Deepm5C: A deep-learning-based hybrid framework for identifying human RNA N5-methylcytosine sites using a stacking strategy

1. Download : Download high-res image (173KB)
2. Download : Download full-size image

     

Bench to bedside: recent advances in lung cancer pathological research with implications for diagnostic clinical practice

After decades of relative stagnation lung cancer is emerging as a disease type where rapid progress is being made in diagnosis and therapy, as well as in our understanding of disease biology. Much of this progress is of immediate impact to diagnosticians, and more is likely to affect diagnostic practice in the near future. In this review we seek to briefly summarize several key areas of active research of immediate or probable imminent value to trainee and consultant pulmonary pathologists alike. We cover some major changes in tumour classification, grading, and patient stratification, as well as considering the state of the art in machine-assisted interpretation of lung cancer histology, and the use of genetically modified lung cancer models.     

新型冠状病毒核酸检测在眼科医院疫情防控中的实践与有效性研究

目的:探索以系统化、标准化的新型冠状病毒核酸检测为核心和重要组成部分,建立适合于眼科医院新冠疫情精准防控切实可行的防控体系。方法:系列病例研究。自2020年2月24日至3月2日期间,以标准化病毒核酸检测联合血常规、C反应蛋白(CRP)、血清淀粉样蛋白A(SAA)等检测作为所有眼科手术患者术前筛查常规检测项目,同时也为返岗员工提供病毒核酸检测。设计调查问卷了解受检者对鼻咽拭子采样的接受度以及核酸检测结果对其心理状态的影响。结果:99例患者血液学检测结果有一定的异常比例,其中SAA检测结果增高13例,淋巴细胞计数减低12例、增高5例,白细胞计数增高11例、减低1例,CRP增高2例,新型冠状病毒核酸检测均阴性。33例本院职工新型冠状病毒核酸检测均阴性。12%的受访者对鼻咽拭子采样接受度评分较低。受检者在核酸检测前后思想压力评分较高的比例分别为46.7%和6.7%。结论:该项举措一方面为术前新冠病毒肺炎筛查及鉴别诊断提供了客观依据,很大程度上排除了隐性无症状感染者传播的可能,有利于减少二次传播的风险,降低院内交叉感染的概率;另一方面,核酸检测阴性结果有利于调整患者术前的心理状态并缓解医护人员在疫情防控期间的心理压力。     

Effectiveness of cognitive rehabilitation for people with multiple sclerosis: a meta-synthesis of patient perspectives

While previous randomised controlled trials and meta-analyses offer only limited evidence for the effectiveness of cognitive rehabilitation, qualitative studies examining patient perspectives report more positive outcomes. This meta-synthesis of qualitative studies examined patient perspectives of cognitive rehabilitation for memory, attention, and executive function problems in people with multiple sclerosis. Using set eligibility criteria, we screened electronic databases, reference lists, and academic networks for relevant papers. Seven papers (195 participants) were selected. Two independent researchers conducted quality appraisals of papers. Data analysis, guided by the thematic synthesis approach, yielded six main themes. These suggested that patients benefitted from the group environment in rehabilitation. Cognitive rehabilitation facilitated the participants’ reflection and awareness of their cognitive deficits, and was associated with increased knowledge and understanding of their illness. Increased strategy use was reported and associated with improvements in cognitive functioning and greater confidence and perseverance. Participants reported emotional and social improvements, and felt more optimistic. Overall, these changes had a positive impact on participants’ quality of life. This synthesis of qualitative studies indicates that people with multiple sclerosis who experience cognitive deficits benefit from cognitive rehabilitation programmes. This finding must, however, be viewed in light of the limitations of this meta-synthesis. The meta-synthesis was registered in the PROSPERO database under CRD42017040148.     

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.     

Coupling online control and inhibitory systems in children with Developmental Coordination Disorder: Goal-directed reaching

For children with Developmental Coordination Disorder (DCD), the real-time coupling between frontal executive function and online motor control has not been explored despite reported deficits in each domain. The aim of the present study was to investigate how children with DCD enlist online control under task constraints that compel the need for inhibitory control. A total of 129 school children were sampled from mainstream primary schools. Forty-two children who met research criteria for DCD were compared with 87 typically developing controls on a modified double-jump reaching task. Children within each skill group were divided into three age bands: younger (6–7 years), mid-aged (8–9), and older (10–12). Online control was compared between groups as a function of trial type (non-jump, jump, anti-jump). Overall, results showed that while movement times were similar between skill groups under simple task constraints (non-jump), on perturbation (or jump) trials the DCD group were significantly slower than controls and corrected trajectories later. Critically, the DCD group was further disadvantaged by anti-jump trials where inhibitory control was required; however, this effect reduced with age. While coupling online control and executive systems is not well developed in younger and mid-aged children, there is evidence of age-appropriate coupling in older children. Longitudinal data are needed to clarify this intriguing finding. The theoretical and applied implications of these results are discussed.