The aim of the present study was to explore the feasibility of using deep learning, such as artificial intelligence (AI), to classify cervical squamous epithelial lesions (SILs) from colposcopy images combined with human papilloma virus (HPV) types. Among 330 patients who underwent colposcopy and biopsy performed by gynecological oncologists, a total of 253 patients with confirmed HPV typing tests were enrolled in the present study. Of these patients, 210 were diagnosed with high-grade SIL (HSIL) and 43 were diagnosed with low-grade SIL (LSIL). An original AI classifier with a convolutional neural network catenating with an HPV tensor was developed and trained. The accuracy of the AI classifier and gynecological oncologists was 0.941 and 0.843, respectively. The AI classifier performed better compared with the oncologists, although not significantly. The sensitivity, specificity, positive predictive value, negative predictive value, Youden's J index and the area under the receiver-operating characteristic curve ± standard error for AI colposcopy combined with HPV types and pathological results were 0.956 (43/45), 0.833 (5/6), 0.977 (43/44), 0.714 (5/7), 0.789 and 0.963±0.026, respectively. Although further study is required, the clinical use of AI for the classification of HSIL/LSIL by both colposcopy and HPV type may be feasible.

Objectives We investigated the efficacy and safety of tacrolimus (TAC) by monitoring its serum concentration for mothers and infants in pregnant patients with systemic lupus erythematosus (SLE). Methods We measured trough concentrations of TAC in 25 pregnant patients with SLE to assess influence of TAC on the disease activity. Additionally, we measured the concentrations of TAC in umbilical arterial blood, breast milk, and breastfed infants to investigate the safety of TAC for the mothers and infants. Results The trough concentrations of TAC in the mothers significantly decreased in the second trimester as compared with those before pregnancy. However, the decrease in the trough concentrations of TAC did not lead to the deterioration of SLE. When examined, the doses of TAC were significantly lower in the second trimester and postpartum in the deteriorating group than those in the non-deteriorating group. There were no adverse events by TAC in mothers and fetuses. The concentrations of TAC in the umbilical cord blood were lower than those in the maternal blood. The relative infant dose in breastfed infants of TAC was < 1%. The level of TAC in infant bloods was below detectable limits. Conclusion These findings suggest that TAC is one of the most effective and safest immunosuppressive drugs for use in pregnant patients with SLE.

Intestinal obstruction in pregnancy is rare and is mainly caused by prior pelvic surgery. We herein report a case of intestinal obstruction in a pregnant female with a history of laparoscopic myomectomy, who presented with hypogastric pain, abdominal distension, and vomiting at 26 weeks of gestation. A simple intestinal obstruction was diagnosed by MRI. Conservative treatments, including intravenous hyperalimentation and the placement of an ileus tube, were provided and her abdominal symptoms improved for 14 days. After restarting oral intake, she had no abdominal symptoms. She gave birth to a 2,146 g female infant by caesarean section at 37 weeks and 1 day of gestation. Although an area of cicatrization, which was thought to have been the starting point of the occlusion that caused the intestinal obstruction, was found, the excision of the small intestine was not necessary. Her postoperative course was uneventful. Intestinal obstruction requires a prompt diagnosis and aggressive intervention may be necessary to minimize the morbidity and mortality associated with this rare complication of pregnancy. MRI can be safely used during pregnancy to diagnose intestinal obstruction and intravenous hyperalimentation may improve the maternal and fetal prognoses.

No abstract

Aim This study examined whether the intake of omega‐3 polyunsaturated fatty acids (PUFA) prevented post‐partum depression and if interleukin 6 (IL‐6) was involved in this effect. We hypothesized that omega‐3 supplementation has a protective effect against post‐partum depression. Methods We measured eicosapentaenoic acid (EPA), the arachidonic acid (AA)/EPA ratio, and IL‐6 in 80 singleton pregnant women during the first and second trimesters, and post‐partum. The women also completed a dietary questionnaire, and post‐partum depression was measured using the Edinburgh Postnatal Depression Scale (EPDS). We examined the correlations between the frequency of eating fish and EPA, the AA/EPA ratio and IL‐6 in the first and second trimesters, and post‐partum. We also investigated the correlation between the EPDS and the EPA, the AA/EPA ratio and IL‐6. Results The frequency of eating fish was significantly correlated with EPA in the second trimester and post‐partum and with the AA/EPA ratio in the second trimester. There was no correlation between IL‐6 levels and the frequency of eating fish. Post‐partum levels of EPA and the AA/EPA ratio were higher in the EPDS >7 group than in the EPDS ≤7 group. In the second trimester, a higher AA/EPA ratio was associated with EPDS >7. IL‐6 levels did not differ between the two groups. Conclusion In conclusion, a low dietary intake of omega‐3 PUFA during pregnancy was correlated with lower EPA levels, which tended to lead to post‐partum depression. The relationship between the IL‐6 level and the pathogenesis of post‐partum depression was unclear from the results of this study.