Transparent photovoltaic devices(TPVDs)have attracted increasing attention in emerging electronic devices.As the application scenarios extend,there raise higher requirements regarding the stability and operating tempe...Transparent photovoltaic devices(TPVDs)have attracted increasing attention in emerging electronic devices.As the application scenarios extend,there raise higher requirements regarding the stability and operating temperature range of TPVDs.In this work,a unique preparation strategy is proposed for air stable TPVD with a wide operating temperature range,i.e.,a nanoscale architecture termed as H-TPVD is constructed that integrates a free-standing and highly transparent conductive hybrid film of graphene and single-walled carbon nanotubes(G-SWNT TCF for short)with a metal oxide NiO/TiO_(2)heterojunction.The preparation approach is suitable for scaling up.Thanks to the excellent transparent conductivity of the freestanding G-SWNT hybrid film and the ultrathin NiO/TiO_(2)heterojunction(100 nm),H-TPVD selectively absorbs the ultraviolet(UV)band of sunlight and has a transparency of up to 71%in the visible light.The integrated nanoscale architecture manifests the significant holecollecting capability of the G-SWNT hybrid film and the efficient carrier generation and separation within the ultrathin NiO/TiO_(2)heterojunction,resulting in excellent performance of the H-TPVD with a specific detectivity of 2.7×10^(10) Jones.Especially,the freestanding G-SWNT TCF is a super stable and non-porous two-dimensional film that can insulate gas molecules,thereby protecting the surface properties of NiO/TiO_(2)heterojunctions and enhancing the stability of H-TPVD.Having subjected to 20,000 cycles and storage in air for three months,the performance parameters such as photo-response signal,output power,and specific detectivity show no noticeable degradation.In particular,the as-fabricated self-powered H-TPVD can operate over a wide temperature range from −180 to 300℃,and can carry out solar-blind UV optical communication in this range.In addition,the 4×4 array H-TPVD demonstrates clear optical imaging.These results make it possible for H-TPVD to expand its potential application scenarios.展开更多
Objective Tumor sprouting can reflect independent risk factors for tumor malignancy and a poor clinical progno-sis.However,there are significant differences and difficulties associated with manually identifying tumor ...Objective Tumor sprouting can reflect independent risk factors for tumor malignancy and a poor clinical progno-sis.However,there are significant differences and difficulties associated with manually identifying tumor sprout-ing.This study used the Faster region convolutional neural network(RCNN)model to build a colorectal cancer tumor sprouting artificial intelligence recognition framework based on pathological sections to automatically identify the budding area to assist in the clinical diagnosis and treatment of colorectal cancer.Methods We retrospectively collected 100 surgical pathological sections of colorectal cancer from January 2019 to October 2019.The pathologists used LabelImg software to identify tumor buds and to count their numbers.Finally,1,000 images were screened,and the total number of tumor buds was approximately 3,226;the images were randomly divided into a training set and a test set at a ratio of 6:4.After the images in the training set were manually identified,the identified buds in the 600 images were used to train the Faster RCNN identification model.After the establishment of the artificial intelligence identification detection platform,400 images in the test set were used to test the identification detection system to identify and predict the area and number of tumor buds.Finally,by comparing the results of the Faster RCNN system and the identification information of pathologists,the performance of the artificial intelligence automatic detection platform was evaluated to determine the area and number of tumor sprouting in the pathological sections of the colorectal cancers to achieve an auxiliary diagnosis and to suggest appropriate treatment.The selected performance indicators include accuracy,precision,specificity,etc.ROC(receiver operator characteristic)and AUC(area under the curve)were used to quantify the performance of the system to automatically identify tumor budding areas and numbers.Results The AUC of the receiver operating characteristic curve of the artificial intelligence detection and identi-fication system was 0.96,the image diagnosis accuracy rate was 0.89,the precision was 0.855,the sensitivity was 0.94,the specificity was 0.83,and the negative predictive value was 0.933.After 400 test sets,pathological image verification showed that there were 356 images with the same positive budding area count,and the difference between the positive area count and the manual detection count in the remaining images was less than 3.The detection system based on tumor budding recognition in pathological sections is comparable to that of patholo-gists’accuracy;however,it took significantly less time(0.03±0.01)s for the pathologist(13±5)s to diagnose the sections with the assistance of the AI model.Conclusion This system can accurately and quickly identify the tumor sprouting area in the pathological sections of colorectal cancer and count their numbers,which greatly improves the diagnostic efficacy,and effectively avoids the need for confirmation by different pathologists.The use of the AI reduces the burden of pathologists in reading sections and it has a certain clinical diagnosis and treatment value.展开更多
基金supported by the National Key Research and Development Program of China(Nos.2018YFA0208402 and 2020YFA0714700)the National Natural Science Foundation of China(Nos.52172060,51820105002,11634014,and 51372269)X.J.W.thanks Youth Innovation Promotion Association of the Chinese Academy of Sciences(No.2020005).
文摘Transparent photovoltaic devices(TPVDs)have attracted increasing attention in emerging electronic devices.As the application scenarios extend,there raise higher requirements regarding the stability and operating temperature range of TPVDs.In this work,a unique preparation strategy is proposed for air stable TPVD with a wide operating temperature range,i.e.,a nanoscale architecture termed as H-TPVD is constructed that integrates a free-standing and highly transparent conductive hybrid film of graphene and single-walled carbon nanotubes(G-SWNT TCF for short)with a metal oxide NiO/TiO_(2)heterojunction.The preparation approach is suitable for scaling up.Thanks to the excellent transparent conductivity of the freestanding G-SWNT hybrid film and the ultrathin NiO/TiO_(2)heterojunction(100 nm),H-TPVD selectively absorbs the ultraviolet(UV)band of sunlight and has a transparency of up to 71%in the visible light.The integrated nanoscale architecture manifests the significant holecollecting capability of the G-SWNT hybrid film and the efficient carrier generation and separation within the ultrathin NiO/TiO_(2)heterojunction,resulting in excellent performance of the H-TPVD with a specific detectivity of 2.7×10^(10) Jones.Especially,the freestanding G-SWNT TCF is a super stable and non-porous two-dimensional film that can insulate gas molecules,thereby protecting the surface properties of NiO/TiO_(2)heterojunctions and enhancing the stability of H-TPVD.Having subjected to 20,000 cycles and storage in air for three months,the performance parameters such as photo-response signal,output power,and specific detectivity show no noticeable degradation.In particular,the as-fabricated self-powered H-TPVD can operate over a wide temperature range from −180 to 300℃,and can carry out solar-blind UV optical communication in this range.In addition,the 4×4 array H-TPVD demonstrates clear optical imaging.These results make it possible for H-TPVD to expand its potential application scenarios.
基金National Natural Science Foun-dation of China Youth Project(Grant No.81802473)Shandong Nat-ural Science Foundation of China(Grant No.ZR201910310332).
文摘Objective Tumor sprouting can reflect independent risk factors for tumor malignancy and a poor clinical progno-sis.However,there are significant differences and difficulties associated with manually identifying tumor sprout-ing.This study used the Faster region convolutional neural network(RCNN)model to build a colorectal cancer tumor sprouting artificial intelligence recognition framework based on pathological sections to automatically identify the budding area to assist in the clinical diagnosis and treatment of colorectal cancer.Methods We retrospectively collected 100 surgical pathological sections of colorectal cancer from January 2019 to October 2019.The pathologists used LabelImg software to identify tumor buds and to count their numbers.Finally,1,000 images were screened,and the total number of tumor buds was approximately 3,226;the images were randomly divided into a training set and a test set at a ratio of 6:4.After the images in the training set were manually identified,the identified buds in the 600 images were used to train the Faster RCNN identification model.After the establishment of the artificial intelligence identification detection platform,400 images in the test set were used to test the identification detection system to identify and predict the area and number of tumor buds.Finally,by comparing the results of the Faster RCNN system and the identification information of pathologists,the performance of the artificial intelligence automatic detection platform was evaluated to determine the area and number of tumor sprouting in the pathological sections of the colorectal cancers to achieve an auxiliary diagnosis and to suggest appropriate treatment.The selected performance indicators include accuracy,precision,specificity,etc.ROC(receiver operator characteristic)and AUC(area under the curve)were used to quantify the performance of the system to automatically identify tumor budding areas and numbers.Results The AUC of the receiver operating characteristic curve of the artificial intelligence detection and identi-fication system was 0.96,the image diagnosis accuracy rate was 0.89,the precision was 0.855,the sensitivity was 0.94,the specificity was 0.83,and the negative predictive value was 0.933.After 400 test sets,pathological image verification showed that there were 356 images with the same positive budding area count,and the difference between the positive area count and the manual detection count in the remaining images was less than 3.The detection system based on tumor budding recognition in pathological sections is comparable to that of patholo-gists’accuracy;however,it took significantly less time(0.03±0.01)s for the pathologist(13±5)s to diagnose the sections with the assistance of the AI model.Conclusion This system can accurately and quickly identify the tumor sprouting area in the pathological sections of colorectal cancer and count their numbers,which greatly improves the diagnostic efficacy,and effectively avoids the need for confirmation by different pathologists.The use of the AI reduces the burden of pathologists in reading sections and it has a certain clinical diagnosis and treatment value.
