Eye health has become a global health concern and attracted broad attention.Over the years,researchers have proposed many state-of-the-art convolutional neural networks(CNNs)to assist ophthalmologists in diagnosing oc...Eye health has become a global health concern and attracted broad attention.Over the years,researchers have proposed many state-of-the-art convolutional neural networks(CNNs)to assist ophthalmologists in diagnosing ocular diseases efficiently and precisely.However,most existing methods were dedicated to constructing sophisticated CNNs,inevitably ignoring the trade-off between performance and model complexity.To alleviate this paradox,this paper proposes a lightweight yet efficient network architecture,mixeddecomposed convolutional network(MDNet),to recognise ocular diseases.In MDNet,we introduce a novel mixed-decomposed depthwise convolution method,which takes advantage of depthwise convolution and depthwise dilated convolution operations to capture low-resolution and high-resolution patterns by using fewer computations and fewer parameters.We conduct extensive experiments on the clinical anterior segment optical coherence tomography(AS-OCT),LAG,University of California San Diego,and CIFAR-100 datasets.The results show our MDNet achieves a better trade-off between the performance and model complexity than efficient CNNs including MobileNets and MixNets.Specifically,our MDNet outperforms MobileNets by 2.5%of accuracy by using 22%fewer parameters and 30%fewer computations on the AS-OCT dataset.展开更多
Excessive fructose diet is closely associated with colorectal cancer(CRC)progression.Nevertheless,fructose’s specific function and precise mechanism in colorectal cancer liver metastasis(CRLM)is rarely known.Here,thi...Excessive fructose diet is closely associated with colorectal cancer(CRC)progression.Nevertheless,fructose’s specific function and precise mechanism in colorectal cancer liver metastasis(CRLM)is rarely known.Here,this study reported that the fructose absorbed by primary colorectal cancer could accelerate CRLM,and the expression of KHK-A,not KHK-C,in liver metastasis was higher than in paired primary tumors.Furthermore,KHK-A facilitated fructose-dependent CRLM in vitro and in vivo by phosphorylating PKM2 at Ser37.PKM2 phosphorylated by KHK-A inhibited its tetramer formation and pyruvic acid kinase activity but promoted the nuclear accumulation of PKM2.EMT and aerobic glycolysis activated by nuclear PKM2 enhance CRC cells’migration ability and anoikis resistance during CRLM progression.TEPP-46 treatment,targeting the phosphorylation of PKM2,inhibited the pro-metastatic effect of KHK-A.Besides,c-myc activated by nuclear PKM2 promotes alternative splicing of KHK-A,forming a positive feedback loop.展开更多
基金Stable Support Plan Program,Grant/Award Number:20200925174052004Shenzhen Natural Science Fund,Grant/Award Number:JCYJ20200109140820699+2 种基金National Natural Science Foundation of China,Grant/Award Number:82272086Guangdong Provincial Department of Education,Grant/Award Numbers:2020ZDZX3043,SJZLGC202202Guangdong Provincial Key Laboratory,Grant/Award Number:2020B121201001。
文摘Eye health has become a global health concern and attracted broad attention.Over the years,researchers have proposed many state-of-the-art convolutional neural networks(CNNs)to assist ophthalmologists in diagnosing ocular diseases efficiently and precisely.However,most existing methods were dedicated to constructing sophisticated CNNs,inevitably ignoring the trade-off between performance and model complexity.To alleviate this paradox,this paper proposes a lightweight yet efficient network architecture,mixeddecomposed convolutional network(MDNet),to recognise ocular diseases.In MDNet,we introduce a novel mixed-decomposed depthwise convolution method,which takes advantage of depthwise convolution and depthwise dilated convolution operations to capture low-resolution and high-resolution patterns by using fewer computations and fewer parameters.We conduct extensive experiments on the clinical anterior segment optical coherence tomography(AS-OCT),LAG,University of California San Diego,and CIFAR-100 datasets.The results show our MDNet achieves a better trade-off between the performance and model complexity than efficient CNNs including MobileNets and MixNets.Specifically,our MDNet outperforms MobileNets by 2.5%of accuracy by using 22%fewer parameters and 30%fewer computations on the AS-OCT dataset.
基金funded by the National Natural Science Foundation(Grant Number 82273406)Basic Research Program of Jiangsu Province(Grant No.BK20201491,China)+2 种基金Nature Key Research and Development Program of Jiangsu Province(BE2021742,China)Jiangsu Province Capability Improvement Project through Science,Technology and Education(Jiangsu Provincial Medical Key Discipline,ZDXK202222,China)the National Natural Science Foundation(Grant Number 82203656,China).
文摘Excessive fructose diet is closely associated with colorectal cancer(CRC)progression.Nevertheless,fructose’s specific function and precise mechanism in colorectal cancer liver metastasis(CRLM)is rarely known.Here,this study reported that the fructose absorbed by primary colorectal cancer could accelerate CRLM,and the expression of KHK-A,not KHK-C,in liver metastasis was higher than in paired primary tumors.Furthermore,KHK-A facilitated fructose-dependent CRLM in vitro and in vivo by phosphorylating PKM2 at Ser37.PKM2 phosphorylated by KHK-A inhibited its tetramer formation and pyruvic acid kinase activity but promoted the nuclear accumulation of PKM2.EMT and aerobic glycolysis activated by nuclear PKM2 enhance CRC cells’migration ability and anoikis resistance during CRLM progression.TEPP-46 treatment,targeting the phosphorylation of PKM2,inhibited the pro-metastatic effect of KHK-A.Besides,c-myc activated by nuclear PKM2 promotes alternative splicing of KHK-A,forming a positive feedback loop.