Microsatellite instability as a marker of prognosis: a systematic review and meta-analysis of endometrioid endometrial cancer survival data

Single-cell profiling of low-stage endometrial cancers identifies low epithelial vimentin expression as a marker of recurrent disease

BACKGROUND

Identification of aggressive low-stage endometrial cancers is challenging. So far, studies have failed to pinpoint robust features or biomarkers associated with risk of recurrence for these patients.

METHODS

Imaging mass cytometry was used to examine single-cell expression of 23 proteins in 36 primary FIGO IB endometrial cancers, of which 17 recurred. Single-cell information was extracted for each tumor and unsupervised clustering was used to identify cellular phenotypes. Distinct phenotypes and cellular neighborhoods were compared in relation to recurrence. Cellular differences were validated in a separate gene expression dataset and the TCGA EC dataset. Vimentin protein expression was evaluated by IHC in pre-operative samples from 518 patients to validate its robustness as a prognostic marker.

FINDINGS

The abundance of epithelial, immune or stromal cell types did not associate with recurrence. Clustering of patients based on tumor single cell marker expression revealed distinct patient clusters associated with outcome. A cell population neighboring CD8+ T cells, defined by vimentin, ER, and PR expressing epithelial cells, was more prevalent in non-recurrent tumors. Importantly, lower epithelial vimentin expression and lower gene expression of VIM associated with worse recurrence-free survival. Loss and low expression of vimentin was validated by IHC as a robust marker for recurrence in FIGO I stage disease and predicted poor prognosis also when including all patients and in endometrioid patients only.

INTERPRETATION

This study reveals distinct characteristics in low-stage tumors and points to vimentin as a clinically relevant marker that may aid in identifying a here to unidentified subgroup of high-risk patients.

FUNDING

A full list of funding that contributed to this study can be found in the Acknowledgements section.

Multisequence magnetic resonance imaging-based radiomics models for the prediction of microsatellite instability in endometrial cancer

PURPOSE

To evaluate the performance of multisequence magnetic resonance imaging (MRI)-based radiomics models in the assessment of microsatellite instability (MSI) status in endometrial cancer (EC).

MATERIALS AND METHODS

This retrospective multicentre study included 338 EC patients with available MSI status and preoperative MRI scans, divided into training (37 MSI, 123 microsatellite stability [MSS]), internal validation (15 MSI, 52 MSS), and external validation cohorts (30 MSI, 81 MSS). Radiomics features were extracted from T2-weighted images, diffusion-weighted images, and contrast-enhanced T1-weighted images. The ComBat harmonisation method was applied to remove intrascanner variability. The Boruta wrapper algorithm was used for key feature selection. Three classification algorithms, logistic regression (LR), random forest (RF), and support vector machine (SVM), were applied to build the radiomics models. The area under the receiver operating characteristic curve (AUC) was calculated to compare the diagnostic performance of the models. Decision curve analysis (DCA) was conducted to determine the clinical usefulness of the models.

RESULTS

Among the 1980 features, Boruta finally selected nine radiomics features. A higher MSI prediction performance was achieved after running the ComBat harmonisation method. The SVM algorithm had the best performance, with AUCs of 0.921, 0.903, and 0.937 in the training, internal validation, and external validation cohorts, respectively. The DCA results showed that the SVM algorithm achieved higher net benefits than the other classifiers over a threshold range of 0.581-0.783.

CONCLUSION

The multisequence MRI-based radiomics models showed promise in preoperatively predicting the MSI status in EC in this multicentre setting.