Objective:To develop a deep learning model to predict lymph node(LN)status in clinical stage IA lung adeno-carcinoma patients.Methods:This diagnostic study included 1,009 patients with pathologically confirmed clinica...Objective:To develop a deep learning model to predict lymph node(LN)status in clinical stage IA lung adeno-carcinoma patients.Methods:This diagnostic study included 1,009 patients with pathologically confirmed clinical stage T1N0M0 lung adenocarcinoma from two independent datasets(699 from Cancer Hospital of Chinese Academy of Medical Sciences and 310 from PLA General Hospital)between January 2005 and December 2019.The Cancer Hospital dataset was randomly split into a training cohort(559 patients)and a validation cohort(140 patients)to train and tune a deep learning model based on a deep residual network(ResNet).The PLA Hospital dataset was used as a testing cohort to evaluate the generalization ability of the model.Thoracic radiologists manually segmented tumors and interpreted high-resolution computed tomography(HRCT)features for the model.The predictive performance was assessed by area under the curves(AUCs),accuracy,precision,recall,and F1 score.Subgroup analysis was performed to evaluate the potential bias of the study population.Results:A total of 1,009 patients were included in this study;409(40.5%)were male and 600(59.5%)were female.The median age was 57.0 years(inter-quartile range,IQR:50.0-64.0).The deep learning model achieved AUCs of 0.906(95%CI:0.873-0.938)and 0.893(95%CI:0.857-0.930)for predicting pN0 disease in the testing cohort and a non-pure ground glass nodule(non-pGGN)testing cohort,respectively.No significant difference was detected between the testing cohort and the non-pGGN testing cohort(P=0.622).The precisions of this model for predicting pN0 disease were 0.979(95%CI:0.963-0.995)and 0.983(95%CI:0.967-0.998)in the testing cohort and the non-pGGN testing cohort,respectively.The deep learning model achieved AUCs of 0.848(95%CI:0.798-0.898)and 0.831(95%CI:0.776-0.887)for predicting pN2 disease in the testing cohort and the non-pGGN testing cohort,respectively.No significant difference was detected between the testing cohort and the non-pGGN testing cohort(P=0.657).The recalls of this model for predicting pN2 disease were 0.903(95%CI:0.870-0.936)and 0.931(95%CI:0.901-0.961)in the testing cohort and the non-pGGN testing cohort,respectively.Conclusions:The superior performance of the deep learning model will help to target the extension of lymph node dissection and reduce the ineffective lymph node dissection in early-stage lung adenocarcinoma patients.展开更多
Objective： To develop and validate a radiomics prediction model for individualized prediction of perineural invasion（PNI） in colorectal cancer（CRC）.Methods： After computed tomography（CT） radiomics features ext...Objective： To develop and validate a radiomics prediction model for individualized prediction of perineural invasion（PNI） in colorectal cancer（CRC）.Methods： After computed tomography（CT） radiomics features extraction, a radiomics signature was constructed in derivation cohort（346 CRC patients）. A prediction model was developed to integrate the radiomics signature and clinical candidate predictors [age, sex, tumor location, and carcinoembryonic antigen（CEA） level]. Apparent prediction performance was assessed. After internal validation, independent temporal validation（separate from the cohort used to build the model） was then conducted in 217 CRC patients. The final model was converted to an easy-to-use nomogram.Results： The developed radiomics nomogram that integrated the radiomics signature and CEA level showed good calibration and discrimination performance [Harrell＇s concordance index（c-index）： 0.817; 95% confidence interval（95% CI）： 0.811–0.823]. Application of the nomogram in validation cohort gave a comparable calibration and discrimination（c-index： 0.803; 95% CI： 0.794–0.812）.Conclusions： Integrating the radiomics signature and CEA level into a radiomics prediction model enables easy and effective risk assessment of PNI in CRC. This stratification of patients according to their PNI status may provide a basis for individualized auxiliary treatment.展开更多
Although prognostic prediction of nasopharyngeal carcinoma (NPC) remains a pivotal research area, the role of dynamic contrast-enhanced magnetic resonance (DCE-MR) has been less explored. This study aimed to investiga...Although prognostic prediction of nasopharyngeal carcinoma (NPC) remains a pivotal research area, the role of dynamic contrast-enhanced magnetic resonance (DCE-MR) has been less explored. This study aimed to investigate the role of DCR-MR in predicting progression-free survival (PFS) in patients with NPC using magnetic resonance (MR)- and DCE-MR-based radiomic models. A total of 434 patients with two MR scanning sequences were included. The MR- and DCE-MR-based radiomics models were developed based on 289 patients with only MR scanning sequences and 145 patients with four additional pharmacokinetic parameters (volume fraction of extravascular extracellular space (ve), volume fraction of plasma space (vp), volume transfer constant (Ktrans), and reverse reflux rate constant (kep) of DCE-MR. A combined model integrating MR and DCE-MR was constructed. Utilizing methods such as correlation analysis, least absolute shrinkage and selection operator regression, and multivariate Cox proportional hazards regression, we built the radiomics models. Finally, we calculated the net reclassification index and C-index to evaluate and compare the prognostic performance of the radiomics models. Kaplan-Meier survival curve analysis was performed to investigate the model’s ability to stratify risk in patients with NPC. The integration of MR and DCE-MR radiomic features significantly enhanced prognostic prediction performance compared to MR- and DCE-MR-based models, evidenced by a test set C-index of 0.808 vs 0.729 and 0.731, respectively. The combined radiomics model improved net reclassification by 22.9%-52.6% and could significantly stratify the risk levels of patients with NPC (p = 0.036). Furthermore, the MR-based radiomic feature maps achieved similar results to the DCE-MR pharmacokinetic parameters in terms of reflecting the underlying angiogenesis information in NPC. Compared to conventional MR-based radiomics models, the combined radiomics model integrating MR and DCE-MR showed promising results in delivering more accurate prognostic predictions and provided more clinical benefits in quantifying and monitoring phenotypic changes associated with NPC prognosis.展开更多
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 ...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.展开更多
Objective To explore the semi-supervised learning(SSL) algorithm for long-tail endoscopic image classification with limited annotations.Method We explored semi-supervised long-tail endoscopic image classification in H...Objective To explore the semi-supervised learning(SSL) algorithm for long-tail endoscopic image classification with limited annotations.Method We explored semi-supervised long-tail endoscopic image classification in HyperKvasir,the largest gastrointestinal public dataset with 23 diverse classes.Semi-supervised learning algorithm FixMatch was applied based on consistency regularization and pseudo-labeling.After splitting the training dataset and the test dataset at a ratio of 4:1,we sampled 20%,50%,and 100% labeled training data to test the classification with limited annotations.Results The classification performance was evaluated by micro-average and macro-average evaluation metrics,with the Mathews correlation coefficient(MCC) as the overall evaluation.SSL algorithm improved the classification performance,with MCC increasing from 0.8761 to 0.8850,from 0.8983 to 0.8994,and from 0.9075 to 0.9095 with 20%,50%,and 100% ratio of labeled training data,respectively.With a 20% ratio of labeled training data,SSL improved both the micro-average and macro-average classification performance;while for the ratio of 50% and 100%,SSL improved the micro-average performance but hurt macro-average performance.Through analyzing the confusion matrix and labeling bias in each class,we found that the pseudo-based SSL algorithm exacerbated the classifier’ s preference for the head class,resulting in improved performance in the head class and degenerated performance in the tail class.Conclusion SSL can improve the classification performance for semi-supervised long-tail endoscopic image classification,especially when the labeled data is extremely limited,which may benefit the building of assisted diagnosis systems for low-volume hospitals.However,the pseudo-labeling strategy may amplify the effect of class imbalance,which hurts the classification performance for the tail class.展开更多
This study aimed to comprehensively evaluate non-contrast computed tomography(CT)-based radiomics for predicting early outcomes in patients with severe atherosclerotic renal artery stenosis(ARAS)after percutaneous tra...This study aimed to comprehensively evaluate non-contrast computed tomography(CT)-based radiomics for predicting early outcomes in patients with severe atherosclerotic renal artery stenosis(ARAS)after percutaneous transluminal renal angioplasty(PTRA).A total of 52 patients were retrospectively recruited,and their clinical characteristics and pretreatment CT images were collected.During a median follow-up period of 3.7 mo,18 patients were confirmed to have benefited from the treatment,defined as a 20%improvement from baseline in the estimated glomerular filtration rate.A deep learning network trained via self-supervised learning was used to enhance the imaging phenotype characteristics.Radiomics features,comprising 116 handcrafted features and 78 deep learning features,were extracted from the affected renal and perirenal adipose regions.More features from the latter were correlated with early outcomes,as determined by univariate analysis,and were visually represented in radiomics heatmaps and volcano plots.After using consensus clustering and the least absolute shrinkage and selection operator method for feature selection,five machine learning models were evaluated.Logistic regression yielded the highest leave-one-out cross-validation accuracy of 0.780(95%CI:0.660-0.880)for the renal signature,while the support vector machine achieved 0.865(95%CI:0.769-0.942)for the perirenal adipose signature.SHapley Additive exPlanations was used to visually interpret the prediction mechanism,and a histogram feature and a deep learning feature were identified as the most influential factors for the renal signature and perirenal adipose signature,respectively.Multivariate analysis revealed that both signatures served as independent predictive factors.When combined,they achieved an area under the receiver operating characteristic curve of 0.888(95%CI:0.784-0.992),indicating that the imaging phenotypes from both regions complemented each other.In conclusion,non-contrast CT-based radiomics can be leveraged to predict the early outcomes of PTRA,thereby assisting in identifying patients with ARAS suitable for this treatment,with perirenal adipose tissue providing added predictive value.展开更多
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...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.展开更多
The COVID-19 pandemic has dramatically threatened the Gulf Cooperation Council(GCC)countries which have a large proportion of foreign workers.The governments of GCC countries have proactively implemented a com-prehens...The COVID-19 pandemic has dramatically threatened the Gulf Cooperation Council(GCC)countries which have a large proportion of foreign workers.The governments of GCC countries have proactively implemented a com-prehensive set of policy measures,and up to our knowledge,a systematic analysis of qualitative and quantitative evidence on the government response is still lacking.We summarized the GCC countries’government response and quantitatively measured that response using four indexes—the Government Response Index,the Stringency Index,the Vaccine Index,and the Initial Response Index,to analyse their response for future pandemic preparedness.Overall,the government response of all the GCC countries to the COVID-19 pandemic has been comprehensive,stringent,and timely.Notably,the GCC countries have implemented comprehensive vaccine policies.In addition,they have worked actively to protect foreign workers to improve their access to health services and secure their essential living conditions,regardless of their immigrant status.All the GCC countries dynamically adjusted their response to the evolving COVID-19 epidemiological burden and started to relax the stringency of the control poli-cies after the Omicron wave,though the governments had different response magnitudes as measured by the four indexes.These findings have provided several important lessons for future pandemic response and preparedness for countries with similar economic,demographic,and health contexts in(1)prompt actions of containment and clo-sure policies with dynamic adjusting,(2)strengthening health system policies,(3)comprehensive vaccination policies with universal access,(4)equitable and free access to testing,diagnosis,and treatment for all,and(5)strengthening the resilience of health systems.展开更多
Gastric cancer(GC)is one of the most common malignant tumors with high mortality.Accurate diagnosis and treatment decisions for GC rely heavily on human experts’careful judgments on medical images.However,the improve...Gastric cancer(GC)is one of the most common malignant tumors with high mortality.Accurate diagnosis and treatment decisions for GC rely heavily on human experts’careful judgments on medical images.However,the improvement of the accuracy is hindered by imaging conditions,limited experience,objective criteria,and inter-observer discrepancies.Recently,the developments of machine learning,especially deep-learning algorithms,have been facilitating computers to extract more information from data automatically.Researchers are exploring the far-reaching applications of artificial intelligence(AI)in various clinical practices,including GC.Herein,we aim to provide a broad framework to summarize current research on AI in GC.In the screening of GC,AI can identify precancerous diseases and assist in early cancer detection with endoscopic examination and pathological confirmation.In the diagnosis of GC,AI can support tumor-node-metastasis(TNM)staging and subtype classification.For treatment decisions,AI can help with surgical margin determination and prognosis prediction.Meanwhile,current approaches are challenged by data scarcity and poor interpretability.To tackle these problems,more regulated data,unified processing procedures,and advanced algorithms are urgently needed to build more accurate and robust AI models for GC.展开更多
Background:Tuberculosis(TB)prevalence is closely associated with poverty in China,and poor patients face more barriers to treatment.Using an insurance-based approach,the China-Gates TB program Phase II was implemented...Background:Tuberculosis(TB)prevalence is closely associated with poverty in China,and poor patients face more barriers to treatment.Using an insurance-based approach,the China-Gates TB program Phase II was implemented between 2012 and 2014 in three cities in China to improve access to TB care and reduce the financial burden on patients,particularly among the poor.This study aims to assess the program effects on service use,and its equity impact across different income groups.Methods:Data from 788 and 775 patients at baseline and final evaluation were available for analysis respectively.Inpatient and outpatient service utilization,treatment adherence,and patient satisfaction were assessed before and after the program,across different income groups(extreme poverty,moderate poverty and non-poverty),and in various program cities,using descriptive statistics and multi-variate regression models.Key stakeholder interviews were conducted to qualitatively evaluate program implementation and impacts.Results:After program implementation,the hospital admission rate increased more for the extreme poverty group(48.5 to 70.7%)and moderate poverty group(45.0 to 68.1%),compared to the non-poverty group(52.9 to 643%).The largest increase in the number of outpatient visits was also for the extreme poverty group(4.6 to 5.7).The proportion of patients with good medication adherence increased by 15 percentage points in the extreme poverty group and by ten percentage points in the other groups.Satisfaction rates were high in all groups.Qualitative feedback from stakeholders also suggested that increased reimbursement rates,easier reimbursement procedures,and allowance improved patients'service utilization.Implementation of case-based payment made service provision more compliant to clinical pathways.Conclusion:Patients in extreme or moderate poverty benefited more from the program compared to a non-poverty group,indicating improved equity in TB service access.The pro-poor design of the program provides important丨essons to other TB programs in China and other countries to better address TB care for the poor.展开更多
基金supported by the National Key R&D Program of China(grant numbers:2020AAA0109504,2023YFC2415200)CAMS Innovation Fund for Medical Sciences(grant number:2021-I2M-C&T-B-061)+5 种基金Beijing Hope Run Special Fund of Cancer Foundation of China(grant number:LC2022A22)the National Natural Science Foundation of China(grant numbers:81971619,81971580,92259302,82372053,91959205,82361168664,82022036,81971776)Beijing Natural Sci-ence Foundation(grant number:Z20J00105)Key-Area Research and Development Program of Guangdong Province(grant number:2021B0101420005)Strategic Priority Research Program of Chinese Academy of Sciences(grant number:XDB38040200)the Youth In-novation Promotion Association CAS(grant number:Y2021049).
文摘Objective:To develop a deep learning model to predict lymph node(LN)status in clinical stage IA lung adeno-carcinoma patients.Methods:This diagnostic study included 1,009 patients with pathologically confirmed clinical stage T1N0M0 lung adenocarcinoma from two independent datasets(699 from Cancer Hospital of Chinese Academy of Medical Sciences and 310 from PLA General Hospital)between January 2005 and December 2019.The Cancer Hospital dataset was randomly split into a training cohort(559 patients)and a validation cohort(140 patients)to train and tune a deep learning model based on a deep residual network(ResNet).The PLA Hospital dataset was used as a testing cohort to evaluate the generalization ability of the model.Thoracic radiologists manually segmented tumors and interpreted high-resolution computed tomography(HRCT)features for the model.The predictive performance was assessed by area under the curves(AUCs),accuracy,precision,recall,and F1 score.Subgroup analysis was performed to evaluate the potential bias of the study population.Results:A total of 1,009 patients were included in this study;409(40.5%)were male and 600(59.5%)were female.The median age was 57.0 years(inter-quartile range,IQR:50.0-64.0).The deep learning model achieved AUCs of 0.906(95%CI:0.873-0.938)and 0.893(95%CI:0.857-0.930)for predicting pN0 disease in the testing cohort and a non-pure ground glass nodule(non-pGGN)testing cohort,respectively.No significant difference was detected between the testing cohort and the non-pGGN testing cohort(P=0.622).The precisions of this model for predicting pN0 disease were 0.979(95%CI:0.963-0.995)and 0.983(95%CI:0.967-0.998)in the testing cohort and the non-pGGN testing cohort,respectively.The deep learning model achieved AUCs of 0.848(95%CI:0.798-0.898)and 0.831(95%CI:0.776-0.887)for predicting pN2 disease in the testing cohort and the non-pGGN testing cohort,respectively.No significant difference was detected between the testing cohort and the non-pGGN testing cohort(P=0.657).The recalls of this model for predicting pN2 disease were 0.903(95%CI:0.870-0.936)and 0.931(95%CI:0.901-0.961)in the testing cohort and the non-pGGN testing cohort,respectively.Conclusions:The superior performance of the deep learning model will help to target the extension of lymph node dissection and reduce the ineffective lymph node dissection in early-stage lung adenocarcinoma patients.
基金supported by the National Key Research and Development Program of China (No. 2017YFC1309100)the National Natural Scientific Foundation of China (No. 81771912, 81701782 and 81601469)
文摘Objective： To develop and validate a radiomics prediction model for individualized prediction of perineural invasion（PNI） in colorectal cancer（CRC）.Methods： After computed tomography（CT） radiomics features extraction, a radiomics signature was constructed in derivation cohort（346 CRC patients）. A prediction model was developed to integrate the radiomics signature and clinical candidate predictors [age, sex, tumor location, and carcinoembryonic antigen（CEA） level]. Apparent prediction performance was assessed. After internal validation, independent temporal validation（separate from the cohort used to build the model） was then conducted in 217 CRC patients. The final model was converted to an easy-to-use nomogram.Results： The developed radiomics nomogram that integrated the radiomics signature and CEA level showed good calibration and discrimination performance [Harrell＇s concordance index（c-index）： 0.817; 95% confidence interval（95% CI）： 0.811–0.823]. Application of the nomogram in validation cohort gave a comparable calibration and discrimination（c-index： 0.803; 95% CI： 0.794–0.812）.Conclusions： Integrating the radiomics signature and CEA level into a radiomics prediction model enables easy and effective risk assessment of PNI in CRC. This stratification of patients according to their PNI status may provide a basis for individualized auxiliary treatment.
基金the Natural Science Foundation of Hainan Province,No.821MS125the National Key R&D Program of China,No.2023YFC2415200+6 种基金the Key R&D projects in Hainan Province,No.ZDYF-2021SHFZ239the Natural Science Research Project“open competition mechanism”of Hainan Medical College,Nos.JBGS202113 and JBGS202107Strategic Priority Research Program of the Chinese Academy of Sciences,No.XDB 38040200National Natural Science Foundation of China,Nos.82372053,82302296,81871346,81971602,82022036,91959130,81971776,81771924,62027901,81930053Beijing Natural Science Foundation,No.L182061 and Z20J00105Chinese Academy of Sciences,Nos.GJJSTD20170004 and QYZDJ-SSW-JSC005and Youth Innovation Promotion Association CAS,No.2017175.
文摘Although prognostic prediction of nasopharyngeal carcinoma (NPC) remains a pivotal research area, the role of dynamic contrast-enhanced magnetic resonance (DCE-MR) has been less explored. This study aimed to investigate the role of DCR-MR in predicting progression-free survival (PFS) in patients with NPC using magnetic resonance (MR)- and DCE-MR-based radiomic models. A total of 434 patients with two MR scanning sequences were included. The MR- and DCE-MR-based radiomics models were developed based on 289 patients with only MR scanning sequences and 145 patients with four additional pharmacokinetic parameters (volume fraction of extravascular extracellular space (ve), volume fraction of plasma space (vp), volume transfer constant (Ktrans), and reverse reflux rate constant (kep) of DCE-MR. A combined model integrating MR and DCE-MR was constructed. Utilizing methods such as correlation analysis, least absolute shrinkage and selection operator regression, and multivariate Cox proportional hazards regression, we built the radiomics models. Finally, we calculated the net reclassification index and C-index to evaluate and compare the prognostic performance of the radiomics models. Kaplan-Meier survival curve analysis was performed to investigate the model’s ability to stratify risk in patients with NPC. The integration of MR and DCE-MR radiomic features significantly enhanced prognostic prediction performance compared to MR- and DCE-MR-based models, evidenced by a test set C-index of 0.808 vs 0.729 and 0.731, respectively. The combined radiomics model improved net reclassification by 22.9%-52.6% and could significantly stratify the risk levels of patients with NPC (p = 0.036). Furthermore, the MR-based radiomic feature maps achieved similar results to the DCE-MR pharmacokinetic parameters in terms of reflecting the underlying angiogenesis information in NPC. Compared to conventional MR-based radiomics models, the combined radiomics model integrating MR and DCE-MR showed promising results in delivering more accurate prognostic predictions and provided more clinical benefits in quantifying and monitoring phenotypic changes associated with NPC prognosis.
基金supported by the National Key Research and Development Program of China (2017YFA0205200,2023YFC2415200,2021YFF1201003,and 2021YFC2500402)the National Natural Science Foundation of China (82022036,91959130,81971776,62027901,81930053,81771924,62333022,82361168664,62176013,and 82302317)+5 种基金the Beijing Natural Science Foundation (Z20J00105)Strategic Priority Research Program of Chinese Academy of Sciences (XDB38040200)Chinese Academy of Sciences (GJJSTD20170004 and QYZDJ-SSW-JSC005)the Project of High-Level Talents Team Introduction in Zhuhai City (Zhuhai HLHPTP201703)the Youth Innovation Promotion Association CAS (Y2021049)the China Postdoctoral Science Foundation (2021M700341).
文摘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.
文摘Objective To explore the semi-supervised learning(SSL) algorithm for long-tail endoscopic image classification with limited annotations.Method We explored semi-supervised long-tail endoscopic image classification in HyperKvasir,the largest gastrointestinal public dataset with 23 diverse classes.Semi-supervised learning algorithm FixMatch was applied based on consistency regularization and pseudo-labeling.After splitting the training dataset and the test dataset at a ratio of 4:1,we sampled 20%,50%,and 100% labeled training data to test the classification with limited annotations.Results The classification performance was evaluated by micro-average and macro-average evaluation metrics,with the Mathews correlation coefficient(MCC) as the overall evaluation.SSL algorithm improved the classification performance,with MCC increasing from 0.8761 to 0.8850,from 0.8983 to 0.8994,and from 0.9075 to 0.9095 with 20%,50%,and 100% ratio of labeled training data,respectively.With a 20% ratio of labeled training data,SSL improved both the micro-average and macro-average classification performance;while for the ratio of 50% and 100%,SSL improved the micro-average performance but hurt macro-average performance.Through analyzing the confusion matrix and labeling bias in each class,we found that the pseudo-based SSL algorithm exacerbated the classifier’ s preference for the head class,resulting in improved performance in the head class and degenerated performance in the tail class.Conclusion SSL can improve the classification performance for semi-supervised long-tail endoscopic image classification,especially when the labeled data is extremely limited,which may benefit the building of assisted diagnosis systems for low-volume hospitals.However,the pseudo-labeling strategy may amplify the effect of class imbalance,which hurts the classification performance for the tail class.
基金supported by the National Natural Science Foundation of China,Nos.82022036,82372053,91959130,81971776,62027901,81930053,and 82302296the China Postdoctoral Science Foundation,No.2022M720357.
文摘This study aimed to comprehensively evaluate non-contrast computed tomography(CT)-based radiomics for predicting early outcomes in patients with severe atherosclerotic renal artery stenosis(ARAS)after percutaneous transluminal renal angioplasty(PTRA).A total of 52 patients were retrospectively recruited,and their clinical characteristics and pretreatment CT images were collected.During a median follow-up period of 3.7 mo,18 patients were confirmed to have benefited from the treatment,defined as a 20%improvement from baseline in the estimated glomerular filtration rate.A deep learning network trained via self-supervised learning was used to enhance the imaging phenotype characteristics.Radiomics features,comprising 116 handcrafted features and 78 deep learning features,were extracted from the affected renal and perirenal adipose regions.More features from the latter were correlated with early outcomes,as determined by univariate analysis,and were visually represented in radiomics heatmaps and volcano plots.After using consensus clustering and the least absolute shrinkage and selection operator method for feature selection,five machine learning models were evaluated.Logistic regression yielded the highest leave-one-out cross-validation accuracy of 0.780(95%CI:0.660-0.880)for the renal signature,while the support vector machine achieved 0.865(95%CI:0.769-0.942)for the perirenal adipose signature.SHapley Additive exPlanations was used to visually interpret the prediction mechanism,and a histogram feature and a deep learning feature were identified as the most influential factors for the renal signature and perirenal adipose signature,respectively.Multivariate analysis revealed that both signatures served as independent predictive factors.When combined,they achieved an area under the receiver operating characteristic curve of 0.888(95%CI:0.784-0.992),indicating that the imaging phenotypes from both regions complemented each other.In conclusion,non-contrast CT-based radiomics can be leveraged to predict the early outcomes of PTRA,thereby assisting in identifying patients with ARAS suitable for this treatment,with perirenal adipose tissue providing added predictive value.
基金the National Natural Science Foundation of China(82102140,62027901,81930053,82022036,81971776,and 91959205)the Beijing Natural Science Foundation(Z20J00105).
文摘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.
基金funded by the 2022 Reimbursable Advisory Services program(RAS)between the World Bank and the Kingdom of Saudi Arabia(KSA).
文摘The COVID-19 pandemic has dramatically threatened the Gulf Cooperation Council(GCC)countries which have a large proportion of foreign workers.The governments of GCC countries have proactively implemented a com-prehensive set of policy measures,and up to our knowledge,a systematic analysis of qualitative and quantitative evidence on the government response is still lacking.We summarized the GCC countries’government response and quantitatively measured that response using four indexes—the Government Response Index,the Stringency Index,the Vaccine Index,and the Initial Response Index,to analyse their response for future pandemic preparedness.Overall,the government response of all the GCC countries to the COVID-19 pandemic has been comprehensive,stringent,and timely.Notably,the GCC countries have implemented comprehensive vaccine policies.In addition,they have worked actively to protect foreign workers to improve their access to health services and secure their essential living conditions,regardless of their immigrant status.All the GCC countries dynamically adjusted their response to the evolving COVID-19 epidemiological burden and started to relax the stringency of the control poli-cies after the Omicron wave,though the governments had different response magnitudes as measured by the four indexes.These findings have provided several important lessons for future pandemic response and preparedness for countries with similar economic,demographic,and health contexts in(1)prompt actions of containment and clo-sure policies with dynamic adjusting,(2)strengthening health system policies,(3)comprehensive vaccination policies with universal access,(4)equitable and free access to testing,diagnosis,and treatment for all,and(5)strengthening the resilience of health systems.
基金supported by the National Natural Science Foundation of China[grant numbers 82022036,91959130,81971776,62027901,81930053]National Key R&D Program of China[grant number 2017YFA0205200]+2 种基金the Beijing Natural Science Foundation[grant number Z20J00105]Strategic Priority Research Program of Chinese Academy of Sciences[grant number XDB38040200]the Youth Innovation Promotion Association CAS[grant number Y2021049].
文摘Gastric cancer(GC)is one of the most common malignant tumors with high mortality.Accurate diagnosis and treatment decisions for GC rely heavily on human experts’careful judgments on medical images.However,the improvement of the accuracy is hindered by imaging conditions,limited experience,objective criteria,and inter-observer discrepancies.Recently,the developments of machine learning,especially deep-learning algorithms,have been facilitating computers to extract more information from data automatically.Researchers are exploring the far-reaching applications of artificial intelligence(AI)in various clinical practices,including GC.Herein,we aim to provide a broad framework to summarize current research on AI in GC.In the screening of GC,AI can identify precancerous diseases and assist in early cancer detection with endoscopic examination and pathological confirmation.In the diagnosis of GC,AI can support tumor-node-metastasis(TNM)staging and subtype classification.For treatment decisions,AI can help with surgical margin determination and prognosis prediction.Meanwhile,current approaches are challenged by data scarcity and poor interpretability.To tackle these problems,more regulated data,unified processing procedures,and advanced algorithms are urgently needed to build more accurate and robust AI models for GC.
文摘Background:Tuberculosis(TB)prevalence is closely associated with poverty in China,and poor patients face more barriers to treatment.Using an insurance-based approach,the China-Gates TB program Phase II was implemented between 2012 and 2014 in three cities in China to improve access to TB care and reduce the financial burden on patients,particularly among the poor.This study aims to assess the program effects on service use,and its equity impact across different income groups.Methods:Data from 788 and 775 patients at baseline and final evaluation were available for analysis respectively.Inpatient and outpatient service utilization,treatment adherence,and patient satisfaction were assessed before and after the program,across different income groups(extreme poverty,moderate poverty and non-poverty),and in various program cities,using descriptive statistics and multi-variate regression models.Key stakeholder interviews were conducted to qualitatively evaluate program implementation and impacts.Results:After program implementation,the hospital admission rate increased more for the extreme poverty group(48.5 to 70.7%)and moderate poverty group(45.0 to 68.1%),compared to the non-poverty group(52.9 to 643%).The largest increase in the number of outpatient visits was also for the extreme poverty group(4.6 to 5.7).The proportion of patients with good medication adherence increased by 15 percentage points in the extreme poverty group and by ten percentage points in the other groups.Satisfaction rates were high in all groups.Qualitative feedback from stakeholders also suggested that increased reimbursement rates,easier reimbursement procedures,and allowance improved patients'service utilization.Implementation of case-based payment made service provision more compliant to clinical pathways.Conclusion:Patients in extreme or moderate poverty benefited more from the program compared to a non-poverty group,indicating improved equity in TB service access.The pro-poor design of the program provides important丨essons to other TB programs in China and other countries to better address TB care for the poor.
