Odontogenic maxillary sinusitis (OMS) is a subtype of maxillary sinusitis (MS). It is actually inflammation of the maxillary sinus that secondary to adjacent infectious maxillary dental lesion. Due to the lack of uniq...Odontogenic maxillary sinusitis (OMS) is a subtype of maxillary sinusitis (MS). It is actually inflammation of the maxillary sinus that secondary to adjacent infectious maxillary dental lesion. Due to the lack of unique clinical features, OMS is difficult to distinguish from other types of rhinosinusitis. Besides, the characteristic infectious pathogeny of OMS makes it is resistant to conventional therapies of rhinosinusitis. Its current diagnosis and treatment are thus facing great difficulties. The multi-disciplinary cooperation between otolaryngologists and dentists is absolutely urgent to settle these questions and to acquire standardized diagnostic and treatment regimen for OMS. However, this disease has actually received little attention and has been underrepresented by relatively low publication volume and quality. Based on systematically reviewed literature and practical experiences of expert members, our consensus focuses on characteristics, symptoms, classification and diagnosis of OMS, and further put forward multidisciplinary treatment decisions for OMS, as well as the common treatment complications and relative managements. This consensus aims to increase attention to OMS, and optimize the clinical diagnosis and decision-making of OMS, which finally provides evidence-based options for OMS clinical management.展开更多
Amide proton transfer (APT) magnetic resonance imaging (MRI) is an important molecularimaging technique at the protein level in tissue. Neurodegenerative diseases have a highlikelihood of causing abnormal protein accu...Amide proton transfer (APT) magnetic resonance imaging (MRI) is an important molecularimaging technique at the protein level in tissue. Neurodegenerative diseases have a highlikelihood of causing abnormal protein accumulation in the brain, which can be detectedby APT MRI. This article briefly introduces the principles and image processing technologyof APT MRI, and reviews the current state of research on Alzheimer's disease and Parkinson's disease using this technique. Early applications of this approach in these twoneurodegenerative diseases are encouraging, which also suggests continued technicaldevelopment and larger clinical trials to gauge the value of this technique.展开更多
Efforts to control inflammation and achieve better tissue repair in the treatment of periodontitis have been ongoing for years.Humanβ-defensin 3,a broad-spectrum antimicrobial peptide has been proven to have a variet...Efforts to control inflammation and achieve better tissue repair in the treatment of periodontitis have been ongoing for years.Humanβ-defensin 3,a broad-spectrum antimicrobial peptide has been proven to have a variety of biological functions in periodontitis;however,relatively few reports have addressed the effects of human periodontal ligament cells(h PDLCs)on osteogenic differentiation.In this study,we evaluated the osteogenic effects of h PDLCs with an adenoviral vector encoding humanβ-defensin 3 in an inflammatory microenvironment.Then humanβ-defensin 3 gene-modified rat periodontal ligament cells were transplanted into rats with experimental periodontitis to observe their effects on periodontal bone repair.We found that the humanβ-defensin 3 gene-modified h PDLCs presented with high levels of osteogenesis-related gene expression and calcium deposition.Furthermore,the p38 MAPK pathway was activated in this process.In vivo,humanβ-defensin 3 gene-transfected rat PDLCs promoted bone repair in SD rats with periodontitis,and the p38 mitogen-activated protein kinase(MAPK)pathway might also have been involved.These findings demonstrate that humanβ-defensin 3 accelerates osteogenesis and that humanβ-defensin 3 gene modification may offer a potential approach to promote bone repair in patients with periodontitis.展开更多
The aim of this study was to identify whether periodontitis induces gut microbiota dysbiosis via invasion by salivary microbes.First,faecal and salivary samples were collected from periodontally healthy participants(P...The aim of this study was to identify whether periodontitis induces gut microbiota dysbiosis via invasion by salivary microbes.First,faecal and salivary samples were collected from periodontally healthy participants(PH group,n=16)and patients with severe periodontitis(SP group,n=21)and analysed by 16S ribosomal RNA sequencing.Significant differences were observed in both the faecal and salivary microbiota between the PH and SP groups.Notably,more saliva-sourced microbes were observed in the faecal samples of the SP group.Then,the remaining salivary microbes were transplanted into C57BL6/J mice(the C-PH group and the C-SP group),and it was found that the composition of the gut microbiota of the C-SP group was significantly different from that of the C-PH group,with Porphyromonadaceae and Fusobacterium being significantly enriched in the C-SP group.In the colon,the C-SP group showed significantly reduced crypt depth and zonula occludens-1 expression.The m RNA expression levels of pro-inflammatory cytokines,chemokines and tight junction proteins were significantly higher in the C-SP group.To further investigate whether salivary bacteria could persist in the intestine,the salivary microbiota was stained with carboxyfluorescein diacetate succinimidyl ester and transplanted into mice.We found that salivary microbes from both the PH group and the SP group could persist in the gut for at least 24 h.Thus,our data demonstrate that periodontitis may induce gut microbiota dysbiosis through the influx of salivary microbes.展开更多
Shrinkage porosity is a type of random distribution defects and exists in most large castings. Different from the periodic symmetry defects or certain distribution defects, shrinkage porosity presents a random "c...Shrinkage porosity is a type of random distribution defects and exists in most large castings. Different from the periodic symmetry defects or certain distribution defects, shrinkage porosity presents a random "cloud-like" configuration, which brings difficulties in quantifying the effective performance of defected casting. In this paper, the influences of random shrinkage porosity on the equivalent elastic modulus of QT400-18 casting were studied by a numerical statistics approach. An improved random algorithm was applied into the lattice model to simulate the "cloud-like" morphology of shrinkage porosity. Then, a large number of numerical samples containing random levels of shrinkage were generated by the proposed algorithm. The stress concentration factor and equivalent elastic modulus of these numerical samples were calculated. Based on a statistical approach, the effects of shrinkage porosity's distribution characteristics, such as area fraction, shape, and relative location on the casting's equivalent mechanical properties were discussed respectively. It is shown that the approach with randomly distributed defects has better predictive capabilities than traditional methods. The following conclusions can be drawn from the statistical simulations:(1) the effective modulus decreases remarkably if the shrinkage porosity percent is greater than 1.5%;(2) the average Stress Concentration Factor(SCF) produced by shrinkage porosity is about 2.0;(3) the defect's length across the loading direction plays a more important role in the effective modulus than the length along the loading direction;(4) the surface defect perpendicular to loading direction reduces the mean modulus about 1.5% more than a defect of other position.展开更多
Background and Aims:Hepatocellular carcinoma(HCC)is the most common primary hepatic malignancy.This study was designed to investigate the value of computed tomography(CT)spectral imaging in differentiating HCC from he...Background and Aims:Hepatocellular carcinoma(HCC)is the most common primary hepatic malignancy.This study was designed to investigate the value of computed tomography(CT)spectral imaging in differentiating HCC from hepatic hemangioma(HH)and focal nodular hyperplasia(FNH).Methods:This was a retrospective study of 51 patients who underwent spectral multiple-phase CT at 40–140 keV during the arterial phase(AP)and portal venous phase(PP).Slopes of the spectral curves,iodine density,water density derived from iodine-and water-based material decomposition images,iodine uptake ratio(IUR),normalized iodine concentration,and the ratio of iodine concentration in liver lesions between AP and PP were measured or calculated.Results:As energy level decreased,the CT values of HCC(n=31),HH(n=17),and FNH(n=7)increased in both AP and PP.There were significant differences in IUR in the AP,IUR in the PP,normalized iodine concentration in the AP,slope in the AP,and slope in the PP among HCC,HH,and FNH.The CT values in AP,IUR in the AP and PP,normalized iodine concentration in the AP,slope in the AP and PP had high sensitivity and specificity in differentiating HH and HCC from FNH.Quantitative CT spectral data had higher sensitivity and specificity than conventional qualitative CT image analysis during the combined phases.Conclusions:Mean CT values at low energy(40–90 keV)and quantitative analysis of CT spectral data(IUR in the AP)could be helpful in the differentiation of HCC,HH,and FNH.展开更多
Gold nanoparticles(AuNPs)with surface-anchored molecules present tremendous potential in tissue regeneration.However,little is known about chiral-modified AuNPs.In this study,we successfully prepared L/D-cysteine-anch...Gold nanoparticles(AuNPs)with surface-anchored molecules present tremendous potential in tissue regeneration.However,little is known about chiral-modified AuNPs.In this study,we successfully prepared L/D-cysteine-anchored AuNPs(L/D-Cys-AuNPs)and studied the effects of chiral-modified AuNPs on osteogenic differentiation and autophagy of human periodontal ligament cells(hPDLCs)and periodontal tissue regeneration.In vitro,more L-Cys-AuNPs than D-Cys-AuNPs tend to internalize in hPDLCs.L-Cys-AuNPs also significantly increased the expression of alkaline phosphatase,collagen type 1,osteocalcin,runt-related transcription factor 2,and microtubule-associated protein light chain 3 II and decreased the expression of sequestosome 1 in hPDLCs compared to the expression levels in the hPDLCs treated by D-Cys-AuNPs.In vivo tests in a rat periodontal-defect model showed that L-Cys-AuNPs had the greatest effect on periodontal-tissue regeneration.The activation of autophagy in L-Cys-AuNP-treated hPDLCs may be responsible for the cell differentiation and tissue regeneration.Therefore,compared to D-Cys-AuNPs,L-Cys-AuNPs show a better performance in cellular internalization,regulation of autophagy,cell osteogenic differentiation,and periodontal tissue regeneration.This demonstrates the immense potential of L-Cys-AuNPs for periodontal regeneration and provides a new insight into chirally modified bioactive nanomaterials.展开更多
Measurement the viscoelastic properties is important for studying the developmental and pathological behavior of soft biological tissues.Magnetic resonance elastography(MRE)is a non-invasive method for in vivo measure...Measurement the viscoelastic properties is important for studying the developmental and pathological behavior of soft biological tissues.Magnetic resonance elastography(MRE)is a non-invasive method for in vivo measurement of tissue viscoelasticity.As a flexible method capable of testing small samples,indentation has been widely used for characterizing soft tissues.Using 2nd-order Prony series and dimensional analysis,we analyzed and compared the model parameters estimated from both indentation and MRE.Conversions of the model parameters estimated from the two methods were established.We found that the indention test is better at capturing the dynamic response of tissues at a frequency less than 10 Hz,while MRE is better for describing the frequency responses at a relatively higher range.The results provided helpful information for testing soft tissues using indentation and MRE.The models analyzed are also helpful for quantifying the frequency response of viscoelastic tissues.展开更多
Background and Aims:Liver stiffness(LS)measured by shear wave elastography(SWE)is often influenced by hepat-ic inflammation.The aim was to develop a dual-task convo-lutional neural network(DtCNN)model for the simultan...Background and Aims:Liver stiffness(LS)measured by shear wave elastography(SWE)is often influenced by hepat-ic inflammation.The aim was to develop a dual-task convo-lutional neural network(DtCNN)model for the simultaneous staging of liver fibrosis and inflammation activity using 2D-SWE.Methods:A total of 532 patients with chronic hepatitis B(CHB)were included to develop and validate the DtCNN model.An additional 180 consecutive patients between De-cember 2019 and April 2021 were prospectively included for further validation.All patients underwent 2D-SWE examina-tion and serum biomarker assessment.A DtCNN model con-taining two pathways for the staging of fibrosis and inflam-mation was used to improve the classification of significant fibrosis(≥F2),advanced fibrosis(≥F3)as well as cirrhosis(F4).Results:Both fibrosis and inflammation affected LS measurements by 2D-SWE.The proposed DtCNN performed the best among all the classification models for fibrosis stage[significant fibrosis AUC=0.89(95%CI:0.87-0.92),ad-vanced fibrosis AUC=0.87(95%CI:0.84-0.90),liver cirrho-sis AUC=0.85(95%CI:0.81-0.89)].The DtCNN-based pre-diction of inflammation activity achieved AUCs of 0.82(95%CI:0.78-0.86)for grade≥A1,0.88(95%CI:0.85-0.90)grade≥A2 and 0.78(95%CI:0.75-0.81)for grade≥A3,which were significantly higher than the AUCs of the single-task groups.Similar findings were observed in the prospec-tive study.Conclusions:The proposed DtCNN improved di-agnostic performance compared with existing fibrosis staging models by including inflammation in the model,which sup-ports its potential clinical application.展开更多
In recent years,with the development of artificial intelligence,especially deep learning technology,researches on automatic detection of cerebrovascular diseases on medical images have made tremendous progress and the...In recent years,with the development of artificial intelligence,especially deep learning technology,researches on automatic detection of cerebrovascular diseases on medical images have made tremendous progress and these models are gradually entering into clinical practice.However,because of the complexity and flexibility of the deep learning algorithms,these researches have great variability on model building,validation process,performance description and results interpretation.The lack of a reliable,consistent,standardized design protocol has,to a certain extent,affected the progress of clinical translation and technology development of computer aided detection systems.After reviewing a large number of literatures and extensive discussion with domestic experts,this position paper put forward recommendations of standardized design on the key steps of deep learning-based automatic image detection models for cerebrovascular diseases.With further research and application expansion,this position paper would continue to be updated and gradually extended to evaluate the generalizability and clinical application efficacy of such tools.展开更多
基金project was supported by grants from National Natural Science Foundations of China (Nos. 82025010, 81630023, 81900917)Changjiang Scholars and Innovative Research Team (No. IRT13082)+4 种基金CAMS Innovation Fund for Medical Sciences (No. 2019-I2M-5-022)Beijing Municipal Science and Technology Commision (Nos. Z181100001618002, Z211100002921057)Capital’s Funds for Health Improvement and Research (No.CFH2022-1-1091)Beijing Municipal Administration of Hospitals’ Mission Project (No. SML20150203)Beijing Municipal Administration of Hospitals’ Dengfeng Project (No. DFL20190202)。
文摘Odontogenic maxillary sinusitis (OMS) is a subtype of maxillary sinusitis (MS). It is actually inflammation of the maxillary sinus that secondary to adjacent infectious maxillary dental lesion. Due to the lack of unique clinical features, OMS is difficult to distinguish from other types of rhinosinusitis. Besides, the characteristic infectious pathogeny of OMS makes it is resistant to conventional therapies of rhinosinusitis. Its current diagnosis and treatment are thus facing great difficulties. The multi-disciplinary cooperation between otolaryngologists and dentists is absolutely urgent to settle these questions and to acquire standardized diagnostic and treatment regimen for OMS. However, this disease has actually received little attention and has been underrepresented by relatively low publication volume and quality. Based on systematically reviewed literature and practical experiences of expert members, our consensus focuses on characteristics, symptoms, classification and diagnosis of OMS, and further put forward multidisciplinary treatment decisions for OMS, as well as the common treatment complications and relative managements. This consensus aims to increase attention to OMS, and optimize the clinical diagnosis and decision-making of OMS, which finally provides evidence-based options for OMS clinical management.
文摘Amide proton transfer (APT) magnetic resonance imaging (MRI) is an important molecularimaging technique at the protein level in tissue. Neurodegenerative diseases have a highlikelihood of causing abnormal protein accumulation in the brain, which can be detectedby APT MRI. This article briefly introduces the principles and image processing technologyof APT MRI, and reviews the current state of research on Alzheimer's disease and Parkinson's disease using this technique. Early applications of this approach in these twoneurodegenerative diseases are encouraging, which also suggests continued technicaldevelopment and larger clinical trials to gauge the value of this technique.
基金supported by the National Natural Science Foundation Project(No.81771078 and No.81570982)Jiangsu Provincial Medical Innovation Team(No.CXTDB2017014)the Nanjing Clinical Research Center for Oral Diseases(No.2019060009)。
文摘Efforts to control inflammation and achieve better tissue repair in the treatment of periodontitis have been ongoing for years.Humanβ-defensin 3,a broad-spectrum antimicrobial peptide has been proven to have a variety of biological functions in periodontitis;however,relatively few reports have addressed the effects of human periodontal ligament cells(h PDLCs)on osteogenic differentiation.In this study,we evaluated the osteogenic effects of h PDLCs with an adenoviral vector encoding humanβ-defensin 3 in an inflammatory microenvironment.Then humanβ-defensin 3 gene-modified rat periodontal ligament cells were transplanted into rats with experimental periodontitis to observe their effects on periodontal bone repair.We found that the humanβ-defensin 3 gene-modified h PDLCs presented with high levels of osteogenesis-related gene expression and calcium deposition.Furthermore,the p38 MAPK pathway was activated in this process.In vivo,humanβ-defensin 3 gene-transfected rat PDLCs promoted bone repair in SD rats with periodontitis,and the p38 mitogen-activated protein kinase(MAPK)pathway might also have been involved.These findings demonstrate that humanβ-defensin 3 accelerates osteogenesis and that humanβ-defensin 3 gene modification may offer a potential approach to promote bone repair in patients with periodontitis.
基金supported by the National Science Foundation of China(No.81970939)the Nanjing Clinical Research Center for Oral Diseases(No.2019060009)。
文摘The aim of this study was to identify whether periodontitis induces gut microbiota dysbiosis via invasion by salivary microbes.First,faecal and salivary samples were collected from periodontally healthy participants(PH group,n=16)and patients with severe periodontitis(SP group,n=21)and analysed by 16S ribosomal RNA sequencing.Significant differences were observed in both the faecal and salivary microbiota between the PH and SP groups.Notably,more saliva-sourced microbes were observed in the faecal samples of the SP group.Then,the remaining salivary microbes were transplanted into C57BL6/J mice(the C-PH group and the C-SP group),and it was found that the composition of the gut microbiota of the C-SP group was significantly different from that of the C-PH group,with Porphyromonadaceae and Fusobacterium being significantly enriched in the C-SP group.In the colon,the C-SP group showed significantly reduced crypt depth and zonula occludens-1 expression.The m RNA expression levels of pro-inflammatory cytokines,chemokines and tight junction proteins were significantly higher in the C-SP group.To further investigate whether salivary bacteria could persist in the intestine,the salivary microbiota was stained with carboxyfluorescein diacetate succinimidyl ester and transplanted into mice.We found that salivary microbes from both the PH group and the SP group could persist in the gut for at least 24 h.Thus,our data demonstrate that periodontitis may induce gut microbiota dysbiosis through the influx of salivary microbes.
基金supported by the National Natural Science Foundation of China(Grant No.51305350)the Basic Research Foundation of NWPU(No.3102014JCQ01045)
文摘Shrinkage porosity is a type of random distribution defects and exists in most large castings. Different from the periodic symmetry defects or certain distribution defects, shrinkage porosity presents a random "cloud-like" configuration, which brings difficulties in quantifying the effective performance of defected casting. In this paper, the influences of random shrinkage porosity on the equivalent elastic modulus of QT400-18 casting were studied by a numerical statistics approach. An improved random algorithm was applied into the lattice model to simulate the "cloud-like" morphology of shrinkage porosity. Then, a large number of numerical samples containing random levels of shrinkage were generated by the proposed algorithm. The stress concentration factor and equivalent elastic modulus of these numerical samples were calculated. Based on a statistical approach, the effects of shrinkage porosity's distribution characteristics, such as area fraction, shape, and relative location on the casting's equivalent mechanical properties were discussed respectively. It is shown that the approach with randomly distributed defects has better predictive capabilities than traditional methods. The following conclusions can be drawn from the statistical simulations:(1) the effective modulus decreases remarkably if the shrinkage porosity percent is greater than 1.5%;(2) the average Stress Concentration Factor(SCF) produced by shrinkage porosity is about 2.0;(3) the defect's length across the loading direction plays a more important role in the effective modulus than the length along the loading direction;(4) the surface defect perpendicular to loading direction reduces the mean modulus about 1.5% more than a defect of other position.
基金This work was supported by the National Natural Science Foundation of China(Grant number 81401406)the Innovative Research Team of High-Level Local Universities in Shanghai.
文摘Background and Aims:Hepatocellular carcinoma(HCC)is the most common primary hepatic malignancy.This study was designed to investigate the value of computed tomography(CT)spectral imaging in differentiating HCC from hepatic hemangioma(HH)and focal nodular hyperplasia(FNH).Methods:This was a retrospective study of 51 patients who underwent spectral multiple-phase CT at 40–140 keV during the arterial phase(AP)and portal venous phase(PP).Slopes of the spectral curves,iodine density,water density derived from iodine-and water-based material decomposition images,iodine uptake ratio(IUR),normalized iodine concentration,and the ratio of iodine concentration in liver lesions between AP and PP were measured or calculated.Results:As energy level decreased,the CT values of HCC(n=31),HH(n=17),and FNH(n=7)increased in both AP and PP.There were significant differences in IUR in the AP,IUR in the PP,normalized iodine concentration in the AP,slope in the AP,and slope in the PP among HCC,HH,and FNH.The CT values in AP,IUR in the AP and PP,normalized iodine concentration in the AP,slope in the AP and PP had high sensitivity and specificity in differentiating HH and HCC from FNH.Quantitative CT spectral data had higher sensitivity and specificity than conventional qualitative CT image analysis during the combined phases.Conclusions:Mean CT values at low energy(40–90 keV)and quantitative analysis of CT spectral data(IUR in the AP)could be helpful in the differentiation of HCC,HH,and FNH.
基金This work was supported by The National Natural Science Foundation Project[grant numbers 81771078,81570982,21675074,21675075]Jiangsu Provincial Medical Innovation Team,The Project of Invigorating Health Care through Science,Technology and Education[grant number CXTDB2017014]+1 种基金the Nanjing Clinical Research Center for Oral Diseases[grant number 2019060009]The Natural Science Foundation of Shandong Province(ZR2018ZC0231).
文摘Gold nanoparticles(AuNPs)with surface-anchored molecules present tremendous potential in tissue regeneration.However,little is known about chiral-modified AuNPs.In this study,we successfully prepared L/D-cysteine-anchored AuNPs(L/D-Cys-AuNPs)and studied the effects of chiral-modified AuNPs on osteogenic differentiation and autophagy of human periodontal ligament cells(hPDLCs)and periodontal tissue regeneration.In vitro,more L-Cys-AuNPs than D-Cys-AuNPs tend to internalize in hPDLCs.L-Cys-AuNPs also significantly increased the expression of alkaline phosphatase,collagen type 1,osteocalcin,runt-related transcription factor 2,and microtubule-associated protein light chain 3 II and decreased the expression of sequestosome 1 in hPDLCs compared to the expression levels in the hPDLCs treated by D-Cys-AuNPs.In vivo tests in a rat periodontal-defect model showed that L-Cys-AuNPs had the greatest effect on periodontal-tissue regeneration.The activation of autophagy in L-Cys-AuNP-treated hPDLCs may be responsible for the cell differentiation and tissue regeneration.Therefore,compared to D-Cys-AuNPs,L-Cys-AuNPs show a better performance in cellular internalization,regulation of autophagy,cell osteogenic differentiation,and periodontal tissue regeneration.This demonstrates the immense potential of L-Cys-AuNPs for periodontal regeneration and provides a new insight into chirally modified bioactive nanomaterials.
基金This work was supported by the National Natural Science Foundation of China(Grant 31870941)Shanghai Science and Technology Committee(Grant 1944190700).
文摘Measurement the viscoelastic properties is important for studying the developmental and pathological behavior of soft biological tissues.Magnetic resonance elastography(MRE)is a non-invasive method for in vivo measurement of tissue viscoelasticity.As a flexible method capable of testing small samples,indentation has been widely used for characterizing soft tissues.Using 2nd-order Prony series and dimensional analysis,we analyzed and compared the model parameters estimated from both indentation and MRE.Conversions of the model parameters estimated from the two methods were established.We found that the indention test is better at capturing the dynamic response of tissues at a frequency less than 10 Hz,while MRE is better for describing the frequency responses at a relatively higher range.The results provided helpful information for testing soft tissues using indentation and MRE.The models analyzed are also helpful for quantifying the frequency response of viscoelastic tissues.
基金the National Natural Science Foundation of China(No.62001120)the Shanghai Sail-ing Program(No.20YF1402400).
文摘Background and Aims:Liver stiffness(LS)measured by shear wave elastography(SWE)is often influenced by hepat-ic inflammation.The aim was to develop a dual-task convo-lutional neural network(DtCNN)model for the simultaneous staging of liver fibrosis and inflammation activity using 2D-SWE.Methods:A total of 532 patients with chronic hepatitis B(CHB)were included to develop and validate the DtCNN model.An additional 180 consecutive patients between De-cember 2019 and April 2021 were prospectively included for further validation.All patients underwent 2D-SWE examina-tion and serum biomarker assessment.A DtCNN model con-taining two pathways for the staging of fibrosis and inflam-mation was used to improve the classification of significant fibrosis(≥F2),advanced fibrosis(≥F3)as well as cirrhosis(F4).Results:Both fibrosis and inflammation affected LS measurements by 2D-SWE.The proposed DtCNN performed the best among all the classification models for fibrosis stage[significant fibrosis AUC=0.89(95%CI:0.87-0.92),ad-vanced fibrosis AUC=0.87(95%CI:0.84-0.90),liver cirrho-sis AUC=0.85(95%CI:0.81-0.89)].The DtCNN-based pre-diction of inflammation activity achieved AUCs of 0.82(95%CI:0.78-0.86)for grade≥A1,0.88(95%CI:0.85-0.90)grade≥A2 and 0.78(95%CI:0.75-0.81)for grade≥A3,which were significantly higher than the AUCs of the single-task groups.Similar findings were observed in the prospec-tive study.Conclusions:The proposed DtCNN improved di-agnostic performance compared with existing fibrosis staging models by including inflammation in the model,which sup-ports its potential clinical application.
基金Project supported by the Key Program of the National Natural Sci-ence Foundation of China(Grant Nos.81830057 and 82230068)the Young Scientists Fund of the National Natural Science Foundation of China(Grant No.82102155).
文摘In recent years,with the development of artificial intelligence,especially deep learning technology,researches on automatic detection of cerebrovascular diseases on medical images have made tremendous progress and these models are gradually entering into clinical practice.However,because of the complexity and flexibility of the deep learning algorithms,these researches have great variability on model building,validation process,performance description and results interpretation.The lack of a reliable,consistent,standardized design protocol has,to a certain extent,affected the progress of clinical translation and technology development of computer aided detection systems.After reviewing a large number of literatures and extensive discussion with domestic experts,this position paper put forward recommendations of standardized design on the key steps of deep learning-based automatic image detection models for cerebrovascular diseases.With further research and application expansion,this position paper would continue to be updated and gradually extended to evaluate the generalizability and clinical application efficacy of such tools.