Purpose: We aimed to develop an ovarian cancer-specific predictive framework for clinical stage, histotype, residual tumor burden, and prognosis using machine learning methods based on multiple biomarkers.Experimental Design: Overall, 334 patients with epithelial ovarian cancer (EOC) and 101 patients with benign ovarian tumors were randomly assigned to "training" and "test" cohorts. Seven supervised machine learning classifiers, including Gradient Boosting Machine (GBM), Support Vector Machine, Random Forest (RF), Conditional RF (CRF), Na€ ve Bayes, Neural Network, and Elastic Net, were used to derive diagnostic and prognostic information from 32 parameters commonly available from pretreatment peripheral blood tests and age.Results: Machine learning techniques were superior to conventional regression-based analyses in predicting multiple clinical parameters pertaining to EOC. Ensemble meth-ods combining weak decision trees, such as GBM, RF, and CRF, showed the best performance in EOC prediction. The values for the highest accuracy and area under the ROC curve (AUC) for segregating EOC from benign ovarian tumors with RF were 92.4% and 0.968, respectively. The highest accuracy and AUC for predicting clinical stages with RF were 69.0% and 0.760, respectively. High-grade serous and mucinous histotypes of EOC could be preoperatively predicted with RF. An ordinal RF classifier could distinguish complete resection from others. Unsupervised clustering analysis identified subgroups among early-stage EOC patients with significantly worse survival.Conclusions: Machine learning systems can provide critical diagnostic and prognostic prediction for patients with EOC before initial intervention, and the use of predictive algorithms may facilitate personalized treatment options through pretreatment stratification of patients.NOTE: There were too few early-stage EOC patients with residual tumor. A definition for the significance of bold is P value of < 0.05.

RET (REarranged during Transfection), which encodes a receptor tyrosine kinase for members of the glial cell line-derived neurotrophic factor, plays a role as driver oncogene in a variety of human cancers. Fusion of RET with several partner genes has been detected in papillary thyroid, lung, colorectal, pancreatic and breast cancers, and tyrosine kinase inhibitors (TKIs) for RET (particularly RET-specific inhibitors) show promising therapeutic effects against such cancers. Oncogenic mutations within the extracellular cysteine-rich and intracellular kinase domains of RET drive medullary thyroid carcinogenesis; the same mutations are also observed in a small subset of diverse cancers such as lung, colorectal and breast cancers. Considering the oncogenic nature of RET mutants, lung, colorectal and breast cancers are predicted to respond to RET TKIs in a manner similar to medullary thyroid cancer. In summary, cancers carrying oncogenic RET alterations as a driver mutation could be collectively termed ‘REToma’ and treated with RET TKIs in a tissue-agnostic manner.

Polypoid endometriosis is a distinctive variant of endometriosis with histological features simulating those of endometrial polyps. Müllerianosis is characterized by the presence of lesions at any site containing admixtures of endosalpingiosis, endometriosis, and endocervicosis. Here, we report a rare case of polypoid endometriosis of the ovary with müllerianosis of the pelvic lymph nodes in a 44-year-old woman without a past history of pelvic surgery. Magnetic resonance imaging revealed an ovarian tumor containing papillary nodules up to 3.0 cm in diameter and left pelvic lymph node enlargement. Nodules in ovarian tumor showed heterogeneous high intensity on T2weighted image and high intensity on diffusion-weighted image and were mildly enhanced by gadolinium contrast material. Enlarged lymph node was markedly enhanced by gadolinium. We considered polypoid endometriosis in the differential diagnosis according to the results of the magnetic resonance imaging, and polypoid endometriosis was included in intraoperative consultation, however, ovarian carcinoma with lymph node metastasis could not be denied. According to histological examination, the final diagnosis was determined as polypoid endometriosis with glandular hyperplasia of the left ovary and müllerianosis in the obturator lymph nodes. To the best of our knowledge, this is the first report of polypoid endometriosis and müllerianosis of the pelvic lymph node.

Ovarian clear cell carcinoma (OCCC) is a subtype of epithelial ovarian cancer (EOC) that is associated with elevated interleukin-6 (IL-6) expression, resistance to chemotherapy, and increased mortality. Although bevacizumab (Bev) is a widely used anti-angiogenic agent for EOC, the efficacy of Bev and the role of IL-6 in modulating angiogenesis in OCCC are unknown. We performed tube formation assays using human umbilical vein endothelial cells (HUVEC) cultured in OCCC cell-conditioned medium and using cells directly co-cultured with OCCC cells. We observed that IL-6 inhibition significantly mitigated the ability of Bev to impede tube formation in both cases. Furthermore, IL-6 blockade disrupted the anti-angiogenic efficacy of Bev and its concomitant anti-tumor activity. In addition, IL-6 inhibition resulted in a significant increase in angiopoietin-1 (Ang1) secretion and decreased vascular endothelial growth factor (VEGF) expression. Clinical specimens also exhibited this reciprocal relationship between IL-6 and Ang1 expression. Finally, depletion of Ang1 abrogated the effects of IL-6 inhibition on Bev activity, demonstrating that IL-6 supports the anti-angiogenic activity of Bev by suppressing Ang1 expression and promoting dependence on VEGF for angiogenesis. Altogether, our data suggest that OCCC tumors with high IL-6 levels are candidates for Bev therapy.

No abstract