Spectral computed tomography(CT)based on photon counting detectors can resolve the energy of every single photon interacting with the sensor layer and be used to analyze material attenuation information under differen...Spectral computed tomography(CT)based on photon counting detectors can resolve the energy of every single photon interacting with the sensor layer and be used to analyze material attenuation information under different energy ranges,which can be helpful for material decomposition studies.However,there is a considerable amount of inherent quantum noise in narrow energy bins,resulting in a low signal-to-noise ratio,which can consequently affect the material decomposition performance in the image domain.Deep learning technology is currently widely used in medical image segmentation,denoising,and recognition.In order to improve the results of material decomposition,we propose an attention-based global convolutional generative adversarial network(AGC-GAN)to decompose different materials for spectral CT.Specifically,our network is a global convolutional neural network based on an attention mechanism that is combined with a generative adversarial network.The global convolutional network based on the attention mechanism is used as the generator,and a patchGAN discriminant network is used as the discriminator.Meanwhile,a clinical spectral CT image dataset is used to verify the feasibility of our proposed approach.Extensive experimental results demonstrate that AGC-GAN achieves a better material decomposition performance than vanilla U-Net,fully convolutional network,and fully convolutional denseNet.Remarkably,the mean intersection over union,structural similarity,mean precision,PAcc,and mean F1-score of our method reach up to 87.31%,94.83%,93.22%,97.39%,and 93.05%,respectively.展开更多
Thermal ablation procedures,such as high intensity focused ultrasound and radiofrequency ablation,are often used to eliminate tumors by minimally invasively heating a focal region.For this task,real-time 3D temperatur...Thermal ablation procedures,such as high intensity focused ultrasound and radiofrequency ablation,are often used to eliminate tumors by minimally invasively heating a focal region.For this task,real-time 3D temperature visualization is key to target the diseased tissues while minimizing damage to the surroundings.Current computed tomography(CT)thermometry is based on energy-integrated CT,tissue-specific experimental data,and linear relationships between attenuation and temperature.In this paper,we develop a novel approach using photon-counting CT for material decomposition and a neural network to predict temperature based on thermal characteristics of base materials and spectral tomographic measurements of a volume of interest.In our feasibility study,distilled water,50 mmol/L CaCl2,and 600 mmol/L CaCl2 are chosen as the base materials.Their attenuations are measured in four discrete energy bins at various temperatures.The neural network trained on the experimental data achieves a mean absolute error of 3.97°C and 1.80°C on 300 mmol/L CaCl2 and a milk-based protein shake respectively.These experimental results indicate that our approach is promising for handling non-linear thermal properties for materials that are similar or dis-similar to our base materials.展开更多
Purpose A major challenge for the material decomposition task of the dual-energy computed tomography(DECT)is the algorithm often suffers from heavy noise in the results.The purpose of this study is to propose a scheme...Purpose A major challenge for the material decomposition task of the dual-energy computed tomography(DECT)is the algorithm often suffers from heavy noise in the results.The purpose of this study is to propose a scheme to increase the noise performance of material decomposition.Methods The scheme we propose in this paper is to apply an autoencoder-based denoising procedure to the photon-counting DECT images before they are fed into the material decomposition algorithm.We implement the autoencoder(AE)by stacking a series of convolutional and deconvolutional layers.The decomposition technique adopted in our work is an iterative method using least squares estimation with the Huber loss function.The noises of the input and the output of material decomposition are analyzed with both simulated data and real data.Phantom and chicken wing experiments are conducted with a photoncounting-based spectral CT scanner to evaluate the proposed material decomposition scheme.Results The noise analysis of the input and the output of material decomposition demonstrates a positive correlation between them.Comparative experiment indicates a noise reduction in the output density maps for 26.07%to 35.65%after the autoencoder pre-processing is applied.The resultant contrast-to-noise ratio is largely increased,correspondingly.Conclusions By utilizing the additional autoencoder denoising step,the material decomposition algorithm achieves an improvement in the noise performance of the resultant density maps.展开更多
The quasi-monochromatic,continuously energy-tunable,and high-brightness gamma rays that are produced by an inverse Compton scattering(ICS)light source provide an ideal probe for gamma-ray imaging.However,owing to the ...The quasi-monochromatic,continuously energy-tunable,and high-brightness gamma rays that are produced by an inverse Compton scattering(ICS)light source provide an ideal probe for gamma-ray imaging.However,owing to the influence of the intrinsic energy-angle correlation spectrum of this type of light source,monochromatic computed tomography(CT),especially in the gamma-ray energy region,can only be realized in a low-efficiency manner,similar to first-generation CT.A dual-energy scan scheme with a large imaging field of view(FOV)was developed in this study to improve the imaging efficiency.The effectiveness of this scheme was demonstrated based on the beam parameters of a typical ICS light source using Monte Carlo simulations.By leveraging the principle of basis material decomposition,the influence of the energyangle correlation spectrum on CT reconstruction was corrected,and a monochromatic CT image of the imaging object was accurately reconstructed.Furthermore,the electron density and effective atomic number of the imaging object could be obtained simultaneously.展开更多
Moolooite particles with flaky morphology were synthesized by mixing dilute solutions of copper nitrate and sodium oxalate in the presence of citric acid. Solution p H value, citric acid concentration, and stirring we...Moolooite particles with flaky morphology were synthesized by mixing dilute solutions of copper nitrate and sodium oxalate in the presence of citric acid. Solution p H value, citric acid concentration, and stirring were found to have large effect on the shape of the precipitated particles. Under the stirring, the radial area of flaky moolooite particles was enlarged and extended to become a thinner and larger flake. This is ascribed to growth promotion caused by the selective absorption of citric ligands onto a particular crystalline surface of the moolooite particles. Flaky shape of the moolooite particles tended to become spherical and disappeared completely when decomposed under an Ar atmosphere, leading to the formation of large porous aggregated particles composed of many tiny nanosized copper crystals.展开更多
Purpose:To assess the iodine concentration of hepatic alveolar echinococcosis(HAE)using spectral computed tomography(CT)with comparison of[^(18)F]fluorodeoxyglucose positron-emission tomography(^(18)F-FDG PET),and to ...Purpose:To assess the iodine concentration of hepatic alveolar echinococcosis(HAE)using spectral computed tomography(CT)with comparison of[^(18)F]fluorodeoxyglucose positron-emission tomography(^(18)F-FDG PET),and to estimate the value of spectral CT for evaluation of HAE activity.Materials and methods:18 patients with histologically confirmed or clinically proved HAE underwent spectral CT and^(18)F-FDG PET examinations.After three-phase scanning,the quantitative iodine-based material decomposition images and optimal monochromatic image of spectral CT were reconstructed and iodine concentration(IC)was measured in different organizational structures.Results:^(18)F-FDG PET identified increased metabolic activity in the corresponding lesions in 13 patients(13/18,72.2%).The iodine concentration in marginal zone of lesion were significantly higher than in solid component of lesion and normal liver parenchyma during PVP and VP.The iodine value of edge tissue of the lesion and normal liver and iodine value of normal liver tissues showed statistically significant difference(P<0.001).There was correlation between IC and SUVmax in marginal zone of HAE lesion,it was highest during PVP(r=0.873,p<0.001).There was low correlation between CT values and SUVmax.Conclusion:There was good correlation between spectral CT and^(18)F-FDG PET.Spectral CT could be recommended as a more practical tool in the clinical routine.展开更多
基金supported by National Natural Science Foundation of China (No.62101136)Shanghai Sailing Program (No.21YF1402800)+3 种基金Shanghai Municipal Science and Technology Major Project (No.2018SHZDZX01)ZJLab,Shanghai Municipal of Science and Technology Project (No.20JC1419500)Natural Science Foundation of Chongqing (No.CSTB2022NSCQ-MSX0360)Shanghai Center for Brain Science and Brain-inspired Technology.
文摘Spectral computed tomography(CT)based on photon counting detectors can resolve the energy of every single photon interacting with the sensor layer and be used to analyze material attenuation information under different energy ranges,which can be helpful for material decomposition studies.However,there is a considerable amount of inherent quantum noise in narrow energy bins,resulting in a low signal-to-noise ratio,which can consequently affect the material decomposition performance in the image domain.Deep learning technology is currently widely used in medical image segmentation,denoising,and recognition.In order to improve the results of material decomposition,we propose an attention-based global convolutional generative adversarial network(AGC-GAN)to decompose different materials for spectral CT.Specifically,our network is a global convolutional neural network based on an attention mechanism that is combined with a generative adversarial network.The global convolutional network based on the attention mechanism is used as the generator,and a patchGAN discriminant network is used as the discriminator.Meanwhile,a clinical spectral CT image dataset is used to verify the feasibility of our proposed approach.Extensive experimental results demonstrate that AGC-GAN achieves a better material decomposition performance than vanilla U-Net,fully convolutional network,and fully convolutional denseNet.Remarkably,the mean intersection over union,structural similarity,mean precision,PAcc,and mean F1-score of our method reach up to 87.31%,94.83%,93.22%,97.39%,and 93.05%,respectively.
基金the Johns Hopkins University Leong Research Award for Undergraduates.
文摘Thermal ablation procedures,such as high intensity focused ultrasound and radiofrequency ablation,are often used to eliminate tumors by minimally invasively heating a focal region.For this task,real-time 3D temperature visualization is key to target the diseased tissues while minimizing damage to the surroundings.Current computed tomography(CT)thermometry is based on energy-integrated CT,tissue-specific experimental data,and linear relationships between attenuation and temperature.In this paper,we develop a novel approach using photon-counting CT for material decomposition and a neural network to predict temperature based on thermal characteristics of base materials and spectral tomographic measurements of a volume of interest.In our feasibility study,distilled water,50 mmol/L CaCl2,and 600 mmol/L CaCl2 are chosen as the base materials.Their attenuations are measured in four discrete energy bins at various temperatures.The neural network trained on the experimental data achieves a mean absolute error of 3.97°C and 1.80°C on 300 mmol/L CaCl2 and a milk-based protein shake respectively.These experimental results indicate that our approach is promising for handling non-linear thermal properties for materials that are similar or dis-similar to our base materials.
基金the National Key R&D Program of China(Grant No.2016YFC0100400)the Instrument Developing Project of the Chinese Academy of Sciences(Grant No.YZ201511)the Key Technology Research and Development Team Project of Chinese Academy of Sciences(Grant No.GJJSTD2017005).
文摘Purpose A major challenge for the material decomposition task of the dual-energy computed tomography(DECT)is the algorithm often suffers from heavy noise in the results.The purpose of this study is to propose a scheme to increase the noise performance of material decomposition.Methods The scheme we propose in this paper is to apply an autoencoder-based denoising procedure to the photon-counting DECT images before they are fed into the material decomposition algorithm.We implement the autoencoder(AE)by stacking a series of convolutional and deconvolutional layers.The decomposition technique adopted in our work is an iterative method using least squares estimation with the Huber loss function.The noises of the input and the output of material decomposition are analyzed with both simulated data and real data.Phantom and chicken wing experiments are conducted with a photoncounting-based spectral CT scanner to evaluate the proposed material decomposition scheme.Results The noise analysis of the input and the output of material decomposition demonstrates a positive correlation between them.Comparative experiment indicates a noise reduction in the output density maps for 26.07%to 35.65%after the autoencoder pre-processing is applied.The resultant contrast-to-noise ratio is largely increased,correspondingly.Conclusions By utilizing the additional autoencoder denoising step,the material decomposition algorithm achieves an improvement in the noise performance of the resultant density maps.
基金supported by the National Natural Science Foundation of China(Nos.12375157,12027902,and 11905011)。
文摘The quasi-monochromatic,continuously energy-tunable,and high-brightness gamma rays that are produced by an inverse Compton scattering(ICS)light source provide an ideal probe for gamma-ray imaging.However,owing to the influence of the intrinsic energy-angle correlation spectrum of this type of light source,monochromatic computed tomography(CT),especially in the gamma-ray energy region,can only be realized in a low-efficiency manner,similar to first-generation CT.A dual-energy scan scheme with a large imaging field of view(FOV)was developed in this study to improve the imaging efficiency.The effectiveness of this scheme was demonstrated based on the beam parameters of a typical ICS light source using Monte Carlo simulations.By leveraging the principle of basis material decomposition,the influence of the energyangle correlation spectrum on CT reconstruction was corrected,and a monochromatic CT image of the imaging object was accurately reconstructed.Furthermore,the electron density and effective atomic number of the imaging object could be obtained simultaneously.
基金financially supported by the Fundamental Research Funds for the Central Universities of China (FRF-BD-15-004A)
文摘Moolooite particles with flaky morphology were synthesized by mixing dilute solutions of copper nitrate and sodium oxalate in the presence of citric acid. Solution p H value, citric acid concentration, and stirring were found to have large effect on the shape of the precipitated particles. Under the stirring, the radial area of flaky moolooite particles was enlarged and extended to become a thinner and larger flake. This is ascribed to growth promotion caused by the selective absorption of citric ligands onto a particular crystalline surface of the moolooite particles. Flaky shape of the moolooite particles tended to become spherical and disappeared completely when decomposed under an Ar atmosphere, leading to the formation of large porous aggregated particles composed of many tiny nanosized copper crystals.
文摘Purpose:To assess the iodine concentration of hepatic alveolar echinococcosis(HAE)using spectral computed tomography(CT)with comparison of[^(18)F]fluorodeoxyglucose positron-emission tomography(^(18)F-FDG PET),and to estimate the value of spectral CT for evaluation of HAE activity.Materials and methods:18 patients with histologically confirmed or clinically proved HAE underwent spectral CT and^(18)F-FDG PET examinations.After three-phase scanning,the quantitative iodine-based material decomposition images and optimal monochromatic image of spectral CT were reconstructed and iodine concentration(IC)was measured in different organizational structures.Results:^(18)F-FDG PET identified increased metabolic activity in the corresponding lesions in 13 patients(13/18,72.2%).The iodine concentration in marginal zone of lesion were significantly higher than in solid component of lesion and normal liver parenchyma during PVP and VP.The iodine value of edge tissue of the lesion and normal liver and iodine value of normal liver tissues showed statistically significant difference(P<0.001).There was correlation between IC and SUVmax in marginal zone of HAE lesion,it was highest during PVP(r=0.873,p<0.001).There was low correlation between CT values and SUVmax.Conclusion:There was good correlation between spectral CT and^(18)F-FDG PET.Spectral CT could be recommended as a more practical tool in the clinical routine.
