PURPOSE: This phase III, multicenter, randomized, open-label study investigated the efficacy and safety of nivolumab versus chemotherapy (gemcitabine [GEM] or pegylated liposomal doxorubicin [PLD]) in patients with platinum-resistant ovarian cancer. MATERIALS AND METHODS: Eligible patients had platinum-resistant epithelial ovarian cancer, received ≤ 1 regimen after diagnosis of resistance, and had an Eastern Cooperative Oncology Group performance score of ≤ 1. Patients were randomly assigned 1:1 to nivolumab (240 mg once every 2 weeks [as one cycle]) or chemotherapy (GEM 1000 mg/m² for 30 minutes [once on days 1, 8, and 15] followed by a week's rest [as one cycle], or PLD 50 mg/m² once every 4 weeks [as one cycle]). The primary outcome was overall survival (OS). Secondary outcomes included progression-free survival (PFS), overall response rate, duration of response, and safety. RESULTS: Patients (n = 316) were randomly assigned to nivolumab (n = 157) or GEM or PLD (n = 159) between October 2015 and December 2017. Median OS was 10.1 (95% CI, 8.3 to 14.1) and 12.1 (95% CI, 9.3 to 15.3) months with nivolumab and GEM or PLD, respectively (hazard ratio, 1.0; 95% CI, 0.8 to 1.3; P = .808). Median PFS was 2.0 (95% CI, 1.9 to 2.2) and 3.8 (95% CI, 3.6 to 4.2) months with nivolumab and GEM or PLD, respectively (hazard ratio, 1.5; 95% CI, 1.2 to 1.9; P = .002). There was no statistical difference in overall response rate between groups (7.6% v 13.2%; odds ratio, 0.6; 95% CI, 0.2 to 1.3; P = .191). Median duration of response was numerically longer with nivolumab than GEM or PLD (18.7 v 7.4 months). Fewer treatment-related adverse events were observed with nivolumab versus GEM or PLD (61.5% v 98.1%), with no additional or new safety risks. CONCLUSION: Although well-tolerated, nivolumab did not improve OS and showed worse PFS compared with GEM or PLD in patients with platinum-resistant ovarian cancer.

Yamagami W, et al. J Gynecol Oncol. 2016 Oct;28(2):e32. https://doi.org/10.3802/jgo.2017.28.e32

The Fourth Edition of the Guidelines for Treatment of Uterine Body Neoplasm was published in 2018. These guidelines include 9 chapters: 1. Overview of the guidelines, 2. Initial treatment for endometrial cancer, 3. Postoperative adjuvant therapy for endometrial cancer, 4. Post-treatment surveillance for endometrial cancer, 5. Treatment for advanced or recurrent endometrial cancer, 6. Fertility-sparing therapy, 7. Treatment of uterine carcinosarcoma and uterine sarcoma, 8. Treatment of trophoblastic disease, 9. Document collection; and nine algorithms: 1-3. Initial treatment of endometrial cancer, 4. Postoperative adjuvant treatment for endometrial cancer, 5. Treatment of recurrent endometrial cancer, 6. Fertility-sparing therapy, 7. Treatment for uterine carcinosarcoma, 8. Treatment for uterine sarcoma, 9. Treatment for choriocarcinoma. Each chapter includes overviews and clinical questions, and recommendations, objectives, explanation, and references are provided for each clinical question. This revision has no major changes compared to the 3rd edition, but does have some differences: 1) an explanation of the recommendation decision process and conflict of interest considerations have been added in the overview, 2) nurses, pharmacists and patients participated in creation of the guidelines, in addition to physicians, 3) the approach to evidence collection is listed at the end of the guidelines, and 4) for clinical questions that lack evidence or clinical validation, the opinion of the Guidelines Committee is given as a "Recommendations for tomorrow".

Image segmentation is the pixel-by-pixel detection of objects, which is the most challenging but informative in the fundamental tasks of machine learning including image classification and object detection. Pixel-by-pixel segmentation is required to apply machine learning to support fetal cardiac ultrasound screening; we have to detect cardiac substructures precisely which are small and change shapes dynamically with fetal heartbeats, such as the ventricular septum. This task is difficult for general segmentation methods such as DeepLab v3+, and U-net. Hence, here we proposed a novel segmentation method named Cropping-Segmentation-Calibration (CSC) that is specific to the ventricular septum in ultrasound videos in this study. CSC employs the time-series information of videos and specific section information to calibrate the output of U-net. The actual sections of the ventricular septum were annotated in 615 frames from 421 normal fetal cardiac ultrasound videos of 211 pregnant women who were screened. The dataset was assigned a ratio of 2:1, which corresponded to a ratio of the training to test data, and three-fold cross-validation was conducted. The segmentation results of DeepLab v3+, U-net, and CSC were evaluated using the values of the mean intersection over union (mIoU), which were 0.0224, 0.1519, and 0.5543, respectively. The results reveal the superior performance of CSC.

Yamagami W, et al. J Gynecol Oncol. 2017 Dec;29:e21. https://doi.org/10.3802/jgo.2018.29.e21