Motivation While deep-learning algorithms have demonstrated outstanding performance in semantic image segmentation tasks, large annotation datasets are needed to create accurate models. Annotation of histology images is challenging due to the effort and experience required to carefully delineate tissue structures, and difficulties related to sharing and markup of whole-slide images. Results We recruited 25 participants, ranging in experience from senior pathologists to medical students, to delineate tissue regions in 151 breast cancer slides using the Digital Slide Archive. Inter-participant discordance was systematically evaluated, revealing low discordance for tumor and stroma, and higher discordance for more subjectively defined or rare tissue classes. Feedback provided by senior participants enabled the generation and curation of 20 000+ annotated tissue regions. Fully convolutional networks trained using these annotations were highly accurate (mean AUC=0.945), and the scale of annotation data provided notable improvements in image classification accuracy. Availability and Implementation Dataset is freely available at: https://goo.gl/cNM4EL. Supplementary information Supplementary data are available at Bioinformatics online.

Summary Background 80% of individuals with cancer will require a surgical procedure, yet little comparative data exist on early outcomes in low-income and middle-income countries (LMICs). We compared postoperative outcomes in breast, colorectal, and gastric cancer surgery in hospitals worldwide, focusing on the effect of disease stage and complications on postoperative mortality. Methods This was a multicentre, international prospective cohort study of consecutive adult patients undergoing surgery for primary breast, colorectal, or gastric cancer requiring a skin incision done under general or neuraxial anaesthesia. The primary outcome was death or major complication within 30 days of surgery. Multilevel logistic regression determined relationships within three-level nested models of patients within hospitals and countries. Hospital-level infrastructure effects were explored with three-way mediation analyses. This study was registered with ClinicalTrials.gov , NCT03471494 . Findings Between April 1, 2018, and Jan 31, 2019, we enrolled 15 958 patients from 428 hospitals in 82 countries (high income 9106 patients, 31 countries; upper-middle income 2721 patients, 23 countries; or lower-middle income 4131 patients, 28 countries). Patients in LMICs presented with more advanced disease compared with patients in high-income countries. 30-day mortality was higher for gastric cancer in low-income or lower-middle-income countries (adjusted odds ratio 3·72, 95% CI 1·70–8·16) and for colorectal cancer in low-income or lower-middle-income countries (4·59, 2·39–8·80) and upper-middle-income countries (2·06, 1·11–3·83). No difference in 30-day mortality was seen in breast cancer. The proportion of patients who died after a major complication was greatest in low-income or lower-middle-income countries (6·15, 3·26–11·59) and upper-middle-income countries (3·89, 2·08–7·29). Postoperative death after complications was partly explained by patient factors (60%) and partly by hospital or country (40%). The absence of consistently available postoperative care facilities was associated with seven to 10 more deaths per 100 major complications in LMICs. Cancer stage alone explained little of the early variation in mortality or postoperative complications. Interpretation Higher levels of mortality after cancer surgery in LMICs was not fully explained by later presentation of disease. The capacity to rescue patients from surgical complications is a tangible opportunity for meaningful intervention. Early death after cancer surgery might be reduced by policies focusing on strengthening perioperative care systems to detect and intervene in common complications. Funding National Institute for Health Research Global Health Research Unit.

No abstract

Background Deep learning enables accurate high-resolution mapping of cells and tissue structures that can serve as the foundation of interpretable machine-learning models for computational pathology. However, generating adequate labels for these structures is a critical barrier, given the time and effort required from pathologists. Results This article describes a novel collaborative framework for engaging crowds of medical students and pathologists to produce quality labels for cell nuclei. We used this approach to produce the NuCLS dataset, containing >220,000 annotations of cell nuclei in breast cancers. This builds on prior work labeling tissue regions to produce an integrated tissue region- and cell-level annotation dataset for training that is the largest such resource for multi-scale analysis of breast cancer histology. This article presents data and analysis results for single and multi-rater annotations from both non-experts and pathologists. We present a novel workflow that uses algorithmic suggestions to collect accurate segmentation data without the need for laborious manual tracing of nuclei. Our results indicate that even noisy algorithmic suggestions do not adversely affect pathologist accuracy and can help non-experts improve annotation quality. We also present a new approach for inferring truth from multiple raters and show that non-experts can produce accurate annotations for visually distinctive classes. Conclusions This study is the most extensive systematic exploration of the large-scale use of wisdom-of-the-crowd approaches to generate data for computational pathology applications.

No abstract

The current study was designed to investigate the protective role of diosmin against cyclophosphamide-induced premature ovarian insufficiency (POI). Female Swiss albino rats received a single intraperitoneal dose of cyclophosphamide (200 mg/kg) followed by 8 mg/kg/day for the next 15 consecutive days either alone or in combination with oral diosmin at 50 or 100 mg/kg. Histopathological examination of ovarian tissues, hormonal assays for follicle stimulating hormone (FSH), estradiol (E2), and anti-Mullerian hormone (AMH), assessment of the oxidative stress status, as well as measurement of the relative expression of miRNA-145 and its target genes [vascular endothelial growth factor B (VEGF-B) and regulator of cell cycle (RGC32)] were performed. Diosmin treatment ameliorated the levels of E2, AMH, and oxidative stress markers. Additionally, both low and high diosmin doses significantly reduced the histopathological alterations and nearly preserved the normal ovarian reserve. MiRNA-145 expression was upregulated after treatment with diosmin high dose. miRNA-145 target genes were over-expressed after both low and high diosmin administration. Based on our findings, diosmin has a dose-dependent protective effect against cyclophosphamide-induced ovarian toxicity in rats.

No abstract

Background The current fact of increasing rates of cesarean deliveries is a catastrophe. Recurrent cesareans result in intraperitoneal adhesions that would lead to maternal morbidity during delivery. Great efforts are directed towards the prediction of intraperitoneal adhesions to provide the best care for laboring women. The aim of the current study was to evaluate the role of abdominal striae and cesarean scar characters in the prediction of intraperitoneal adhesions. Methods This was a case- control study conducted in the emergency ward of the obstetrics and gynecology department of a tertiary hospital from June to December 2019. The study was carried on patients admitted to the ward fulfilling particular inclusion and exclusion criteria. The study included two groups, group one was assessed for the presence of striae, and the degree of intraperitoneal adhesions was evaluated during the current cesarean section. Group two included patients without evidence of abdominal striae. They were evaluated for the severity of adhesions also after evaluation of the previous scar. Evaluation of the striae was done using Davey’s scoring system. The scar was assessed using the Vancouver Scar Scale. The modified Nair’s scoring system was used to evaluate intraperitoneal adhesions. Results The study group included 203 women, while the control group included 205 women. There were significant differences in the demographic characters of the recruited patients (p-value 0.001 for almost all variables). The mean Davey score in those with mild, moderate, and severe striae was 1.82 ± 0.39, 3.57 ± 0.5, and 6.73 ± 0.94, respectively (p-value < 0.001). Higher scores for the parameters of the Vancouver scale were present in patients with severe striae (1.69 ± 1.01, 1.73 ± 0.57, 2.67 ± 1.23, and 1.35 ± 1.06 for scar vascularity, pigmentation, pliability, and height respectively with a p-value of < 0.001 each). Thick intraperitoneal adhesions were noted significantly in women with severe striae [21 (43.75%), p-value < 0.001)]. The Davey’s and Vancouver scores showed highly significant predictive performance in the prediction of intraperitoneal adhesions (p-value < 0.001). Conclusion Abdominal striae and cesarean scar were significant predictors for intraperitoneal adhesions.