Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of...Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians.Moreover,some potentially useful quantitative information in medical images,especially that which is not visible to the naked eye,is often ignored during clinical practice.In contrast,radiomics performs high-throughput feature extraction from medical images,which enables quantitative analysis of medical images and prediction of various clinical endpoints.Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis,demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine.However,radiomics remains in a developmental phase as numerous technical challenges have yet to be solved,especially in feature engineering and statistical modeling.In this review,we introduce the current utility of radiomics by summarizing research on its application in the diagnosis,prognosis,and prediction of treatment responses in patients with cancer.We focus on machine learning approaches,for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling.Furthermore,we introduce the stability,reproducibility,and interpretability of features,and the generalizability and interpretability of models.Finally,we offer possible solutions to current challenges in radiomics research.展开更多
Epilepsy is a central nervous system disorder in which brain activity becomes abnormal.Electroencephalogram(EEG)signals,as recordings of brain activity,have been widely used for epilepsy recognition.To study epilep-ti...Epilepsy is a central nervous system disorder in which brain activity becomes abnormal.Electroencephalogram(EEG)signals,as recordings of brain activity,have been widely used for epilepsy recognition.To study epilep-tic EEG signals and develop artificial intelligence(AI)-assist recognition,a multi-view transfer learning(MVTL-LSR)algorithm based on least squares regression is proposed in this study.Compared with most existing multi-view transfer learning algorithms,MVTL-LSR has two merits:(1)Since traditional transfer learning algorithms leverage knowledge from different sources,which poses a significant risk to data privacy.Therefore,we develop a knowledge transfer mechanism that can protect the security of source domain data while guaranteeing performance.(2)When utilizing multi-view data,we embed view weighting and manifold regularization into the transfer framework to measure the views’strengths and weaknesses and improve generalization ability.In the experimental studies,12 different simulated multi-view&transfer scenarios are constructed from epileptic EEG signals licensed and provided by the Uni-versity of Bonn,Germany.Extensive experimental results show that MVTL-LSR outperforms baselines.The source code will be available on https://github.com/didid5/MVTL-LSR.展开更多
BACKGROUND D-dimer,a soluble degradation product of cross-linked fibrin,is commonly used as an important marker for the diagnosis of disseminated intravascular coagulation and differential diagnosis of thrombosis.Here...BACKGROUND D-dimer,a soluble degradation product of cross-linked fibrin,is commonly used as an important marker for the diagnosis of disseminated intravascular coagulation and differential diagnosis of thrombosis.Herein,we present a geriatric case with an unusually elevated D-dimer level.CASE SUMMARY An 82-year-old woman,admitted to the ward with a diagnosis of chronic heart failure,was noted to have a remarkably elevated D-dimer level,beyond the qualified range(>100 mg/L),utilizing the Innovating D-dimer for Sysmex CS-5100 System?.However,no evidence,including clinical symptoms,radiographic evidence of thromboembolic disease,and parallel fibrinogen degradation product values,suggested that this patient was at high risk of thrombopenia.To confirm the discrepancy,a series of approaches including sample dilution,re-analysis via alternative methods,and sample treatment with blockage of specific heterophilic antibodies were performed.A remarkable disappearance of the elevated D-dimer values was observed in the samples after they were subjected to these approaches(4.49,9.42,9.06,and 12.58 mg/L,respectively).This confirmed the presence of heterophilic antibodies in this case.In addition,a reduction in cardiac output due to the presence of cardiac failure could also be responsible for the existence of a hypercoagulable state in this case.CONCLUSION In conclusion,the presence of heterophilic antibodies should be considered when an elevated D-dimer value is not in conformity with the clinical evidence,and a viral infection should be considered when interference by a heterophilic antibody exists.展开更多
[Objectives]This study aimed to screen the suitable medium and symbiotic fungi for tissue culture of Paphiopedilum dianthum and to establish a rapid propagation system of Paphiopedilum,so as to promote the development...[Objectives]This study aimed to screen the suitable medium and symbiotic fungi for tissue culture of Paphiopedilum dianthum and to establish a rapid propagation system of Paphiopedilum,so as to promote the development of planting industry and commercial application of Paphiopedilum.[Methods]Using P.dianthum as an experimental materials,the optimal culture medium for P.dianthum was selected from DE medium,Harvais modified medium and(bark+DE)liquid medium.Then,six fungal species isolated from the original habitat soil of Paphiopedilum were co-cultured with P.dianthum on the selected optimal culture medium.By comparing the morphology,the growth amount and the physiological indexes,such as chlorophyll content,soluble sugar content and root vitality of tissue culture plantlets of P.dianthum co-cultured with the six fungal species,the suitable fungal strains for symbiosis with P.dianthum were screened out.[Results]In three kinds of culture media,P.dianthum grew normally.The growth rate was higher than that in the mediums containing DE,and there were no significant differences in the content of soluble sugar from the leaves of tissue culture plantlets,which were symbiotic with the six different fungi species.Among the six fungi species growing on the optimal medium,the growing rate of XH-A was the fastest,and that of YY001 was the slowest.The growth and physiological indexes of P.dianthum co-cultured with DY1 in DE medium were higher than those in the control group.[Conclusions]DE medium was the optimal tissue culture medium for P.dianthum,and the optimal symbiotic fungus was DY1.展开更多
Chemotherapy remains one of the irreplaceable treatments for cancer therapy.The use of immunogenic cell death(ICD)-inducing chemotherapeutic drugs offers a practical strategy for killing cancer cells,simultaneously el...Chemotherapy remains one of the irreplaceable treatments for cancer therapy.The use of immunogenic cell death(ICD)-inducing chemotherapeutic drugs offers a practical strategy for killing cancer cells,simultaneously eliciting an antitumor immune response by promoting the recruitment of cytotoxic immune cells and production of granzyme B(GrB).However,numerous malignant cancers adaptively acquired the capacity of secreting serpinb9(Sb9),a physiological inhibitor of GrB,which can reversibly inhibit the biological activity of GrB.To circumvent this dilemma,in this study,an integrated tailor-made nanomedicine composed of tumor-targeting peptide(Arg-Gly-Asp,RGD)decorated liposome,doxorubicin(DOX,an effective ICD inducer),and the compound 3034(an inhibitor of Sb9),is developed(termed as D3RL)for breast cancer chemo-immunotherapy.In vitro and in vivo studies show that D3RL can directly kill tumor cells and trigger the host immune response by inducing ICD.Meanwhile,D3RL can competitively relieve the inhibition of Sb9 to GrB.The restored GrB can not only effectively induce tumor immunotherapy,but also degrade matrix components in the tumor microenvironment,consequently improving the infiltration of immune cells and the penetration of nanomedicines,which in return enhance the combined antitumor effect.Taken together,this work develops an integrated therapeutic solution for targeted production and restoration of GrB to achieve a combined chemo-immunotherapy for breast cancer.展开更多
基金supported in part by the National Natural Science Foundation of China(82072019)the Shenzhen Basic Research Program(JCYJ20210324130209023)+5 种基金the Shenzhen-Hong Kong-Macao S&T Program(Category C)(SGDX20201103095002019)the Mainland-Hong Kong Joint Funding Scheme(MHKJFS)(MHP/005/20),the Project of Strategic Importance Fund(P0035421)the Projects of RISA(P0043001)from the Hong Kong Polytechnic University,the Natural Science Foundation of Jiangsu Province(BK20201441)the Provincial and Ministry Co-constructed Project of Henan Province Medical Science and Technology Research(SBGJ202103038,SBGJ202102056)the Henan Province Key R&D and Promotion Project(Science and Technology Research)(222102310015)the Natural Science Foundation of Henan Province(222300420575),and the Henan Province Science and Technology Research(222102310322).
文摘Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians.Moreover,some potentially useful quantitative information in medical images,especially that which is not visible to the naked eye,is often ignored during clinical practice.In contrast,radiomics performs high-throughput feature extraction from medical images,which enables quantitative analysis of medical images and prediction of various clinical endpoints.Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis,demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine.However,radiomics remains in a developmental phase as numerous technical challenges have yet to be solved,especially in feature engineering and statistical modeling.In this review,we introduce the current utility of radiomics by summarizing research on its application in the diagnosis,prognosis,and prediction of treatment responses in patients with cancer.We focus on machine learning approaches,for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling.Furthermore,we introduce the stability,reproducibility,and interpretability of features,and the generalizability and interpretability of models.Finally,we offer possible solutions to current challenges in radiomics research.
基金supported in part by the National Natural Science Foundation of China(Grant No.82072019)the Shenzhen Basic Research Program(JCYJ20210324130209023)of Shenzhen Science and Technology Innovation Committee+6 种基金the Shenzhen-Hong Kong-Macao S&T Program(Category C)(SGDX20201103095002019)the Natural Science Foundation of Jiangsu Province(No.BK20201441)the Provincial and Ministry Co-constructed Project of Henan Province Medical Science and Technology Research(SBGJ202103038 and SBGJ202102056)the Henan Province Key R&D and Promotion Project(Science and Technology Research)(222102310015)the Natural Science Foundation of Henan Province(222300420575)the Henan Province Science and Technology Research(222102310322)The Jiangsu Students’Innovation and Entrepreneurship Training Program(202110304096Y).
文摘Epilepsy is a central nervous system disorder in which brain activity becomes abnormal.Electroencephalogram(EEG)signals,as recordings of brain activity,have been widely used for epilepsy recognition.To study epilep-tic EEG signals and develop artificial intelligence(AI)-assist recognition,a multi-view transfer learning(MVTL-LSR)algorithm based on least squares regression is proposed in this study.Compared with most existing multi-view transfer learning algorithms,MVTL-LSR has two merits:(1)Since traditional transfer learning algorithms leverage knowledge from different sources,which poses a significant risk to data privacy.Therefore,we develop a knowledge transfer mechanism that can protect the security of source domain data while guaranteeing performance.(2)When utilizing multi-view data,we embed view weighting and manifold regularization into the transfer framework to measure the views’strengths and weaknesses and improve generalization ability.In the experimental studies,12 different simulated multi-view&transfer scenarios are constructed from epileptic EEG signals licensed and provided by the Uni-versity of Bonn,Germany.Extensive experimental results show that MVTL-LSR outperforms baselines.The source code will be available on https://github.com/didid5/MVTL-LSR.
基金Supported by the National Natural Science Foundation of China,No.81672083 and No.81702071
文摘BACKGROUND D-dimer,a soluble degradation product of cross-linked fibrin,is commonly used as an important marker for the diagnosis of disseminated intravascular coagulation and differential diagnosis of thrombosis.Herein,we present a geriatric case with an unusually elevated D-dimer level.CASE SUMMARY An 82-year-old woman,admitted to the ward with a diagnosis of chronic heart failure,was noted to have a remarkably elevated D-dimer level,beyond the qualified range(>100 mg/L),utilizing the Innovating D-dimer for Sysmex CS-5100 System?.However,no evidence,including clinical symptoms,radiographic evidence of thromboembolic disease,and parallel fibrinogen degradation product values,suggested that this patient was at high risk of thrombopenia.To confirm the discrepancy,a series of approaches including sample dilution,re-analysis via alternative methods,and sample treatment with blockage of specific heterophilic antibodies were performed.A remarkable disappearance of the elevated D-dimer values was observed in the samples after they were subjected to these approaches(4.49,9.42,9.06,and 12.58 mg/L,respectively).This confirmed the presence of heterophilic antibodies in this case.In addition,a reduction in cardiac output due to the presence of cardiac failure could also be responsible for the existence of a hypercoagulable state in this case.CONCLUSION In conclusion,the presence of heterophilic antibodies should be considered when an elevated D-dimer value is not in conformity with the clinical evidence,and a viral infection should be considered when interference by a heterophilic antibody exists.
基金Project of Construction of Advanced Horticulture Discipline Under Beijing Municipality(2020)Key Laboratory of Biological and Genetic Improvement of Horticultural Crops under Ministry of Agriculture。
文摘[Objectives]This study aimed to screen the suitable medium and symbiotic fungi for tissue culture of Paphiopedilum dianthum and to establish a rapid propagation system of Paphiopedilum,so as to promote the development of planting industry and commercial application of Paphiopedilum.[Methods]Using P.dianthum as an experimental materials,the optimal culture medium for P.dianthum was selected from DE medium,Harvais modified medium and(bark+DE)liquid medium.Then,six fungal species isolated from the original habitat soil of Paphiopedilum were co-cultured with P.dianthum on the selected optimal culture medium.By comparing the morphology,the growth amount and the physiological indexes,such as chlorophyll content,soluble sugar content and root vitality of tissue culture plantlets of P.dianthum co-cultured with the six fungal species,the suitable fungal strains for symbiosis with P.dianthum were screened out.[Results]In three kinds of culture media,P.dianthum grew normally.The growth rate was higher than that in the mediums containing DE,and there were no significant differences in the content of soluble sugar from the leaves of tissue culture plantlets,which were symbiotic with the six different fungi species.Among the six fungi species growing on the optimal medium,the growing rate of XH-A was the fastest,and that of YY001 was the slowest.The growth and physiological indexes of P.dianthum co-cultured with DY1 in DE medium were higher than those in the control group.[Conclusions]DE medium was the optimal tissue culture medium for P.dianthum,and the optimal symbiotic fungus was DY1.
基金supported by grants from the National Natural Science Foundation of China(Nos.32000998,and 32201240)The Young Elite Scientists Sponsorship Program by Henan Association for Science and Technology(No.2022HYTP046)+2 种基金the China Postdoctoral Science Foundation(Nos.2019TQ0285,2019M662513,and 2021TQ0298)Henan provincial Medical Science and Technology Research Project(No.LHGJ20210210)Science and Technology Development Project of Henan Province(Nos.212102310138 and 222102310525).
文摘Chemotherapy remains one of the irreplaceable treatments for cancer therapy.The use of immunogenic cell death(ICD)-inducing chemotherapeutic drugs offers a practical strategy for killing cancer cells,simultaneously eliciting an antitumor immune response by promoting the recruitment of cytotoxic immune cells and production of granzyme B(GrB).However,numerous malignant cancers adaptively acquired the capacity of secreting serpinb9(Sb9),a physiological inhibitor of GrB,which can reversibly inhibit the biological activity of GrB.To circumvent this dilemma,in this study,an integrated tailor-made nanomedicine composed of tumor-targeting peptide(Arg-Gly-Asp,RGD)decorated liposome,doxorubicin(DOX,an effective ICD inducer),and the compound 3034(an inhibitor of Sb9),is developed(termed as D3RL)for breast cancer chemo-immunotherapy.In vitro and in vivo studies show that D3RL can directly kill tumor cells and trigger the host immune response by inducing ICD.Meanwhile,D3RL can competitively relieve the inhibition of Sb9 to GrB.The restored GrB can not only effectively induce tumor immunotherapy,but also degrade matrix components in the tumor microenvironment,consequently improving the infiltration of immune cells and the penetration of nanomedicines,which in return enhance the combined antitumor effect.Taken together,this work develops an integrated therapeutic solution for targeted production and restoration of GrB to achieve a combined chemo-immunotherapy for breast cancer.