Sparse feature selection for classification and prediction of metastasis in endometrial cancer.

BACKGROUND: Metastasis via pelvic and/or para-aortic lymph nodes is a major risk factor for endometrial cancer. Lymph-node resection ameliorates risk but is associated with significant co-morbidities. Incidence in patients with stage I disease is 4-22% but no mechanism exists to accurately predict it. Therefore, national guidelines for primary staging surgery include pelvic and para-aortic lymph node dissection for all patients whose tumor exceeds 2cm in diameter. We sought to identify a robust molecular signature that can accurately classify risk of lymph node metastasis in endometrial cancer patients. 86 tumors matched for age and race, and evenly distributed between lymph node-positive and lymph node-negative cases, were selected as a training cohort. Genomic micro-RNA expression was profiled for each sample to serve as the predictive feature matrix. An independent set of 28 tumor samples was collected and similarly characterized to serve as a test cohort. RESULTS: A feature selection algorithm was designed for applications where the number of samples is far smaller than the number of measured features per sample. A predictive miRNA expression signature was developed using this algorithm, which was then used to predict the metastatic status of the independent test cohort. A weighted classifier, using 18 micro-RNAs, achieved 100% accuracy on the training cohort. When applied to the testing cohort, the classifier correctly predicted 90% of node-positive cases, and 80% of node-negative cases (FDR = 6.25%). CONCLUSION: Results indicate that the evaluation of the quantitative sparse-feature classifier proposed here in clinical trials may lead to significant improvement in the prediction of lymphatic metastases in endometrial cancer patients.

Correlation of cone biopsy with findings at radical hysterectomy and use of adjuvant radiation therapy.

OBJECTIVE: To determine if pathologic findings in cone biopsy specimens correlate with residual invasive disease in radical hysterectomy specimens and the need for adjuvant chemo-radiation therapy. STUDY DESIGN: We identified 65 patients who underwent a cone biopsy and subsequent radical hysterectomy. Clinico-pathologic parameters in the cone specimens were correlated with the presence of residual invasive disease in the radical hysterectomy specimens and the need for adjuvant chemo-radiation. RESULTS: A positive endocervical margin, a positive deep margin, a positive post-cone ECC, and positive LVSI were significantly associated with the presence of residual disease in the radical hysterectomy specimen, while positive LVSI, a positive ECC, a positive deep cone margin, and greater than 1 positive margin were significantly associated with the use of adjuvant chemo-radiation therapy. CONCLUSION: Pathologic parameters in cone biopsy specimens can estimate the risk of residual invasive disease in radical hysterectomy specimens and the use of adjuvant chemo-radiation.

Should all patients with serous and clear cell endometrial carcinoma receive adjuvant chemotherapy?

Uterine papillary serous carcinoma (UPSC) and uterine clear cell carcinoma (UCCC) represent two rare subtypes that have an increased risk of recurrence and worse overall survival compared with the more common endometrioid endometrial cancers. Meaningful data in the form of prospective randomized trials is lacking for both advanced and early-stage UPSC and UCCC. Data extrapolated from prospective trials in advanced endometrioid endometrial cancer and retrospective trials on early-stage UPSC suggest that adjuvant platinum and taxane-based chemotherapy may provide a survival benefit for these patients. Future trials specifically examining UPSC and UCCC are needed to elucidate the optimal treatment regimen for these patients. Given the current data, the option of chemotherapy should be considered in treatment-planning discussions for all patients with UPSC and UCCC.