Uterine cancer (also known as endometrial cancer) can seriously affect the female reproductive system, and histopathological image analysis is the gold standard for diagnosing endometrial cancer. Due to the limited ability to model the complicated relationships between histopathological images and their interpretations, existing computer-aided diagnosis (CADx) approaches using traditional machine learning algorithms often failed to achieve satisfying results. In this study, we develop a CADx approach based on a convolutional neural network (CNN) and attention mechanisms, called HIENet. In the ten-fold cross-validation on ~3,300 hematoxylin and eosin (H&E) image patches from ~500 endometrial specimens, HIENet achieved a 76.91 ± 1.17% (mean ± s. d.) accuracy for four classes of endometrial tissue, i.e., normal endometrium, endometrial polyp, endometrial hyperplasia, and endometrial adenocarcinoma. Also, HIENet obtained an area-under-the-curve (AUC) of 0.9579 ± 0.0103 with an 81.04 ± 3.87% sensitivity and 94.78 ± 0.87% specificity in a binary classification task that detected endometrioid adenocarcinoma. Besides, in the external validation on 200 H&E image patches from 50 randomly-selected female patients, HIENet achieved an 84.50% accuracy in the four-class classification task, as well as an AUC of 0.9829 with a 77.97% (95% confidence interval, CI, 65.27%~87.71%) sensitivity and 100% (95% CI, 97.42%~100.00%) specificity. The proposed CADx method outperformed three human experts and five CNN-based classifiers regarding overall classification performance. It was also able to provide pathologists better interpretability of diagnoses by highlighting the histopathological correlations of local pixel-level image features to morphological characteristics of endometrial tissue.

Optical coherence tomography (OCT) is a promising research tool for brain imaging and developmental biology. Serving as a three-dimensional optical biopsy technique, OCT provides volumetric reconstruction of brain tissues and embryonic structures with micrometer resolution and video rate imaging speed. Functional OCT enables label-free monitoring of hemodynamic and metabolic changes in the brain in vitro and in vivo in animal models. Due to its noninvasiveness nature, OCT enables longitudinal imaging of developing specimens in vivo without potential damage from surgical operation, tissue fixation and processing, and staining with exogenous contrast agents. In this paper, various OCT applications in brain imaging and developmental biology are reviewed, with a particular focus on imaging heart development. In addition, we report findings on the effects of a circadian gene (Clock) and high-fat diet on heart development in Drosophila melanogaster. These findings contribute to our understanding of the fundamental mechanisms connecting circadian genes and obesity to heart development and cardiac diseases.

The role of Artificial intelligence (AI) in pathology is one that offers many exciting new possibilities for improving patient care. This study contributes to this development by identifying the viability of AICyte Assistive System for cervical screening, and to investigate the utility of the system in assisting with workflow and diagnostic capability. In this study, a novel scanner was developed using a Ruiqian WSI-2400, trademarked AICyte Assistive system, to create AI-generated gallery of the most diagnostically relevant images, objects of interest (OOI), and provide categorical assessment, according to Bethesda category, for cervical ThinPrep Pap slides. For validation purposes, two pathologists reviewed OOIs from 32,451 cases of ThinPrep Paps independently, and their interpretations were correlated with the original ThinPrep interpretations (OTPI). The analysis was focused on the comparison of reporting rates, correlation between cytological results and histological follow-up findings, and the assessment of independent AICyte screening utility. Pathologists using the AICyte system had a mean reading time of 55.14 seconds for the first 3,000 cases trending down to 12.90 seconds in the last 6,000 cases. Overall average reading time was 22.23 seconds per case as compared to a manual reading time approximation of 180 seconds. Usage of AICyte compared to OTPI had similar sensitivity (97.89% vs 97.89%) and a statistically significant increase in specificity (16.19% vs 6.77%). When AICyte was run alone at a 50% negative cut-off value, it was able to read slides with a sensitivity of 99.30% and specificity of 9.87%. When AICyte was run independently at this cut-off value, no sole case of HSIL/SCC squamous lesion was missed. AICyte can provide a potential tool to help pathologists in both diagnostic capability and efficiency, which remained reliable as compared to baseline standard. Also unique for AICyte is the development of a negative cutoff value for which AICyte can categorize cases as "not needed for review" to triage cases and lower pathologist workload. This is the largest case number study that pathologists reviewed OOI with AI assistive system. The study demonstrates that AI assistive system can be broadly applied for cervical cancer screening.

Invasive micropapillary carcinoma (IMPC) is a rare subtype of breast cancer that lacks a prognostic prediction model. Its treatment and prognostic factors remain controversial. Our study aimed to develop nomograms to predict overall survival (OS) and cancer-specific survival (CSS) in IMPC patients. A total of 2149 patients confirmed to have IMPC between 2003 and 2018 were selected from the Surveillance, Epidemiology and End Results (SEER) database. They were divided into training and validation cohorts. Univariate and multivariate Cox regression analyses were used to identify significant independent prognostic factors. The nomograms were used to predict 3- and 5-year OS and CSS. The training and validation cohorts were used to verify the nomograms internally and externally. The predictive capability of the nomograms was evaluated by the consistency index (C-index), calibration curve, receiver operating characteristic (ROC) curve and decision curve analysis (DCA) curve. In the study, 2149 IMPC patients were randomized to a training group (n = 1611) and a validation group (n = 538). Age, T stage, N stage, ER, radiotherapy, and surgery were identified as independent prognostic factors for OS and CSS. These variables were selected to construct nomograms for IMPC. The C-index (0.768 for OS and 0.811 for CSS) and the time-dependent AUC (>0.7) indicated satisfactory discriminative ability of the nomograms. Additionally, DCA showed that the nomograms had higher clinical value than traditional TNM tumor staging. The models can accurately predict the prognosis of IMPC patients and can aid in providing individualized treatment for patients.

Purpose: The lung is the most common distant metastatic organ in patients with endometrial cancer (EC) but is rarely reported. This study examines the association between clinical characteristics and overall survival (OS) in EC with lung metastasis.Methods: Patients with EC who had accompanying lung metastasis were selected from the Surveillance, Epidemiology, and End Results (SEER) database between 2010 and 2017. Univariate and multivariate Cox regression were used to estimate hazard ratios (HRs) and 95% confidence intervals (95% CIs) and assess OS outcomes related to EC with lung metastasis. A Cox proportional hazards nomogram model for OS was constructed and validated. The calibration plot, receiver operating characteristic (ROC) curve and decision curve analysis (DCA) were used to evaluate the discriminative ability and clinical benefit of the novel nomogram. Kaplan–Meier curves and scatter diagram analysis were used to investigate the risk stratifications of the nomogram.Results: Overall, 1542 EC patients with lung metastasis between 2010 and 2017 were included and randomly divided into training and validation cohorts. A nomogram model was constructed using the clinical characteristics of tumor grade, histological type, surgery, adjuvant chemotherapy, adjuvant radiation, brain metastasis and liver metastasis. The concordance indexes (C-indexes) were 0.750 (95% CI, 0.732-0.767) and 0.743 (95% CI, 0.719-0.767) for the training cohort and validation cohort, respectively. Calibration plots and DCA showed good clinical applicability of the nomogram. The areas under the curves (AUCs) were 0.803 and 0.766 for 1-year and 3-year OS, respectively, indicating that the nomogram model had a stable discriminative ability. An online calculator of our nomogram is available on the internet at https://endometrialcancer.shinyapps.io/DynNomapp/. Additionally, patients in the high-risk group had a significantly worse OS than those in the low-risk group.Conclusion: An easy-to-use, highly accurate nomogram was developed for predicting the prognosis of EC patients with lung metastasis.

Objective: This study aimed to analyze the association between the Dietary Inflammatory Index (DII) and the risk of gynecological cancers using data collected from the National Health and Nutrition Examination Survey (NHANES) between 2011 and 2018.Methods: The data for this study were obtained from NHANES, conducted between 2011 and 2018, and included a total of 8,380 women. To examine the association between the Dietary Inflammatory Index and gynecological cancers, weighted multivariable logistic regression analyses were performed, using DII both as a continuous variable and as a categorical variable divided into tertiles. Subgroup analyses stratified by DII and gynecological cancer characteristics were conducted to further explore this association. Additionally, restricted cubic spline (RCS) analysis was applied to evaluate potential non-linear relationships between DII and gynecological cancer risk.Results: Among the 8,380 women included in the analysis, the mean age was 47.02 (SD: 16.91) years, and 196 participants self-reported a diagnosis of gynecological cancer. In fully adjusted models, DII was significantly positively associated with the prevalence of gynecological cancer, whether analyzed as a continuous variable (OR = 1.15, 95% CI: 1.00–1.33, p = 0.046) or as a categorical variable (highest tertile compared to the lowest tertile: OR = 2.14, 95% CI: 1.14–4.04, p = 0.021, p for trend = 0.021). Restricted cubic spline analysis confirmed a linear relationship between DII and gynecological cancer risk (p for non-linear association = 0.1984). Subgroup analyses revealed a significant interaction effect with smoking status (p for interaction = 0.037).Conclusion: Our findings suggest that higher DII scores are positively associated with an increased risk of gynecological cancer. These results contribute to the existing literature and underscore the need for further validation through larger prospective cohort studies.