ABSTRACT
The ground glass opacity (GGO) of the lung is one of the essential features of COVID-19. The GGO in computed tomography (CT) images has various features and low-intensity contrast between the GGO and edge structures. These problems pose significant challenges for segmenting the GGO. To tackle these problems, we propose a new threshold method for accurate segmentation of GGO. Specifically, we offer a framework for adjusting the threshold parameters according to the image contrast. Three functions include Attention mechanism threshold, Contour equalization, and Lung segmentation (ACL). The lung is divided into three areas using the attention mechanism threshold. Further, the segmentation parameters of the attention mechanism thresholds of the three parts are adaptively adjusted according to the image contrast. Only the segmentation regions restricted by the lung segmentation results are retained. Extensive experiments on four COVID datasets show that ACL can segment GGO images at low contrast well. Compared with the state-of-the-art methods, the similarity Dice of the ACL segmentation results is improved by 8.9%, the average symmetry surface distance ASD is reduced by 23%, and the required computational power F L O P s are only 0.09% of those of deep learning models. For GGO segmentation, ACL is more lightweight, and the accuracy is higher. Code will be released at https://github.com/Lqs-github/ACL.
ABSTRACT
The ground glass opacity (GGO) of the lung is one of the essential features of COVID-19. The GGO in computed tomography (CT) images has various features and low-intensity contrast between the GGO and edge structures. These problems pose significant challenges for segmenting the GGO. To tackle these problems, we propose a new threshold method for accurate segmentation of GGO. Specifically, we offer a framework for adjusting the threshold parameters according to the image contrast. Three functions include Attention mechanism threshold, Contour equalization, and Lung segmentation (ACL). The lung is divided into three areas using the attention mechanism threshold. Further, the segmentation parameters of the attention mechanism thresholds of the three parts are adaptively adjusted according to the image contrast. Only the segmentation regions restricted by the lung segmentation results are retained. Extensive experiments on four COVID datasets show that ACL can segment GGO images at low contrast well. Compared with the state-of-the-art methods, the similarity Dice of the ACL segmentation results is improved by 8.9%, the average symmetry surface distance ASD is reduced by 23%, and the required computational power
ABSTRACT
To deal with the ever-growing toxic benzene-derived compounds in the water system, extensive efforts have been dedicated for catalytic degradation of pollutants. However, the activities and efficiencies of the transition metal-based nanoparticles or single-atom sites are still ambiguous in Fenton-like reactions. Herein, to compare the Fenton-like catalytic efficiencies of the nanoparticles and single atoms, the free-standing nanofibrous catalyst comprising Co nanocrystals and Co-Nx codoped carbon nanotubes (CNTs) or bare Co-Nx doped CNTs is fabricated. It is noteworthy that all these nanofibrous catalysts exhibit efficient activities, mesoporous structures, and conductive carbon networks, which allow a feasible validation of the catalytic effects. Benefiting from the maximized atomic utilization, the atomic Co-Nx centers exhibit much higher reaction kinetic constant (κ = 0.157 min-1 ) and mass activity toward the degradation of bisphenol A, far exceeding the Co nanocrystals (κ = 0.082 min-1 ). However, for the volume activities, the single-atom catalyst does not show apparent advantages compared to the nanocrystal-based catalyst. Overall, this work not only provides a viable pathway for comparing Fenton-like catalytic effects of transition metal-based nanoparticles or single atoms but also opens up a new avenue for developing prominent catalysts for organic pollutants' degradation.