To overcome the computational burden of processing three-dimensional(3 D)medical scans and the lack of spatial information in two-dimensional(2 D)medical scans,a novel segmentation method was proposed that integrates ...To overcome the computational burden of processing three-dimensional(3 D)medical scans and the lack of spatial information in two-dimensional(2 D)medical scans,a novel segmentation method was proposed that integrates the segmentation results of three densely connected 2 D convolutional neural networks(2 D-CNNs).In order to combine the lowlevel features and high-level features,we added densely connected blocks in the network structure design so that the low-level features will not be missed as the network layer increases during the learning process.Further,in order to resolve the problems of the blurred boundary of the glioma edema area,we superimposed and fused the T2-weighted fluid-attenuated inversion recovery(FLAIR)modal image and the T2-weighted(T2)modal image to enhance the edema section.For the loss function of network training,we improved the cross-entropy loss function to effectively avoid network over-fitting.On the Multimodal Brain Tumor Image Segmentation Challenge(BraTS)datasets,our method achieves dice similarity coefficient values of 0.84,0.82,and 0.83 on the BraTS2018 training;0.82,0.85,and 0.83 on the BraTS2018 validation;and 0.81,0.78,and 0.83 on the BraTS2013 testing in terms of whole tumors,tumor cores,and enhancing cores,respectively.Experimental results showed that the proposed method achieved promising accuracy and fast processing,demonstrating good potential for clinical medicine.展开更多
We demonstrate a 200 m outdoor 2×2 multiple-input multiple-output(MIMO)terahertz(THz)communication system operating at 300 GHz with 200 Gb/s polarization-division multiplexed quadrature phase-shift keying(PDM-QPS...We demonstrate a 200 m outdoor 2×2 multiple-input multiple-output(MIMO)terahertz(THz)communication system operating at 300 GHz with 200 Gb/s polarization-division multiplexed quadrature phase-shift keying(PDM-QPSK)transmission.We propose an iteratively pruned two-dimensional convolutional neural network(2D CNN)equalizer that adaptively captures polarization crosstalk and temporal nonlinearities through 2D convolution kernels.The system achieves a bit error rate(BER)below the hard-decision forward error correction(HD-FEC)threshold at a lower power of 6 d Bm,while reducing the computational complexity by 30.2%compared to the iteratively pruned one-dimensional(1D)CNN approach.This enables high-capacity and energy-efficient operation in long-distance THz links.展开更多
基金the National Natural Science Foundation of China(No.81830052)the Shanghai Natural Science Foundation of China(No.20ZR1438300)the Shanghai Science and Technology Support Project(No.18441900500),China。
文摘To overcome the computational burden of processing three-dimensional(3 D)medical scans and the lack of spatial information in two-dimensional(2 D)medical scans,a novel segmentation method was proposed that integrates the segmentation results of three densely connected 2 D convolutional neural networks(2 D-CNNs).In order to combine the lowlevel features and high-level features,we added densely connected blocks in the network structure design so that the low-level features will not be missed as the network layer increases during the learning process.Further,in order to resolve the problems of the blurred boundary of the glioma edema area,we superimposed and fused the T2-weighted fluid-attenuated inversion recovery(FLAIR)modal image and the T2-weighted(T2)modal image to enhance the edema section.For the loss function of network training,we improved the cross-entropy loss function to effectively avoid network over-fitting.On the Multimodal Brain Tumor Image Segmentation Challenge(BraTS)datasets,our method achieves dice similarity coefficient values of 0.84,0.82,and 0.83 on the BraTS2018 training;0.82,0.85,and 0.83 on the BraTS2018 validation;and 0.81,0.78,and 0.83 on the BraTS2013 testing in terms of whole tumors,tumor cores,and enhancing cores,respectively.Experimental results showed that the proposed method achieved promising accuracy and fast processing,demonstrating good potential for clinical medicine.
基金supported by the National Key R&D Program of China(No.2023YFB2905600)the National Natural Science Foundation of China(Nos.62127802,62331004,62305067,U24B20142,U24B20168,and 62427815)the Key Project of Jiangsu Province of China(No.BE2023001-4)。
文摘We demonstrate a 200 m outdoor 2×2 multiple-input multiple-output(MIMO)terahertz(THz)communication system operating at 300 GHz with 200 Gb/s polarization-division multiplexed quadrature phase-shift keying(PDM-QPSK)transmission.We propose an iteratively pruned two-dimensional convolutional neural network(2D CNN)equalizer that adaptively captures polarization crosstalk and temporal nonlinearities through 2D convolution kernels.The system achieves a bit error rate(BER)below the hard-decision forward error correction(HD-FEC)threshold at a lower power of 6 d Bm,while reducing the computational complexity by 30.2%compared to the iteratively pruned one-dimensional(1D)CNN approach.This enables high-capacity and energy-efficient operation in long-distance THz links.
