Development and validation of an interpretable model integrating multimodal information for improving ovarian cancer diagnosis.

Ovarian cancer, a group of heterogeneous diseases, presents with extensive characteristics with the highest mortality among gynecological malignancies. Accurate and early diagnosis of ovarian cancer is of great significance. Here, we present OvcaFinder, an interpretable model constructed from ultrasound images-based deep learning (DL) predictions, Ovarian-Adnexal Reporting and Data System scores from radiologists, and routine clinical variables. OvcaFinder outperforms the clinical model and the DL model with area under the curves (AUCs) of 0.978, and 0.947 in the internal and external test datasets, respectively. OvcaFinder assistance led to improved AUCs of radiologists and inter-reader agreement. The average AUCs were improved from 0.927 to 0.977 and from 0.904 to 0.941, and the false positive rates were decreased by 13.4% and 8.3% in the internal and external test datasets, respectively. This highlights the potential of OvcaFinder to improve the diagnostic accuracy, and consistency of radiologists in identifying ovarian cancer.

Tris(1,3-dichloro-2-propyl) Phosphate Inhibits Early Embryonic Development by Binding to Gsk-3ß Protein in Zebrafish.

Recently, several studies have reported that exposure to tris(1,3-dichloro-2-propyl) phosphate (TDCIPP) results in abnormal development of zebrafish embryos in blastocyst and gastrula stages, but molecular mechanisms are still not clear. This lacking strongly affects the interspecific extrapolation of embryonic toxicity induced by TDCIPP and hazard evaluation. In this study, zebrafish embryos were exposed to 100, 500 or 1000 µg/L TDCIPP, and 6-bromoindirubin-3'-oxime (BIO, 35.62 µg/L) was used as a positive control. Results demonstrated that treatment with TDCIPP or BIO caused an abnormal stacking of blastomere cells in mid blastula transition (MBT) stage, and subsequently resulted in epiboly delay of zebrafish embryos. TDCIPP and BIO up-regulated the expression of ß-catenin protein and increased its accumulation in nuclei of embryonic cells. This accumulation was considered as a driver for early embryonic developmental toxicity of TDCIPP. Furthermore, TDCIPP and BIO partly shared the same modes of action, and both of them could bind to Gsk-3ß protein, and then decreased the phosphorylation level of Gsk-3ß in TYR·216 site and lastly inhibited the activity of Gsk-3ß kinase, which was responsible for the increased concentrations of ß-catenin protein in embryonic cells and accumulation in nuclei. Our findings provide new mechanisms for clarifying the early embryonic developmental toxicity of TDCIPP in zebrafish.

Rethinking Annotation Granularity for Overcoming Shortcuts in Deep Learning-based Radiograph Diagnosis: A Multicenter Study.

Purpose: To evaluate the ability of fine-grained annotations to overcome shortcut learning in deep learning (DL)-based diagnosis using chest radiographs. Materials and Methods: Two DL models were developed using radiograph-level annotations (disease present: yes or no) and fine-grained lesion-level annotations (lesion bounding boxes), respectively named CheXNet and CheXDet. A total of 34 501 chest radiographs obtained from January 2005 to September 2019 were retrospectively collected and annotated regarding cardiomegaly, pleural effusion, mass, nodule, pneumonia, pneumothorax, tuberculosis, fracture, and aortic calcification. The internal classification performance and lesion localization performance of the models were compared on a testing set (n = 2922); external classification performance was compared on National Institutes of Health (NIH) Google (n = 4376) and PadChest (n = 24 536) datasets; and external lesion localization performance was compared on the NIH ChestX-ray14 dataset (n = 880). The models were also compared with radiologist performance on a subset of the internal testing set (n = 496). Performance was evaluated using receiver operating characteristic (ROC) curve analysis. Results: Given sufficient training data, both models performed similarly to radiologists. CheXDet achieved significant improvement for external classification, such as classifying fracture on NIH Google (CheXDet area under the ROC curve [AUC], 0.67; CheXNet AUC, 0.51; P < .001) and PadChest (CheXDet AUC, 0.78; CheXNet AUC, 0.55; P < .001). CheXDet achieved higher lesion detection performance than CheXNet for most abnormalities on all datasets, such as detecting pneumothorax on the internal set (CheXDet jackknife alternative free-response ROC [JAFROC] figure of merit [FOM], 0.87; CheXNet JAFROC FOM, 0.13; P < .001) and NIH ChestX-ray14 (CheXDet JAFROC FOM, 0.55; CheXNet JAFROC FOM, 0.04; P < .001). Conclusion: Fine-grained annotations overcame shortcut learning and enabled DL models to identify correct lesion patterns, improving the generalizability of the models.Keywords: Computer-aided Diagnosis, Conventional Radiography, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms, Localization Supplemental material is available for this article © RSNA, 2022.

[Study on the prevalence and risk factors of "subhealth" status in college and university staff in Guangdong province].

OBJECTIVE: To understand the current status and risk factors of "subhealth" in college and university staff in Guangdong province. METHODS: Eight thousand four hundred and seventeen staff in 19 colleges and universities in Guangdong were investigated through a self-developed questionnaire, and statistically analyzed using chi(2) test, chi(2)(strand) test and odd ratio. Judgement was based on the criteria on "subhealth" through Delphi method. RESULTS: Overall incidence of "subhealth" was 69.18% in 8,417 staff members, and the highest was in the age group of 30 - 40 year olds (totally 79.17%). The prevalence of severe "subhealth" in females was significantly higher than that of males (chi(2) = 14.19, P < 0.01). The main risk factors of "subhealth" were occupational stress, psychological factors, bad habits and behaviors. 44.21% of the 8,417 staff were aware of the terminology "subhealth", and 36.84% thought themselves under "subhealthy" condition. CONCLUSION: The health condition of college and university staff in Guangdong was not satisfactory, thus it was essential to carry out active measures of prevention and intervention among this population.