T he scientific, academic, medical and data science communities have come together in the face of the COVID-19 pandemic crisis to rapidly assess novel paradigms in artificial intelligence (AI) that are rapid and secure, and potentially incentivize data sharing and model training and testing without the usual privacy and data ownership hurdles of conventional collaborations 1,2 . Healthcare providers, researchers and industry have pivoted their focus to address unmet and critical clinical needs created by the crisis, with remarkable results [3][4][5][6][7][8][9] . Clinical trial recruitment has been expedited and facilitated by national regulatory bodies and an international cooperative spirit 10-12 . The data analytics and AI disciplines have always fostered open

PET image reconstruction is challenging due to the ill-poseness of the inverse problem and limited number of detected photons. Recently deep neural networks have been widely and successfully used in computer vision tasks and attracted growing interests in medical imaging. In this work, we trained a deep residual convolutional neural network to improve PET image quality by using the existing inter-patient information. An innovative feature of the proposed method is that we embed the neural network in the iterative reconstruction framework for image representation, rather than using it as a post-processing tool. We formulate the objective function as a constrained optimization problem and solve it using the alternating direction method of multipliers (ADMM) algorithm. Both simulation data and hybrid real data are used to evaluate the proposed method. Quantification results show that our proposed iterative neural network method can outperform the neural network denoising and conventional penalized maximum likelihood methods.

No abstract

Extracellular superoxide dismutase (EC-SOD) is the major extracellular antioxidant enzyme. We have determined the primary structure of mouse EC-SOD by characterization of complementary DNA (cDNA) clones and by amino-acid sequence analysis of purified protein. cDNA sequence analysis indicates that mouse EC-SOD is synthesized as a 251-amino-acid precursor protein with a predicted molecular weight of 27,400 D. Amino-terminal micro sequence analysis of purified mature mouse lung EC-SOD demonstrated the sequence to begin with SSFDLADRLDPV-. These results indicate that EC-SOD as initially synthesized contains a 24-amino-acid precursor peptide, and that the mature protein is 227 amino acids in length. Computer algorithms that predict the most likely site of cotranslational signal peptidase cleavage suggest that processing will occur between amino acids 18 and 19 or 20 and 21, which implies that EC-SOD may be initially synthesized as a pre-pro-protein. Like human EC-SOD, mature mouse EC-SOD is glycosylated. The full-length mouse EC-SOD cDNA is 1,834 base pairs long and is 82% (79% for protein) identical to rat EC-SOD, but only 60% (60% for protein) identical to human EC-SOD. The mouse EC-SOD gene locus (Sod3) was mapped by interspecific backcross haplotype analysis as being 0.9 +/- 0.9 centimorgans distal to the Qdpr locus on mouse Chromosome 5, a position suggesting that the human homologue of EC-SOD will map close to the human QDPR locus (4p15.3). Of nine tissues examined by Northern blot analysis, those of the kidney and lung are by far the major tissues that express EC-SOD messenger RNA. Using in situ hybridization in the mouse lung, we demonstrate EC-SOD gene expression to be highly localized to alveolar Type II epithelial cells. These data suggest that alveolar Type II cells play a central role in mediating EC-SOD antioxidant function in the lung.