Stratification of endometrioid endometrial cancer patients into risk levels using somatic mutations

Co-reactivity pattern of glucose metabolism and blood perfusion revealing DNA mismatch repair deficiency based on PET/DCE-MRI in endometrial cancer

BACKGROUND

Identifying DNA mismatch repair deficiency (MMRd) is important for prognosis risk stratification in patients with early-stage endometrial cancer (EC), but there is a notable absence of cost-effective and non-invasive preoperative assessment techniques. The study explored the co-reactivity pattern of glucose metabolism and blood perfusion in EC based on hybrid [18F]fluorodeoxyglucose ([18F]FDG) PET/dynamic contrast enhanced (DCE)-MRI to provide an imaging biomarker for identifying MMRd.

METHODS

Patients with a history of postmenopausal bleeding and initially diagnosed with EC on ultrasound were recruited to perform a PET/DCE-MRI scan. Glucose metabolism parameters were calculated on PET, and blood perfusion parameters were calculated semi-automatically by the DCE-Tofts pharmacokinetic model. The MMRd of early-stage EC was evaluated by immunohistochemistry. The synchronous variation of PET and DCE-MRI parameters was compared between the MMRd and mismatch repair proficiency (MMRp). The association between PET/DCE-MRI and MMRd was analyzed by logistic regression to establish the digital biomarker for predicting MMRd. Receiver operating characteristic curve, decision curve analysis, and the net reclassification index (NRI) were used to evaluate the value of the digital biomarker in identifying MMRd.

RESULTS

Eighty-six early-stage EC cases (58.92 ± 10.13 years old, 34 MMRd) were enrolled. The max/mean standardized uptake value (SUVmax/SUVmean), metabolic tumor volume, total lesion glycolysis, transfer constant (Ktrans), and efflux rate (Kep) were higher in MMRd than those in MMRp (P < 0.001, < 0.001, 0.002, 0.004, < 0.001, and 0.005, respectively). The correlations between glucose metabolism and blood perfusion were different between the MMRd and MMRp subgroups. SUVmax was correlated with Kep (r = 0.36) in the MMRd. SUVmean (odds ratio [OR] = 1.32, P = 0.006) and Ktrans (OR = 1.90, P = 0.021) were independent risk factors for MMRd. And the digital biomarker that combined SUVmean and Ktrans outperformed in identifying MMRd in early-stage EC more than DCE-MRI (AUC: 0.83 vs. 0.78, NRI = 13%).

CONCLUSION

A potential digital biomarker based on [18F]FDG PET/DCE-MRI can identify MMRd for prognosis risk stratification in early-stage EC.

Integration of Genomic and Clinical Retrospective Data to Predict Endometrioid Endometrial Cancer Recurrence

Endometrial cancer (EC) incidence and mortality continues to rise. Molecular profiling of EC promises improvement of risk assessment and treatment selection. However, we still lack robust and accurate models to predict those at risk of failing treatment. The objective of this pilot study is to create models with clinical and genomic data that will discriminate patients with EC at risk of disease recurrence. We performed a pilot, retrospective, case−control study evaluating patients with EC, endometrioid type: 7 with recurrence of disease (cases), and 55 without (controls). RNA was extracted from frozen specimens and sequenced (RNAseq). Genomic features from RNAseq included transcriptome expression, genomic, and structural variation. Feature selection for variable reduction was performed with univariate ANOVA with cross-validation. Selected variables, informative for EC recurrence, were introduced in multivariate lasso regression models. Validation of models was performed in machine-learning platforms (ML) and independent datasets (TCGA). The best performing prediction models (out of >170) contained the same lncRNA features (AUC of 0.9, and 95% CI: 0.75, 1.0). Models were validated with excellent performance in ML platforms and good performance in an independent dataset. Prediction models of EC recurrence containing lncRNA features have better performance than models with clinical data alone.

Creation and validation of models to predict response to primary treatment in serous ovarian cancer

Nearly a third of patients with high-grade serous ovarian cancer (HGSC) do not respond to initial therapy and have an overall poor prognosis. However, there are no validated tools that accurately predict which patients will not respond. Our objective is to create and validate accurate models of prediction for treatment response in HGSC. This is a retrospective case–control study that integrates comprehensive clinical and genomic data from 88 patients with HGSC from a single institution. Responders were those patients with a progression-free survival of at least 6 months after treatment. Only patients with complete clinical information and frozen specimen at surgery were included. Gene, miRNA, exon, and long non-coding RNA (lncRNA) expression, gene copy number, genomic variation, and fusion-gene determination were extracted from RNA-sequencing data. DNA methylation analysis was performed. Initial selection of informative variables was performed with univariate ANOVA with cross-validation. Significant variables (p < 0.05) were included in multivariate lasso regression prediction models. Initial models included only one variable. Variables were then combined to create complex models. Model performance was measured with area under the curve (AUC). Validation of all models was performed using TCGA HGSC database. By integrating clinical and genomic variables, we achieved prediction performances of over 95% in AUC. Most performances in the validation set did not differ from the training set. Models with DNA methylation or lncRNA underperformed in the validation set. Integrating comprehensive clinical and genomic data from patients with HGSC results in accurate and robust prediction models of treatment response.

An integrated prediction model of recurrence in endometrial endometrioid cancers

Objectives: Endometrial cancer incidence and mortality are rising in the US. Disease recurrence has been shown to have a significant impact on mortality. However, to date, there are no accurate and validated prediction models that would discriminate which individual patients are likely to recur. Reliably predicting recurrence would be of benefit for treatment decisions following surgery. We present an integrated model constructed with comprehensive clinical, pathological and molecular features designed to discriminate risk of recurrence for patients with endometrioid endometrial adenocarcinoma. Subjects and methods: A cohort of endometrioid endometrial cancer patients treated at our institution was assembled. Clinical characteristics were extracted from patient charts. Primary tumors from these patients were obtained and total tissue RNA extracted for RNA sequencing. A prediction model was designed containing both clinical characteristics and molecular profiling of the tumors. The same analysis was carried out with data derived from The Cancer Genome Atlas for replication and external validation. Results: Prediction models derived from our institutional data predicted recurrence with high accuracy as evidenced by areas under the curve approaching 1. Similar trends were observed in the analysis of TCGA data. Further, a scoring system for risk of recurrence was devised that showed specificities as high as 81% and negative predictive value as high as 90%. Lastly, we identify specific molecular characteristics of patient tumors that may contribute to the process of disease recurrence. Conclusion: By constructing a comprehensive model, we are able to reliably predict recurrence in endometrioid endometrial cancer. We devised a clinically useful scoring system and thresholds to discriminate risk of recurrence. Finally, the data presented here open a window to understanding the mechanisms of recurrence in endometrial cancer.

A Prediction Model for Preoperative Risk Assessment in Endometrial Cancer Utilizing Clinical and Molecular Variables

The utility of comprehensive surgical staging in patients with low risk disease has been questioned. Thus, a reliable means of determining risk would be quite useful. The aim of our study was to create the best performing prediction model to classify endometrioid endometrial cancer (EEC) patients into low or high risk using a combination of molecular and clinical-pathological variables. We then validated these models with publicly available datasets. Analyses between low and high risk EEC were performed using clinical and pathological data, gene and miRNA expression data, gene copy number variation and somatic mutation data. Variables were selected to be included in the prediction model of risk using cross-validation analysis; prediction models were then constructed using these variables. Model performance was assessed by area under the curve (AUC). Prediction models were validated using appropriate datasets in The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases. A prediction model with only clinical variables performed at 88%. Integrating clinical and molecular data improved prediction performance up to 97%. The best prediction models included clinical, miRNA expression and/or somatic mutation data, and stratified pre-operative risk in EEC patients. Integrating molecular and clinical data improved the performance of prediction models to over 95%, resulting in potentially useful clinical tests.