 (Siemens Healthcare). Patients were divided into three groups according to their estimated glomerular filtration rate (eGFR) (Group1, healthy volunteers without kidney disease or other diseases that affect renal function; Group2, IgAN patients with eGFR > 60 mL/min/1.73 m²; Group3, IgAN patients with eGFR < 60 mL/min/1.73 m²). One-way analysis of variance, Pearson or Spearman correlation, and receiver operating characteristic curves were applied in our statistical analysis.

Results

MK_Cortex and ADC_Cortex showed significant differences between the Group1 and Group2. MK_Cortex, MD_Cortex, ADC_Cortex, MK_Medulla, and ADC_Medulla showed significant differences between Group2 and Group3. MK_Cortex had the highest correlation with CKD stages (r = 0.749, p < 0.001), and tubulointerstitial lesion score (r = 0.656, p < 0.001). MD_Cortex had the highest correlation with glomerular lesion score (r = − 0.475, p = 0.011). MK_Cortex had the highest AUC (AUC = 0.923) for differentiating Group1 from Group2, and MD_Cortex had the highest AUC (AUC = 0.924) for differentiating Group2 from Group3, followed by MK_Medulla (AUC = 0.923).

Conclusions

DKI is a feasible and reliable technique that can assess the clinical and pathological characteristics of IgAN patients and can provide more valuable information than conventional DWI, especially MK_Cortex.