Development and Validation of Multiparametric MRI-based Radiomics Models for Preoperative Risk Stratification of Endometrial Cancer.

Background Stratifying high-risk histopathologic features in endometrial carcinoma is important for treatment planning. Radiomics analysis at preoperative MRI holds potential to identify high-risk phenotypes. Purpose To evaluate the performance of multiparametric MRI three-dimensional radiomics-based machine learning models for differentiating low- from high-risk histopathologic markers-deep myometrial invasion (MI), lymphovascular space invasion (LVSI), and high-grade status-and advanced-stage endometrial carcinoma. Materials and Methods This dual-center retrospective study included women with histologically proven endometrial carcinoma who underwent 1.5-T MRI before hysterectomy between January 2011 and July 2015. Exclusion criteria were tumor diameter less than 1 cm, missing MRI sequences or histopathology reports, neoadjuvant therapy, and malignant neoplasms other than endometrial carcinoma. Three-dimensional radiomics features were extracted after tumor segmentation at MRI (T2-weighted, diffusion-weighted, and dynamic contrast-enhanced MRI). Predictive features were selected in the training set with use of random forest (RF) models for each end point, and trained RF models were applied to the external test set. Five board-certified radiologists conducted MRI-based staging and deep MI assessment in the training set. Areas under the receiver operating characteristic curve (AUCs) were reported with balanced accuracies, and radiologists' readings were compared with radiomics with use of McNemar tests. Results In total, 157 women were included: 94 at the first institution (training set; mean age, 66 years ± 11 [SD]) and 63 at the second institution (test set; 67 years ± 12). RF models dichotomizing deep MI, LVSI, high grade, and International Federation of Gynecology and Obstetrics (FIGO) stage led to AUCs of 0.81 (95% CI: 0.68, 0.88), 0.80 (95% CI: 0.67, 0.93), 0.74 (95% CI: 0.61, 0.86), and 0.84 (95% CI: 0.72, 0.92), respectively, in the test set. In the training set, radiomics provided increased performance compared with radiologists' readings for identifying deep MI (balanced accuracy, 86% vs 79%; P = .03), while no evidence of a difference was observed in performance for advanced FIGO stage (80% vs 78%; P = .27). Conclusion Three-dimensional radiomics can stratify patients by using preoperative MRI according to high-risk histopathologic end points in endometrial carcinoma and provide nonsignificantly different or higher performance than radiologists in identifying advanced stage and deep myometrial invasion, respectively. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Kido and Nishio in this issue.

Clinical significance of isolated tumor cells and micrometastasis in low-grade, stage I endometrial cancer.

INTRODUCTION: Ultrastaging in endometrial cancer (EC) led to increased detection of isolated tumor cells (ITC, ≤0.2 mm) and micrometastases (MM, 0.2-2 mm), with unclear effect on prognosis. Our aim was to characterize the impact of ITC and MM on the outcome of these patients. METHODS: Grade 1 to 2 stage I endometrioid EC patients with nodal ITC (n = 11) or MM (n = 12) between 2012 and 2018 were retrospectively compared to a matched group of lymph node negative (n = 18) patients based on age, body mass index, grade, myometrial invasion, and lymphovascular space invasion (LVI) status using propensity score analysis (1:1). Mann-Whitney U tests were performed on continuous variables and χ2 tests on categorical variables. Progression-free survival (PFS) was the main endpoint. RESULTS: All MM and 81% of ITC had LVI. More ITC/MM patients received RT and chemotherapy (91.7% vs 18.4%; 70.8% vs 4.5%, respectively; P < 0.01) without significant difference in treatment-related toxicities (25% vs 27.3% grade 1%-2% and 20.8% vs 9.1% grade 2-3; P = 0.538) or PFS (29.2 vs 25 months; P = 0.828). Two distant recurrences occurred in MM patients after 2.5 years; one lung and one para-aortic lymph node. CONCLUSION: With adjuvant treatment, ITC/MM in otherwise well-differentiated stage I endometrial cancer have similar outcomes to matched LN- patients.

Impact of a Multidimensional Technical Skills Training Session Before Obstetrics and Gynaecology Clerkship Rotation on Performance and Exposure.

OBJECTIVE: This study sought to assess the impact of an obstetrics and gynaecology (OBGYN) multidimensional technical skills training session on medical student self-perceived confidence, objective performance, clinical exposure, and interest in OBGYN. METHODS: OBGYN clerkship students were divided into control (i.e., traditional curriculum) and intervention (i.e., additional pre-rotation simulation training in vaginal delivery, suturing and knot tying, speculum and bimanual examinations, and intrapartum cervical examination) groups. Both groups underwent an objective structured clinical examination (OSCE) after the rotation and completed pre- and post-rotation questionnaires to assess confidence, clinical exposure, and interest in OBGYN. The primary outcomes were self-reported confidence and OSCE scores, and the secondary outcomes were clinical exposure and interest in OBGYN. RESULTS: A total of 148 students participated. Both groups reported least confidence with vaginal delivery and cervical examinations before the rotation. There was improved self-confidence across all skills after the rotation, with the intervention group demonstrating greater improvement for vaginal delivery (3.36 vs. 3.10; P < 0.05) and cervical examination (3.14 vs. 2.86; P < 0.05). The intervention group also demonstrated a trend towards higher OSCE scores for all skills, but only speculum and bimanual examinations reached statistical significance. The intervention increased exposure from "0 to 5" to "6 to 10" for vaginal delivery and suturing. There was no difference in interest in OBGYN between the two groups. CONCLUSION: A technical skills training session before OBGYN clerkship is feasible and has the potential to increase students' confidence, OSCE performance, and hands-on procedural exposure. The optimal combination of skills to be included still needs to be defined.

Endometrial Carcinoma: MR Imaging-based Texture Model for Preoperative Risk Stratification-A Preliminary Analysis.

Purpose To evaluate the associations among mathematical modeling with the use of magnetic resonance (MR) imaging-based texture features and deep myometrial invasion (DMI), lymphovascular space invasion (LVSI), and histologic high-grade endometrial carcinoma. Materials and Methods Institutional review board approval was obtained for this retrospective study. This study included 137 women with endometrial carcinomas measuring greater than 1 cm in maximal diameter who underwent 1.5-T MR imaging before hysterectomy between January 2011 and December 2015. Texture analysis was performed with commercial research software with manual delineation of a region of interest around the tumor on MR images (T2-weighted, diffusion-weighted, and dynamic contrast material-enhanced images and apparent diffusion coefficient maps). Areas under the receiver operating characteristic curve and diagnostic performance of random forest models determined by using a subset of the most relevant texture features were estimated and compared with those of independent and blinded visual assessments by three subspecialty radiologists. Results A total of 180 texture features were extracted and ultimately limited to 11 features for DMI, 12 for LVSI, and 16 for high-grade tumor for random forest modeling. With random forest models, areas under the receiver operating characteristic curve, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were estimated at 0.84, 79.3%, 82.3%, 81.0%, 76.7%, and 84.4% for DMI; 0.80, 80.9%, 72.5%, 76.6%, 74.3%, and 79.4% for LVSI; and 0.83, 81.0%, 76.8%, 78.1%, 60.7%, and 90.1% for high-grade tumor, respectively. Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of visual assessment for DMI were 84.5%, 82.3%, 83.2%, 77.7%, and 87.8% (reader 3). Conclusion The mathematical models that incorporated MR imaging-based texture features were associated with the presence of DMI, LVSI, and high-grade tumor and achieved equivalent accuracy to that of subspecialty radiologists for assessment of DMI in endometrial cancers larger than 1 cm. However, these preliminary results must be interpreted with caution until they are validated with an independent data set, because the small sample size relative to the number of features extracted may have resulted in overfitting of the models. © RSNA, 2017 Online supplemental material is available for this article.

Outcome of robotic surgery for endometrial cancer as a function of patient age.

OBJECTIVE: This study aimed to evaluate and compare robot-assisted surgical staging on clinical outcomes, including quality of life and survival, as a function of patient age. METHODS: Evaluation and comparison of perioperative morbidity, survival, and postoperative quality of life after prospective accumulation of clinical information including outcome measures for patients with endometrial cancer during the first 5 years of a robotic program, based on the following 3 age categories: women older than 80 years, women between 70 and 80 years, and women younger than 70 years. RESULTS: All consecutive patients with endometrial cancer undergoing robotic surgery (n = 303) were included, with 197 women younger than 70 years, 75 women between 70 and 80 years, and 31 women older than 80 years. There were significantly more patients with advanced stage (stage II to IV in 17%, 34%, and 35%, P = 0.02) and grade 3 disease (26%, 43%, and 58%, P = 0.002) with increasing age. The perioperative data showed similar grade I or II complications (Clavien-Dindo classification) between the groups, but significantly more grade III and IV complications for women older than 80 years compared with women 80 years or younger (10% vs 1%, P = 0.004). The time needed to resume chore activities was significantly shorter for patients 70 years or older than patients younger than 70 years [8.9 (8.7) vs 18.8 (25.5) days, P = 0.048]. Overall, all patients irrespective of age were highly satisfied with the procedure. There was no difference between young and elderly patients for disease-free survival (P = 0.99). CONCLUSIONS: Patient's age did not influence minor postoperative morbidity or overall satisfaction after robotic assisted surgery for endometrial cancer. Elderly patients had more major postoperative morbidity but resumed activities quicker than younger patients.