Objective:Early predicting response before neoadjuvant chemotherapy(NAC)is crucial for personalized treatment plans for locally advanced breast cancer patients.We aim to develop a multi-task model using multiscale who...Objective:Early predicting response before neoadjuvant chemotherapy(NAC)is crucial for personalized treatment plans for locally advanced breast cancer patients.We aim to develop a multi-task model using multiscale whole slide images(WSIs)features to predict the response to breast cancer NAC more finely.Methods:This work collected 1,670 whole slide images for training and validation sets,internal testing sets,external testing sets,and prospective testing sets of the weakly-supervised deep learning-based multi-task model(DLMM)in predicting treatment response and pCR to NAC.Our approach models two-by-two feature interactions across scales by employing concatenate fusion of single-scale feature representations,and controls the expressiveness of each representation via a gating-based attention mechanism.Results:In the retrospective analysis,DLMM exhibited excellent predictive performance for the prediction of treatment response,with area under the receiver operating characteristic curves(AUCs)of 0.869[95%confidence interval(95%CI):0.806−0.933]in the internal testing set and 0.841(95%CI:0.814−0.867)in the external testing sets.For the pCR prediction task,DLMM reached AUCs of 0.865(95%CI:0.763−0.964)in the internal testing and 0.821(95%CI:0.763−0.878)in the pooled external testing set.In the prospective testing study,DLMM also demonstrated favorable predictive performance,with AUCs of 0.829(95%CI:0.754−0.903)and 0.821(95%CI:0.692−0.949)in treatment response and pCR prediction,respectively.DLMM significantly outperformed the baseline models in all testing sets(P<0.05).Heatmaps were employed to interpret the decision-making basis of the model.Furthermore,it was discovered that high DLMM scores were associated with immune-related pathways and cells in the microenvironment during biological basis exploration.Conclusions:The DLMM represents a valuable tool that aids clinicians in selecting personalized treatment strategies for breast cancer patients.展开更多
Objective: Accurate detection and classification of breast lesions in early stage is crucial to timely formulate effective treatments for patients. We aim to develop a fully automatic system to detect and classify bre...Objective: Accurate detection and classification of breast lesions in early stage is crucial to timely formulate effective treatments for patients. We aim to develop a fully automatic system to detect and classify breast lesions using multiple contrast-enhanced mammography(CEM) images.Methods: In this study, a total of 1,903 females who underwent CEM examination from three hospitals were enrolled as the training set, internal testing set, pooled external testing set and prospective testing set. Here we developed a CEM-based multiprocess detection and classification system(MDCS) to perform the task of detection and classification of breast lesions. In this system, we introduced an innovative auxiliary feature fusion(AFF)algorithm that could intelligently incorporates multiple types of information from CEM images. The average freeresponse receiver operating characteristic score(AFROC-Score) was presented to validate system’s detection performance, and the performance of classification was evaluated by area under the receiver operating characteristic curve(AUC). Furthermore, we assessed the diagnostic value of MDCS through visual analysis of disputed cases,comparing its performance and efficiency with that of radiologists and exploring whether it could augment radiologists’ performance.Results: On the pooled external and prospective testing sets, MDCS always maintained a high standalone performance, with AFROC-Scores of 0.953 and 0.963 for detection task, and AUCs for classification were 0.909[95% confidence interval(95% CI): 0.822-0.996] and 0.912(95% CI: 0.840-0.985), respectively. It also achieved higher sensitivity than all senior radiologists and higher specificity than all junior radiologists on pooled external and prospective testing sets. Moreover, MDCS performed superior diagnostic efficiency with an average reading time of 5 seconds, compared to the radiologists’ average reading time of 3.2 min. The average performance of all radiologists was also improved to varying degrees with MDCS assistance.Conclusions: MDCS demonstrated excellent performance in the detection and classification of breast lesions,and greatly enhanced the overall performance of radiologists.展开更多
Objective:The assessment of lateral lymph node metastasis(LLNM)in patients with papillary thyroid carcinoma(PTC)holds great significance.This study aims to develop and evaluate a deep learning-based automatic pipeline...Objective:The assessment of lateral lymph node metastasis(LLNM)in patients with papillary thyroid carcinoma(PTC)holds great significance.This study aims to develop and evaluate a deep learning-based automatic pipeline system(DLAPS)for diagnosing LLNM in PTC using computed tomography(CT).Methods:A total of 1,266 lateral lymph nodes(LLNs)from 519 PTC patients who underwent CT examinations from January 2019 to November 2022 were included and divided into training and validation set,internal test set,pooled external test set,and prospective test set.The DLAPS consists of an auto-segmentation network based on RefineNet model and a classification network based on ensemble model(ResNet,Xception,and DenseNet).The performance of the DLAPS was compared with that of manually segmented DL models,the clinical model,and Node Reporting and Data System(Node-RADS).The improvement of radiologists’diagnostic performance under the DLAPS-assisted strategy was explored.In addition,bulk RNA-sequencing was conducted based on 12 LLNs to reveal the underlying biological basis of the DLAPS.Results:The DLAPS yielded good performance with area under the receiver operating characteristic curve(AUC)of 0.872,0.910,and 0.822 in the internal,pooled external,and prospective test sets,respectively.The DLAPS significantly outperformed clinical models(AUC 0.731,P<0.001)and Node-RADS(AUC 0.602,P<0.001)in the internal test set.Moreover,the performance of the DLAPS was comparable to that of the manually segmented deep learning(DL)model with AUCs ranging 0.814−0.901 in three test sets.Furthermore,the DLAPSassisted strategy improved the performance of radiologists and enhanced inter-observer consistency.In clinical situations,the rate of unnecessary LLN dissection decreased from 33.33%to 7.32%.Furthermore,the DLAPS was associated with the cell-cell conjunction in the microenvironment.Conclusions:Using CT images from PTC patients,the DLAPS could effectively segment and classify LLNs non-invasively,and this system had a good generalization ability and clinical applicability.展开更多
With the depletion of fossil fuel and climate change,multi-energy systems have attracted widespread attention in buildings.Multi-energy systems,fuelled by renewable energy,including solar and biomass energy,are gain-i...With the depletion of fossil fuel and climate change,multi-energy systems have attracted widespread attention in buildings.Multi-energy systems,fuelled by renewable energy,including solar and biomass energy,are gain-ing increasing adoption in commercial buildings.Most of previous capacity design approaches are formulated based upon conventional operating schedules,which result in inappropriate design capacities and ineffective operating schedules of the multi-energy system.Therefore,a two-stage capacity optimization approach is pro-posed for the multi-energy system with its optimal operating schedule taken into consideration.To demonstrate the effectiveness of the proposed capacity optimization approach,it is tested on a renewable energy fuelled multi-energy system in a commercial building.The primary energy devices of the multi-energy system consist of biomass gasification-based power generation unit,heat recovery unit,heat exchanger,absorption chiller,elec-tric chiller,biomass boiler,building integrated photovoltaic and photovoltaic thermal hybrid solar collector.The variable efficiency owing to weather condition and part-load operation is also considered.Genetic algorithm is adopted to determine the optimal design capacity and operating capacity of energy devices for the first-stage and second-stage optimization,respectively.The two optimization stages are interrelated;thus,the optimal design and operation of the multi-energy system can be obtained simultaneously and effectively.With the adoption of the proposed novel capacity optimization approach,there is a 14%reduction of year-round biomass consumption compared to one with the conventional capacity design approach.展开更多
A genetic algorithm-determined deep feedforward neural network architecture(GA-DFNN)is proposed for both day-ahead hourly and week-ahead daily electricity consumption of a real-world campus building in the United King...A genetic algorithm-determined deep feedforward neural network architecture(GA-DFNN)is proposed for both day-ahead hourly and week-ahead daily electricity consumption of a real-world campus building in the United Kingdom.Due to the comprehensive relationship between affecting factors and real-world building electricity consumption,the adoption of multiple hidden layers in the deep neural network(DFNN)algorithm would improve its prediction accuracy.The architecture of a DFNN model mainly refers to its quantity of hidden layers,quantity of neurons in the hidden layers,activation function in each layer and learning process to obtain the connecting weights.The optimal architecture of DFNN model was generally determined through a trial-and-error process,which is an exponential combinatorial problem and a tedious task.To address this problem,genetic algorithm(GA)is adopted to automatically design an optimal architecture with improved generalization ability.One year and six months of measurement data from a campus building is used for training and testing the proposed GA-DFNN model,respectively.To demonstrate the effectiveness of the proposed GA-DFNN prediction model,its prediction performance,including mean absolute percentage error,coefficient of determination,root mean square error and mean absolute error,was compared to the reference feedforward neural network models with single hidden layer,DFNN models with other architecture,random search determined DFNN model,long-short-term-memory model and temporal convolutional network model.The comparison results show that the proposed GA-DFNN predictive model has superior performance than all the reference prediction models,demonstrating the optimization effectiveness of GA and the prediction effectiveness of DFNN model with multiple hidden layers and optimal architecture.展开更多
基金supported by the National Natural Science Foundation of China(No.82371933)the National Natural Science Foundation of Shandong Province of China(No.ZR2021MH120)+1 种基金the Taishan Scholars Project(No.tsqn202211378)the Shandong Provincial Natural Science Foundation for Excellent Young Scholars(No.ZR2024YQ075).
文摘Objective:Early predicting response before neoadjuvant chemotherapy(NAC)is crucial for personalized treatment plans for locally advanced breast cancer patients.We aim to develop a multi-task model using multiscale whole slide images(WSIs)features to predict the response to breast cancer NAC more finely.Methods:This work collected 1,670 whole slide images for training and validation sets,internal testing sets,external testing sets,and prospective testing sets of the weakly-supervised deep learning-based multi-task model(DLMM)in predicting treatment response and pCR to NAC.Our approach models two-by-two feature interactions across scales by employing concatenate fusion of single-scale feature representations,and controls the expressiveness of each representation via a gating-based attention mechanism.Results:In the retrospective analysis,DLMM exhibited excellent predictive performance for the prediction of treatment response,with area under the receiver operating characteristic curves(AUCs)of 0.869[95%confidence interval(95%CI):0.806−0.933]in the internal testing set and 0.841(95%CI:0.814−0.867)in the external testing sets.For the pCR prediction task,DLMM reached AUCs of 0.865(95%CI:0.763−0.964)in the internal testing and 0.821(95%CI:0.763−0.878)in the pooled external testing set.In the prospective testing study,DLMM also demonstrated favorable predictive performance,with AUCs of 0.829(95%CI:0.754−0.903)and 0.821(95%CI:0.692−0.949)in treatment response and pCR prediction,respectively.DLMM significantly outperformed the baseline models in all testing sets(P<0.05).Heatmaps were employed to interpret the decision-making basis of the model.Furthermore,it was discovered that high DLMM scores were associated with immune-related pathways and cells in the microenvironment during biological basis exploration.Conclusions:The DLMM represents a valuable tool that aids clinicians in selecting personalized treatment strategies for breast cancer patients.
基金supported by the National Natural Science Foundation of China (No.82001775, 82371933)the Natural Science Foundation of Shandong Province of China (No.ZR2021MH120)+1 种基金the Special Fund for Breast Disease Research of Shandong Medical Association (No.YXH2021ZX055)the Taishan Scholar Foundation of Shandong Province of China (No.tsgn202211378)。
文摘Objective: Accurate detection and classification of breast lesions in early stage is crucial to timely formulate effective treatments for patients. We aim to develop a fully automatic system to detect and classify breast lesions using multiple contrast-enhanced mammography(CEM) images.Methods: In this study, a total of 1,903 females who underwent CEM examination from three hospitals were enrolled as the training set, internal testing set, pooled external testing set and prospective testing set. Here we developed a CEM-based multiprocess detection and classification system(MDCS) to perform the task of detection and classification of breast lesions. In this system, we introduced an innovative auxiliary feature fusion(AFF)algorithm that could intelligently incorporates multiple types of information from CEM images. The average freeresponse receiver operating characteristic score(AFROC-Score) was presented to validate system’s detection performance, and the performance of classification was evaluated by area under the receiver operating characteristic curve(AUC). Furthermore, we assessed the diagnostic value of MDCS through visual analysis of disputed cases,comparing its performance and efficiency with that of radiologists and exploring whether it could augment radiologists’ performance.Results: On the pooled external and prospective testing sets, MDCS always maintained a high standalone performance, with AFROC-Scores of 0.953 and 0.963 for detection task, and AUCs for classification were 0.909[95% confidence interval(95% CI): 0.822-0.996] and 0.912(95% CI: 0.840-0.985), respectively. It also achieved higher sensitivity than all senior radiologists and higher specificity than all junior radiologists on pooled external and prospective testing sets. Moreover, MDCS performed superior diagnostic efficiency with an average reading time of 5 seconds, compared to the radiologists’ average reading time of 3.2 min. The average performance of all radiologists was also improved to varying degrees with MDCS assistance.Conclusions: MDCS demonstrated excellent performance in the detection and classification of breast lesions,and greatly enhanced the overall performance of radiologists.
基金supported by the Taishan Scholar Project(No.ts20190991,No.tsqn202211378)the Key R&D Project of Shandong Province(No.2022CXPT023)+1 种基金the General Program of National Natural Science Foundation of China(No.82371933)the Medical and Health Technology Project of Shandong Province(No.202307010677)。
文摘Objective:The assessment of lateral lymph node metastasis(LLNM)in patients with papillary thyroid carcinoma(PTC)holds great significance.This study aims to develop and evaluate a deep learning-based automatic pipeline system(DLAPS)for diagnosing LLNM in PTC using computed tomography(CT).Methods:A total of 1,266 lateral lymph nodes(LLNs)from 519 PTC patients who underwent CT examinations from January 2019 to November 2022 were included and divided into training and validation set,internal test set,pooled external test set,and prospective test set.The DLAPS consists of an auto-segmentation network based on RefineNet model and a classification network based on ensemble model(ResNet,Xception,and DenseNet).The performance of the DLAPS was compared with that of manually segmented DL models,the clinical model,and Node Reporting and Data System(Node-RADS).The improvement of radiologists’diagnostic performance under the DLAPS-assisted strategy was explored.In addition,bulk RNA-sequencing was conducted based on 12 LLNs to reveal the underlying biological basis of the DLAPS.Results:The DLAPS yielded good performance with area under the receiver operating characteristic curve(AUC)of 0.872,0.910,and 0.822 in the internal,pooled external,and prospective test sets,respectively.The DLAPS significantly outperformed clinical models(AUC 0.731,P<0.001)and Node-RADS(AUC 0.602,P<0.001)in the internal test set.Moreover,the performance of the DLAPS was comparable to that of the manually segmented deep learning(DL)model with AUCs ranging 0.814−0.901 in three test sets.Furthermore,the DLAPSassisted strategy improved the performance of radiologists and enhanced inter-observer consistency.In clinical situations,the rate of unnecessary LLN dissection decreased from 33.33%to 7.32%.Furthermore,the DLAPS was associated with the cell-cell conjunction in the microenvironment.Conclusions:Using CT images from PTC patients,the DLAPS could effectively segment and classify LLNs non-invasively,and this system had a good generalization ability and clinical applicability.
文摘With the depletion of fossil fuel and climate change,multi-energy systems have attracted widespread attention in buildings.Multi-energy systems,fuelled by renewable energy,including solar and biomass energy,are gain-ing increasing adoption in commercial buildings.Most of previous capacity design approaches are formulated based upon conventional operating schedules,which result in inappropriate design capacities and ineffective operating schedules of the multi-energy system.Therefore,a two-stage capacity optimization approach is pro-posed for the multi-energy system with its optimal operating schedule taken into consideration.To demonstrate the effectiveness of the proposed capacity optimization approach,it is tested on a renewable energy fuelled multi-energy system in a commercial building.The primary energy devices of the multi-energy system consist of biomass gasification-based power generation unit,heat recovery unit,heat exchanger,absorption chiller,elec-tric chiller,biomass boiler,building integrated photovoltaic and photovoltaic thermal hybrid solar collector.The variable efficiency owing to weather condition and part-load operation is also considered.Genetic algorithm is adopted to determine the optimal design capacity and operating capacity of energy devices for the first-stage and second-stage optimization,respectively.The two optimization stages are interrelated;thus,the optimal design and operation of the multi-energy system can be obtained simultaneously and effectively.With the adoption of the proposed novel capacity optimization approach,there is a 14%reduction of year-round biomass consumption compared to one with the conventional capacity design approach.
文摘A genetic algorithm-determined deep feedforward neural network architecture(GA-DFNN)is proposed for both day-ahead hourly and week-ahead daily electricity consumption of a real-world campus building in the United Kingdom.Due to the comprehensive relationship between affecting factors and real-world building electricity consumption,the adoption of multiple hidden layers in the deep neural network(DFNN)algorithm would improve its prediction accuracy.The architecture of a DFNN model mainly refers to its quantity of hidden layers,quantity of neurons in the hidden layers,activation function in each layer and learning process to obtain the connecting weights.The optimal architecture of DFNN model was generally determined through a trial-and-error process,which is an exponential combinatorial problem and a tedious task.To address this problem,genetic algorithm(GA)is adopted to automatically design an optimal architecture with improved generalization ability.One year and six months of measurement data from a campus building is used for training and testing the proposed GA-DFNN model,respectively.To demonstrate the effectiveness of the proposed GA-DFNN prediction model,its prediction performance,including mean absolute percentage error,coefficient of determination,root mean square error and mean absolute error,was compared to the reference feedforward neural network models with single hidden layer,DFNN models with other architecture,random search determined DFNN model,long-short-term-memory model and temporal convolutional network model.The comparison results show that the proposed GA-DFNN predictive model has superior performance than all the reference prediction models,demonstrating the optimization effectiveness of GA and the prediction effectiveness of DFNN model with multiple hidden layers and optimal architecture.
