Multiparametric MRI-based radiomics analysis: differentiation of subtypes of cervical cancer in the early stage

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.

RESOLVE-based radiomics in cervical cancer: improved image quality means better feature reproducibility?

AIM

To compare the reproducibility of apparent diffusion coefficient (ADC)-based radiomic features between readout-segmented echo-planar diffusion-weighted imaging (RESOLVE) and single-shot echo-planar diffusion-weighted imaging (SS-EPI DWI) in cervical cancer.

MATERIALS AND METHODS

The RESOLVE and SS-EPI DWI images of 36 patients with histopathologically confirmed cervical cancer were collected retrospectively. Two observers independently delineated the whole tumour on RESOLVE and SS-EPI DWI, and then copied them to the corresponding ADC maps. Shape, first-order, and texture features were extracted from ADC maps in the original and filtered (Laplacian of Gaussian [LoG] and wavelet) images. Thereafter, 1,316 features were generated in each RESOLVE and SS-EPI DWI, respectively. The reproducibility of radiomic features was assessed using intraclass correlation coefficient (ICC).

RESULTS

In the original images, RESOLVE showed 92.86%, 66.67%, and 86.67% of features with excellent reproducibility in shape, first-order, and texture features, while SS-EPI DWI showed 85.71%, 72.22%, and 60% of features with excellent reproducibility, respectively. In the LoG and wavelet filtered images, RESOLVE had 56.77% and 65.32% of features with excellent reproducibility and SS-EPI DWI had 44.95% and 61.96% of features with excellent reproducibility, respectively.

CONCLUSION

Compared with SS-EPI DWI, the feature reproducibility of RESOLVE was better in cervical cancer, especially for texture features. The filtered images cannot improve the feature reproducibility compared with the original images for both SS-EPI DWI and RESOLVE.

Reduced field-of-view DWI‑derived clinical-radiomics model for the prediction of stage in cervical cancer

BACKGROUND

Pretreatment prediction of stage in patients with cervical cancer (CC) is vital for tailoring treatment strategy. This study aimed to explore the feasibility of a model combining reduced field-of-view (rFOV) diffusion-weighted imaging (DWI)-derived radiomics with clinical features in staging CC.

METHODS

Patients with pathologically proven CC were enrolled in this retrospective study. The rFOV DWI with b values of 0 and 800 s/mm² was acquired and the clinical characteristics of each patient were collected. Radiomics features were extracted from the apparent diffusion coefficient maps and key features were selected subsequently. A clinical-radiomics model combining radiomics with clinical features was constructed. The receiver operating characteristic curve was introduced to evaluate the predictive efficacy of the model, followed by comparisons with the MR-based subjective stage assessment (radiological model).

RESULTS

Ninety-four patients were analyzed and divided into training (n = 61) and testing (n = 33) cohorts. In the training cohort, the area under the curve (AUC) of clinical-radiomics model (AUC = 0.877) for staging CC was similar to that of radiomics model (AUC = 0.867), but significantly higher than that of clinical model (AUC = 0.673). In the testing cohort, the clinical-radiomics model yielded the highest predictive performance (AUC = 0.887) of staging CC, even without a statistically significant difference when compared with the clinical model (AUC = 0.793), radiomics model (AUC = 0.846), or radiological model (AUC = 0.823).

CONCLUSIONS

The rFOV DWI-derived clinical-radiomics model has the potential for staging CC, thereby facilitating clinical decision-making.

Self-supervised learning for multi-center magnetic resonance imaging harmonization without traveling phantoms

Objective. With the progress of artificial intelligence (AI) in magnetic resonance imaging (MRI), large-scale multi-center MRI datasets have a great influence on diagnosis accuracy and model performance. However, multi-center images are highly variable due to the variety of scanners or scanning parameters in use, which has a negative effect on the generality of AI-based diagnosis models. To address this problem, we propose a self-supervised harmonization (SSH) method. Approach. Mapping the style of images between centers allows harmonization without traveling phantoms to be formalized as an unpaired image-to-image translation problem between two domains. The mapping is a two-stage transform, consisting of a modified cycle generative adversarial network (cycleGAN) for style transfer and a histogram matching module for structure fidelity. The proposed algorithm is demonstrated using female pelvic MRI images from two 3 T systems and compared with three state-of-the-art methods and one conventional method. In the absence of traveling phantoms, we evaluate harmonization from three perspectives: image fidelity, ability to remove inter-center differences, and influence on the downstream model. Main results. The improved image sharpness and structure fidelity are observed using the proposed harmonization pipeline. It largely decreases the number of features with a significant difference between two systems (from 64 to 45, lower than dualGAN: 57, cycleGAN: 59, ComBat: 64, and CLAHE: 54). In the downstream cervical cancer classification, it yields an area under the receiver operating characteristic curve of 0.894 (higher than dualGAN: 0.828, cycleGAN: 0.812, ComBat: 0.685, and CLAHE: 0.770). Significance. Our SSH method yields superior generality of downstream cervical cancer classification models by significantly decreasing the difference in radiomics features, and it achieves greater image fidelity.

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.