RESUMEN
No prospective study has validated molecular classification to guide adjuvant treatment in endometrial cancer (EC), and not even retrospective data are present for patients with morphological low-risk EC. We conducted a retrospective, multicenter, observational study including 370 patients with low-risk endometrioid EC to evaluate the incidence and prognostic role of p53 abnormal expression (p53abn) in this specific subgroup. Among 370 patients, 18 had abnormal expressions of p53 (4.9%). In 13 out of 370 patients (3.6%), recurrences were observed and two were p53abn. When adjusting for median follow-up time, the odds ratio (OR) for recurrence among those with p53abn versus p53 wild type (p53wt) was 5.23-CI 95% 0.98-27.95, p = 0.053. The most common site of recurrence was the vaginal cuff (46.2%). One recurrence occurred within the first year of follow-up, and the patient exhibited p53abn. Both 1-year and 2-year DFS rates were 94.4% and 100% in the p53abn and p53wt groups, respectively. One patient died from the disease and comprised p53wt. No difference in OS was registered between the two groups; the median OS was 21.9 months (16.4-30.1). Larger multicenter studies are needed to tailor the treatment of low-risk EC patients with p53abn. Performing molecular classification on all EC patients might be cost-effective, and despite the limits of our relatively small sample, p53abn patients seem to be at greater risk of recurrence, especially locally and after two years since diagnosis.
RESUMEN
Neoadjuvant chemotherapy plus radical surgery could be a safe alternative to chemo-radiation in cervical cancer patients who are not willing to receive radiotherapy. The response to neoadjuvant chemotherapy is the main factor influencing the need for adjunctive treatments and survival. In the present paper we aim to develop a machine learning model based on cervix magnetic resonance imaging (MRI) images to stratify the single-subject risk of cervical cancer. We collected MRI images from 72 subjects. Among these subjects, 28 patients (38.9%) belonged to the "Not completely responding" class and 44 patients (61.1%) belonged to the 'Completely responding' class according to their response to treatment. This image set was used for the training and cross-validation of different machine learning models. A robust radiomic approach was applied, under the hypothesis that the radiomic features could be able to capture the disease heterogeneity among the two groups. Three models consisting of three ensembles of machine learning classifiers (random forests, support vector machines, and k-nearest neighbor classifiers) were developed for the binary classification task of interest ("Not completely responding" vs. "Completely responding"), based on supervised learning, using response to treatment as the reference standard. The best model showed an ROC-AUC (%) of 83 (majority vote), 82.3 (mean) [79.9-84.6], an accuracy (%) of 74, 74.1 [72.1-76.1], a sensitivity (%) of 71, 73.8 [68.7-78.9], and a specificity (%) of 75, 74.2 [71-77.5]. In conclusion, our preliminary data support the adoption of a radiomic-based approach to predict the response to neoadjuvant chemotherapy.