Deep learning with biopsy whole slide images for pretreatment prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer：A multicenter study

IntroductionPredicting pathological complete response (pCR) for patients receiving neoadjuvant chemotherapy (NAC) is crucial in establishing individualized treatment. Whole-slide images (WSIs) of tumor tissues reflect the histopathologic information of the tumor, which is important for therapeutic response effectiveness. In this study, we aimed to investigate whether predictive information for pCR could be detected from WSIs.Materials and methodsWe retrospectively collected data from four cohorts of 874 patients diagnosed with biopsy-proven breast cancer. A deep learning pathological model (DLPM) was constructed to predict pCR using biopsy WSIs in the primary cohort, and it was then validated in three external cohorts. The DLPM could generate a deep learning pathological score (DLPs) for each patient; stromal tumor-infiltrating lymphocytes (TILs) were selected for comparison with DLPs.ResultsThe WSI feature-based DLPM showed good predictive performance with the highest area under the curve (AUC) of 0.72 among the cohorts. Alternatively, the combination of the DLPM and clinical characteristics offered a better prediction performance (AUC >0.70) in all cohorts. We also evaluated the performance of DLPM in three different breast subtypes with the best prediction for the triple-negative breast cancer (TNBC) subtype (AUC: 0.73). Moreover, DLPM combined with clinical characteristics and stromal TILs achieved the highest AUC in the primary cohort (AUC: 0.82) and validation cohort 1 (AUC: 0.80).ConclusionOur study suggested that WSIs integrated with deep learning could potentially predict pCR to NAC in breast cancer. The predictive performance will be improved by combining clinical characteristics. DLPs from DLPM can provide more information compared to stromal TILs for pCR prediction.     

Uncertainty evaluation at three spatial scales for the NDVI-based VWC estimation method used in the SMAP algorithm

Vegetation water content (VWC) is the key input parameter for a soil moisture retrieval algorithm based on microwave remote sensing, and VWC uncertainty can limit the estimated accuracy of soil moisture. There has been little research on VWC algorithm development and validation in China, and the uncertainty of the VWC estimation method has not been well evaluated. Therefore, the aim of this study is to evaluate the uncertainty of the VWC estimation method used in the SMAP (Soil Moisture Active Passive) algorithm on three spatial scales (the point-scale, 30 m scale, and 1 km scale) for maize in northeast China. Results from three ground experimental datasets showed that the SMAP VWC estimation method was strongly biased with an average overestimation of 1.16 kg m^?2,1.04 kg m^?2, and 1.13 kg m^?2 for the point-scale, 30 m scale, and 1 km scale respectively, and maximum bias occurred in the mid-stage of maize. Also, a new power relationship between NDVI (Normalized Difference Vegetation Index) and VWC was proposed for the 30 m scale based on Sentinel 2 NDVI and field VWC values from 2017 experiment, with respective R² (coefficient of determination) and Root Mean Squared Error (RMSE) values of 0.80 and 0.67 kg m^?2. The results confirmed that this power relationship was still suitable for VWC estimation at the 1 km scale, and it has smaller bias than the original SMAP VWC method. Future work will be carried out to evaluate the applicability of this VWC estimation method over a lager region. It is expected that it can improve the accuracy of soil moisture by providing high precision VWC input parameters.     

科研评价导向的改变对中文科技期刊的机遇与挑战

【目的】 值此《中国科技期刊研究》创刊30周年之际,思考科研评价体系的改变给中文科技期刊带来的影响,为中文期刊探寻发展路径。【方法】 结合对中文科技期刊困境的研究,提出应对策略。【结果】 近期国家陆续出台的纠偏评价导向的政策文件,为中文科技期刊既带来了发展机遇,也提出了挑战。【结论】 在重构符合中文科技期刊发展特点的评价体系的基础上,中文科技期刊应明确目标定位,面向国家需求,提升知识服务能力,建立品牌特色。     

Longistylin A,a natural stilbene isolated from the leaves of Cajanus cajan,exhibits significant anti-MRSA activity

Longistylin A (LLA) is an abundant stilbene isolated from the leaves of Cajanus cajan (L.) Millsp. However, the antibacterial effect of LLA is not yet understood. Therefore, in this study, a detailed investigation of the antibacterial effect of LLA, particularly against methicillin-resistant Staphylococcus aureus (MRSA), was conducted. In vitro, LLA exhibited strong antibacterial activity against MRSA with a minimum inhibitory concentration (MIC) of 1.56 µg/mL and displayed much more rapid bactericidal activity (3-log decrease in MRSA survival within 8 h) than vancomycin. A membrane-targeting experiment suggested that the antibacterial activity of LLA is associated with perturbation of the bacterial membrane potential and increased membrane permeability. Notably, LLA had relatively weak cytotoxicity to murine macrophages [50% cytotoxic concentration (CC₅₀) = 8.61 ± 0.57 µg/mL]. In vivo, topical treatment of a skin injury with LLA improved wound healing and closure in an MRSA-infected wound healing mouse model. After 3 days treatment, LLA decreased MRSA bacterial counts in the wounded region, reduced the accumulation of immune cells at the injury site, and alleviated induction of the inflammatory cytokines tumour necrosis factor-alpha (180.74 ± 10.78 pg/mL vs. 606.57 ± 68.99 pg/mL) and interleukin-6 (87.25 ± 10.19 pg/mL vs. 280.58 ± 42.27 pg/mL) in serum.     

中医药文献语义标注系统研究与开发

目的研究和开发支持中医和现代生物医学本体和术语集的语义标注系统。方法以MedPortal本体库和中医临床术语集等为术语资源库,设计语义标注系统工作流程和功能框架,并开发Web应用系统。结果构建了一个基于Web的中医药文献语义标注系统,支持语料库管理与维护、术语词典管理、语义标注和语义检索等功能,既可以为基于机器学习的信息抽取算法研究提供训练集,又能实现语义层面的多来源数据集成与知识融合。结论该中医药文献语义标注系统设计方案已经过实际项目验证,可为其他同类系统研发提供参考。