从信号到知识——基于人工智能的医学影像裸数据诊断价值初探

Encouraging and astonishing developments have recently been achieved in image-based diagnostic technology.Modern medical care and imaging technology are becoming increasingly inseparable.However,the current diagnosis pattern of signal to image to knowledge inevitably leads to information distortion and noise introduction in the procedure of image reconstruction(from signal to image).Artificial intelligence(AI)technologies that can mine knowledge from vast amounts of data offer opportunities to disrupt established workflows.In this prospective study,for the first time,we develop an AI-based signal-toknowledge diagnostic scheme for lung nodule classification directly from the computed tomography(CT)raw data(the signal).We find that the raw data achieves almost comparable performance with CT,indicating that it is possible to diagnose diseases without reconstructing images.Moreover,the incorporation of raw data through three common convolutional network structures greatly improves the performance of the CT models in all cohorts(with a gain ranging from 0.01 to 0.12),demonstrating that raw data contains diagnostic information that CT does not possess.Our results break new ground and demonstrate the potential for direct signal-to-knowledge domain analysis.

Validation and evaluation of clinical prediction systems for first and repeated transarterial chemoembolization in unresectable hepatocellular carcinoma: A Chinese multicenter retrospective study

BACKGROUND The treatment outcome of transarterial chemoembolization(TACE)in unresectable hepatocellular carcinoma(HCC)varies greatly due to the clinical heterogeneity of the patients.Therefore,several prognostic systems have been proposed for risk stratification and candidate identification for first TACE and repeated TACE(re-TACE).AIM To investigate the correlations between prognostic systems and radiological response,compare the predictive abilities,and integrate them in sequence for outcome prediction.METHODS This nationwide multicenter retrospective cohort consisted of 1107 unresectable HCC patients in 15 Chinese tertiary hospitals from January 2010 to May 2016.The Hepatoma Arterial-embolization Prognostic(HAP)score system and its modified versions(mHAP,mHAP2 and mHAP3),as well as the six-and-twelve criteria were compared in terms of their correlations with radiological response and overall survival(OS)prediction for first TACE.The same analyses were conducted in 912 patients receiving re-TACE to evaluate the ART(assessment for re-treatment with TACE)and ABCR(alpha-fetoprotein,Barcelona Clinic Liver Cancer,Child-Pugh and Response)systems for post re-TACE survival(PRTS).RESULTS All the prognostic systems were correlated with radiological response achieved by first TACE,and the six-and-twelve criteria exhibited the highest correlation(Spearman R=0.39,P=0.026)and consistency(Kappa=0.14,P=0.019),with optimal performance by area under the receiver operating characteristic curve of 0.71[95%confidence interval(CI):0.68-0.74].With regard to the prediction of OS,the mHAP3 system identified patients with a favorable outcome with the highest concordance(C)-index of 0.60(95%CI:0.57-0.62)and the best area under the receiver operating characteristic curve at any time point during follow-up;whereas,PRTS was well-predicted by the ABCR system with a C-index of 0.61(95%CI:0.59-0.63),rather than ART.Finally,combining the mHAP3 and ABCR systems identified candidates suitable for TACE with an improved median PRTS of 36.6 mo,compared with non-candidates with a median PRTS of 20.0 mo(logrank test P<0.001).CONCLUSION Radiological response to TACE is closely associated with tumor burden,but superior prognostic prediction could be achieved with the combination of mHAP3 and ABCR in patients with unresectable liver-confined HCC.

医患共同决策系列之二:医患共同决策研究典范——渥太华患者决策辅助工具 研究小组

医患共同决策(shared decision making,SDM)在西方发达国家发展较早较快,出现了成果斐然的研究组织,如渥太华患者决策辅助工具研究小组、梅奥诊所医患共同决策国家资源中心以及英国国家卫生医疗质量标准署等。本文拟对渥太华患者决策辅助工具研究小组的创建和使命,决策支持和SDM的理论模型与框架,决策指导、国际患者决策辅助工具合作组织及其制订的标准,用于研发患者决策辅助工具的相关资源,以及实施决策支持的步骤等进行介绍,以期为国内SDM相关研究者提供参考。

The concept of narrative evidence-based medicine and shared decision-making in traditional Chinese medical practice

For the explosive development of emerging diagnostic and therapeutic technologies brought by the advancement of precision medicine strategy, shared decision-making could improve the quality of clinical decision-making and promote the transformation of clinical research evidence in TCM. Paying attention to patients＇ narrative needs and strengthening medical humanistic concerns could improve clinical outcome and patient satisfaction. We described the origins and development of evidence-based medicine, narrative medicine and shared decision-making, and analyzed the existing problems in TCM clinical decision-making. Further, we put forward the model of shared decision-making between clinicians and patients under the guidance of narrative evidence-based medicine concepts and methods.

A review on the International Patient Decision Aid Standards （IPDAS）： history, development and application

A Patient Decision Aid （PtDA） is an important means in TCM practice to promote shared decision-making between doctor and patient, which is developed based on evidence-based and narrative medicine concepts. It is also an important tool for individualized diagnosis and treatment in the context of precision medical care. With the rapid increase of interest on the PtDA, it is important to establish a unified quality evaluation standard and standardize the development process. This article aims to introduce the main content, development history and application of International Patient Decision Aid Standards （IPDAS）, and provide reference for the application of the evaluation standard in China.

Exosomal CD44 Cooperates with Integrin a6b4 to Support Organotropic Metastasis via Regulating Tumor Cell Motility and Target Host Cell Activation

Rapid metastasis to vital organs such as the lung,liver,and brain is responsible for the vast majority of pancreatic cancer deaths.Liver metastasis of pancreatic cancer accounts for the high mortality rate in patients.Exosomes derived from pancreatic cancer cells tend to be enriched in proteins that are anchored to the cell membrane,supporting the reprogramming of the tumor microenvironment and the progression of distant metastatic lesions.For the first time,our study has demonstrated that cluster of differentiation 44(CD44),a transmembrane glycoprotein delivered by exosomes,is involved in the metastatic process of pancreatic cancer.Moreover,CD44 was found to interact with integrin a6b4 to form a complex,thereby remodeling intracellular skeleton proteins,and to promote tumor cell motility through the activation of the Src and Ras signaling cascades.Notably,we also demonstrated that the CD44–a6b4 complex can be delivered to the target region via the paracrine effects of exosomes.The selective uptake of CD44-competent tumor exosomes by liver cells activated fibrotic pathways and generated a pre-metastatic niche by stimulating the cytokines,proinflammatory factors,and growth factors that ultimately support tumor metastasis.Our results suggest the potential application of exosomal CD44 as a biomarker for the clinical diagnosis of and therapy for pancreatic cancer.

Analysis of Adverse Drug Reactions Caused by Chinese Patent Medicine Treatment Based on Kidney Damp-heat Syndrome and Damp-turbidity Syndrome

[Objectives]To determine relationship of the adverse drug reaction(ADR)occurrence of the single use and combined use of Huangkui Capsule and Haikun Shenxi Capsule.[Methods]To determine relationship of the ADR occurrence of the single use and combined use of Huangkui Capsule and Haikun Shenxi Capsule.[Results]The main adverse drug reactions of the single use of Huangkui Capsule or Haikun Shenxi Capsule was severe diarrhea(n=7,n=9),however the combined use of the two resulted in more occurrence of adverse drug reactions(n=23)with significant difference in contrast to the single use group(P=0.0015,P=0.0069).[Conclusions]When traditional Chinese patent medicines are used in combination to treat kidney damp-heat syndrome and damp-turbid syndrome,it is necessary to pay close attention to the occurrence of adverse drug reactions,especially the digestive system.

Chinese patent medicine for stable angina pectoris:protocol for a systematic review and network meta-analysis

Stable angina pectoris is a common condition that affects a wide group of patients with coronary artery diseases.A number of Chinese patent drugs based on classic herbal formulations are available for angina management.A network meta-analysis is proposed to assess the relative efficacy and safety of commonly used drugs for stable angina and generate a clinically meaningful ranking for each important outcome.We composed a list of 24 widely-used oral blood-quickening Chinese patent drugs from literature review and expert consultation.Three English and five Chinese electronic databases will be searched up to July 2021 for randomised clinical trials comparing between drugs on the list or with nitrates or placebo for stable angina.Unpublished data or grey literature will be sought through trial registries and correspondence to the report authors.Two reviewers independently screen literature,extract data and assess clinical and methodological features of included studies.The WinBUGS software will be used to perform network meta-analysis and the Stata 13.0 software to generate graphic demonstrations of the results.Primary outcomes are the incidence of cardiovascular events and changes in angina frequency,duration and intensity.We will use the surface under the cumulative ranking curve and the mean value for the numeric presentation of efficacy and safety ranking probabilities of multiple treatments.Heterogeneity and inconsistency will be assessed using appropriate statistical tests,and subgroup analysis and network meta-regression will be resorted when necessary.The quality of evidence for each outcome will be graded with the web-based GRADEpro GDT.

Prospects for the future of clinical efficacy evaluation of traditional Chinese medicine——Emphasis on original theory and clinical practice

Traditional Chinese medicine(TCM)clinical efficacy evaluation runs through the development of TCM and has been progressing so far.With the introduction of evidence-based medicine(EBM)in recent 20 years,TCM clinical efficacy evaluation has developed rapidly,accumulated research and experience,improved the quality and standardization of research,but also gradually found deep-seated deficiencies.In 2019,the China Center for Evidence-based Traditional Chinese Medicine(CCEBTCM)was established,and TCM was included in the 11th revision of the International Statistical Classification of Diseases(ICD-11).In above opportunities for TCM clinical efficacy evaluation,it is necessary to face up to the previous deficiencies,so that the TCM clinical efficacy evaluation can truly reflect the actual clinical practice characteristics,including TCM clinical problems,TCM thinking and TCM diagnosis&treatment mode.Based on the summary and analysis of past research,development concepts are proposed in this article.On the one hand,original concepts of TCM should be confidently paid more attention to the design and implementation of TCM clinical efficacy evaluation to be close to TCM clinical practice.On the other hand,it is necessary to consolidate the foundation of TCM clinical practice before evaluating efficacy.Evaluated object built on TCM ontology knowledge should be demonstrated based on clinical practice,and unknown evaluated object combined with new methods,technologies and concepts should be maturely integrated in clinical practice firstly.

Rethinking the Encoder-decoder Structure in Medical Image Segmentation from Releasing Decoder Structure

Medical image segmentation has witnessed rapid advancements with the emergence of encoder-decoder based methods.In the encoder-decoder structure,the primary goal of the decoding phase is not only to restore feature map resolution,but also to mitigate the loss of feature information incurred during the encoding phase.However,this approach gives rise to a challenge:multiple up-sampling operations in the decoder segment result in the loss of feature information.To address this challenge,we propose a novel network that removes the decoding structure to reduce feature information loss(CBL-Net).In particular,we introduce a Parallel Pooling Module(PPM)to counteract the feature information loss stemming from conventional and pooling operations during the encoding stage.Furthermore,we incorporate a Multiplexed Dilation Convolution(MDC)module to expand the network's receptive field.Also,although we have removed the decoding stage,we still need to recover the feature map resolution.Therefore,we introduced the Global Feature Recovery(GFR)module.It uses attention mechanism for the image feature map resolution recovery,which can effectively reduce the loss of feature information.We conduct extensive experimental evaluations on three publicly available medical image segmentation datasets:DRIVE,CHASEDB and MoNuSeg datasets.Experimental results show that our proposed network outperforms state-of-the-art methods in medical image segmentation.In addition,it achieves higher efficiency than the current network of coding and decoding structures by eliminating the decoding component.

Exposure of benzo[a]pyrene induces HCC exosome-circular RNA to activate lung fibroblasts and trigger organotropic metastasis

Background:Benzo[a]pyrene(B[a]P),a carcinogen pollutant produced by combustion processes,is present in the western diet with grilled meats.Chronic exposure of B[a]P in hepatocellular carcinoma(HCC)cells promotes metastasis rather than primary proliferation,implying an unknown mechanism of B[a]P-induced malignancy.Given that exosomes carry bioactive molecules to distant sites,we investigated whether and how exosomes mediate cancer-stroma communications for a toxicologically associated microenvironment.Method:Exosomes were isolated from B[a]P stimulated BEL7404 HCC cells(7404-100Bap Exo)at an environmental relevant dose(100 nmol/L).Lung preeducation animal model was prepared via injection of exosomes and cytokines.The inflammatory genes of educated lungs were evaluated using quantitative reverse transcription PCR array.HCC LM3 cells transfected with firefly luciferase were next injected to monitor tumor burdens and organotropic metastasis.Profile of B[a]P-exposed exosomes were determined by ceRNA microarray.Interactions between circular RNA(circRNA)and microRNAs(miRNAs)were detected using RNA pull-down in target lung fibroblasts.Fluorescence in situ hybridization and RNA immunoprecipitation assay was used to evaluate the“on-off”interaction of circRNA-miRNA pairs.We further developed an adenoassociated virus inhalation model to examine mRNA expression specific in lung,thereby exploring the mRNA targets of B[a]P induced circRNA-miRNA cascade.Results:Lung fibroblasts exert activation phenotypes,including focal adhesion and motility were altered by 7404-100Bap Exo.In the exosome-educated in vivo model,fibrosis factors and pro-inflammatory molecules of are up-regulated when injected with exosomes.Compared to non-exposed 7404 cells,circ_0011496 was up-regulated following B[a]P treatment and wasmainly packaged into 7404-100Bap Exo.Exosomal circ_0011496 were delivered and competitively bound to miR-486-5p in recipient fibroblasts.The down-regulation of miR-486-5p converted fibroblast to cancer-associated fibroblast via regulating the downstream of Twinfilin-1(TWF1)and matrix metalloproteinase-9(MMP9)cascade.Additionally,increased TWF1,specifically in exosomal circ_0011496 educated lungs,could promote cancer-stroma crosstalk via activating vascular endothelial growth factor(VEGF).These modulated fibroblasts promoted endothelial cells angiogenesis and recruited primary HCC cells invasion,as a consequence of a pre-metastatic niche formation.Conclusion:We demonstrated that B[a]P-induced tumor exosomes can deliver circ_0011496 to activate miR-486-5p/TWF1/MMP9 cascade in the lung fibroblasts,generating a feedback loop that promoted HCC metastasis.

Benzo[a]pyrene stimulates miR-650 expression to promote the pathogenesis of fatty liver disease and hepatocellular carcinoma via SOCS3/JAK/STAT3 cascades

Modern diets,which often feature high levels of fat and charcoal-grilled meat,contribute to the pathogenesis of obesity and non-alcoholic fatty liver disease(NAFLD),resulting in liver cancer progression.Benzo(a)pyrene(B[a]P)is a common environ-mental and foodborne pollutant found in smoke and fire-grilled foods,which can have an adverse effect on human health.Hepatocellular carcinoma(HCC)is the fifth leading cause of cancer and the second leading cause of cancer-related deaths worldwide.The epidemiological studies suggest that both environmental risk factors and chronic liver injury including NAFL are important for HCC development,but the precise mechanisms linking eating habits to hepato-carcinogenesis remain unclear.In the present study,we demonstrated that various miRNAs in B[a]P-exposed tumor cells contribute to tumor metastasis,among which miR-650 could be the most potent inducer.Furthermore,we found that the suppressor of cytokine signaling 3(SOCS3)is directly regulated by miR-650 and its suppression regulates the activation of the Janus kinase/signal transducer and activator of transcription 3 (JAK/STAT3)cascade.Our findings reveal a possible adverse outcome pathway of SOCS3/JAK/STAT3 regulation in B[a]P-induced HCC progress.These results provide a better understanding of the adverse effects of chronic exposure to B[a]P on human health.

Transarterial chemoembolization with PD-(L)1 inhibitors plus molecular targeted therapies for hepatocellular carcinoma(CHANCE001)

There is considerable potential for integrating transarterial chemoembolization(TACE),programmed death-(ligand)1(PD-[L]1)inhibitors,and molecular targeted treatments(MTT)in hepatocellular carcinoma(HCC).It is necessary to investigate the therapeutic efficacy and safety of TACE combined with PD-(L)1 inhibitors and MTT in real-world situations.In this nationwide,retrospective,cohort study,826 HCC patients receiving either TACE plus PD-(L)1 blockades and MTT(combination group,n=376)or TACE monotherapy(monotherapy group,n=450)were included from January 2018 to May 2021.The primary endpoint was progression-free survival(PFS)according to modified RECIST.The secondary outcomes included overall survival(OS),objective response rate(ORR),and safety.We performed propensity score matching approaches to reduce bias between two groups.After matching,228 pairs were included with a predominantly advanced disease population.Median PFS in combination group was 9.5 months(95%confidence interval[CI],8.4-11.0)versus 8.0 months(95%CI,6.6-9.5)(adjusted hazard ratio[HR],0.70,P=0.002).OS and ORR were also significantly higher in combination group(median OS,19.2[16.1-27.3]vs.15.7 months[13.0-20.2];adjusted HR,0.63,P=0.001;ORR,60.1%vs.32.0%;P<0.001).Grade 3/4 adverse events were observed at a rate of 15.8%and 7.5%in combination and monotherapy groups,respectively.Our results suggest that TACE plus PD-(L)1 blockades and MTT could significantly improve PFS,OS,and ORR versus TACE monotherapy for Chinese patients with predominantly advanced HCC in real-world practice,with an acceptable safety profile.

The Applications of Artificial Intelligence in Digestive System Neoplasms:A Review

Importance:Digestive system neoplasms(DSNs)are the leading cause of cancer-related mortality with a 5-year survival rate of less than 20%.Subjective evaluation of medical images including endoscopic images,whole slide images,computed tomography images,and magnetic resonance images plays a vital role in the clinical practice of DSNs,but with limited performance and increased workload of radiologists or pathologists.The application of artificial intelligence(AI)in medical image analysis holds promise to augment the visual interpretation of medical images,which could not only automate the complicated evaluation process but also convert medical images into quantitative imaging features that associated with tumor heterogeneity.Highlights:We briefly introduce the methodology of AI for medical image analysis and then review its clinical applications including clinical auxiliary diagnosis,assessment of treatment response,and prognosis prediction on 4 typical DSNs including esophageal cancer,gastric cancer,colorectal cancer,and hepatocellular carcinoma.Conclusion:AI technology has great potential in supporting the clinical diagnosis and treatment decision-making of DSNs.Several technical issues should be overcome before its application into clinical practice of DSNs.

基于UPLC-PDA指纹图谱及多成分含量的化学模式识别法评价大黄质量

目的采用超高效液相色谱-光电二极管阵列检测器(UPLC-PDA)建立大黄药材指纹图谱及同时测定大黄中9个成分含量的分析方法,并对17批不同产地、不同基原、不同生长年限的大黄进行质量分析和评价。方法采用ThermoSyncronis C18色谱柱(100 mm×2.1 mm,1.7μm),以乙腈(A)-0.1%甲酸水溶液(B)为流动相,梯度洗脱。指纹图谱数据导入SIMCA-P14.1软件进行聚类分析和主成分分析,同时基于UPLC-PDA法对番泻苷B、大黄酸-8-O-β-D-葡萄糖苷、番泻苷A、大黄素-8-O-β-D-葡萄糖苷、大黄素、大黄酸、大黄酚、大黄素甲醚、芦荟大黄素共9个成分进行定量分析。结果17批大黄药材指纹图谱共寻找共有峰20个,经对照品指认9个峰。聚类分析与主成分分析显示,唐古特大黄、掌叶大黄能够显著区分,唐古特大黄与药用大黄相似,聚为一类;4年与5年的唐古特大黄不能区分、1年与2年的掌叶大黄不能区分。指标性成分含量测定结果显示,唐古特大黄高于其他2种大黄,4年的唐古特大黄质量优于5年的,2年的掌叶大黄质量优于1年的。结论采用UPLC-PDA技术,建立的大黄药材指纹图谱结合多成分含量测定的方法能够快速、科学、准确地区分不同基原的大黄,并对不同年限大黄质量进行初步评价,为大黄药材基原区分及质量评价提供依据。

医患共同决策系列之一:医患共同决策的国内外发展现状

医患共同决策(Shared Decision Making,SDM)作为一种新型医疗决策模式,越来越被国际社会关注和重视。SDM在欧美等国家和地区已发展得比较成熟,但国内对SDM的研究仍处于理论借鉴和应用摸索阶段。本文主要回顾SDM的起源和发展,探究其国内外研究现状,并思索其在临床实践中的局限性,为其系列研究做出铺垫,同时为国内SDM研究者全面了解SDM的发展历史及研究现状提供参考。

CRISPR-Cas9 mediated LAG-3 disruption in CAR-T cells

T cells engineered with chimeric antigen receptor （CAR） have been successfully applied to treat advanced refractory B cell malignancy. However, many challenges remain in extending its application toward the treatment of solid tumors. The immunosuppressive nature of tumor microenvironment is considered one of the key factors limiting CART efficacy. One negative regulator of T cell activity is lymphocyte activation gene-3 （LAG-3）. We successfully generated LAG-3 knockout T and CAR-T cells with high efficiency using CRISPR-Cas9 mediated gene editing and found that the viability and immune phenotype were not dramatically changed during in vitro culture. LAG-3 knockout CART cells displayed robust antigen-specific antitumor activity in cell culture and in murine xenograft model, which is comparable to standard CAR-T cells. Our study demonstrates an efficient approach to silence immune checkpoint in CAR-T cells via gene editing.

T cells expressing CD5/CD7 bispecific chimeric antigen receptors with fully human heavy-chain-only domains mitigate tumor antigen escape

Bispecific chimeric antigen receptor T-cell(CAR-T)therapies have shown promising results in clinical trials for advanced B-cell malignancies.However,it is challenging to broaden the success of bispecific CAR-T therapies to treat refractory/relapse(r/r)T-cell leukemia/lymphoma because targeting multiple T-cell-expressing antigens leads to exacerbated CAR-T cell fratricide and potential safety concerns.Fully human heavy chain variable(FHVH)antibodies that specifically target CD5 or CD7 were screened and constructed to CD5/CD7 bispecific CARs.A truncated Epidermal growth factor receptor were integrated into CAR constructs to address safety concerns.To tackle the fratricidal issue of CAR-T cells targeting T-cell-pan marker(s),CRISPR/Cas9-based CD5 and CD7 genes knockout were performed before lentiviral transduction of bispecific CARs.Functional comparison between different bispecific CAR structures:tandem CARs and dual CAR were performed in vitro and in vivo to determine the optimal construct suitable for addressing T-cell malignancy antigen escape in clinical setting.Knockout of CD5 and CD7 prevents fratricide of CD5/CD7 bispecific CAR-T cells,and FHVH-derived CD5/CD7 bispecific CAR-T cells demonstrate potent antitumor activity in vitro and in vivo.The fratricide-resistant FHVH-derived CD5/CD7 bispecific CAR-T cells have potent antitumor activity against T-cell malignancies,and tandem CARs are more effective than dual CAR in preventing tumor escape in heterogeneous leukemic cells.The meaningful clinical efficacy and safety of tandem CD5/CD7 CAR-T cells deserve to be explored urgently.

In vitro transcribed sgRNA causes cell death by inducing interferon release

Dear editor The clustered regularly in terspaced short palindromic repeats (CRISPR) and the CRISPR-associated proteins 9 (Cas9) systems are powerful tools for gene editing. Ribonucleoprotein (RNP) complex composed of Cas9 pro? tein and sgRNA binds to specific genomic loci and gen erate DNA double strand breaks. While plasmids expressing Cas9 protein and sgRNA are routinely transfected into various cell lines to perform gene editing (Cong et al., 2013;Mali et al., 2013;Ran et al., 2013), direct delivery of Cas9-sgRNA RNP has shown higher efficiency and lower off-target effects (Kim et al., 2014), especially in human primary cells such as T cells (Hendel et al., 2015;Schumann et al., 2015). SgRNA can be gen erated by either in vitro transcript! on (IVT) or chemical syn thesis. IVT is widely used to gen erate sgRNAs, since it can be easily performed in most labs.

5'capped and 3'polyA-tailed sgRNAs enhance the efficiency of CRISPR-Cas9 system

Dear Editor,The clustered regularly interspaced short palindromic repeats(CRISPR)-associated(Cas)system is an adaptive immune system in a variety of bacteria and archaea(Terns and Terns,2011).The most commonly used Streptococcus pyogenes type II CRISPR-Cas9 system consists of Cas9 nuclease and two short RNAs,crRNA and tracrRNA,which can be linked together forming one chimeric single guide RNA(sgRNA)(Jinek et al.,2012).