A deep learning based microwave imaging model which can directly map the scattered electric field to the dielectric property distribution image of the target object is developed,and its potential for medical applications is explored.The two-dimensional time-domain finite difference method is used for numerical simulation to obtain a dataset of scattered electric fields;a deep convolutional autoencoder based imaging model is constructed to perform imaging studies on two types of target objects;the imaging results are quantitatively evaluated using relative error,and the model's ability to distinguish different types of strokes is also analyzed.The results show that the imaging network based on deep convolutional autoencoder exhibits excellent imaging performance when processing both numerical models.For simple objects,the model can accurately locate and preliminarily reconstruct the shape of the object,with an average relative error of 0.3012,while for the stroke models,it can effectively reconstruct the location and shape of the stroke area,and preliminarily reconstruct other brain tissues,with an average relative error of 0.077 8.The microwave imaging network based on deep convolutional autoencoder has great promise for fast and accurate image reconstruction,and the numerical example of stroke detection demonstrates its significant application potential in biomedical imaging.

A deep learning based microwave imaging model which can directly map the scattered electric field to the dielectric property distribution image of the target object is developed,and its potential for medical applications is explored.The two-dimensional time-domain finite difference method is used for numerical simulation to obtain a dataset of scattered electric fields;a deep convolutional autoencoder based imaging model is constructed to perform imaging studies on two types of target objects;the imaging results are quantitatively evaluated using relative error,and the model's ability to distinguish different types of strokes is also analyzed.The results show that the imaging network based on deep convolutional autoencoder exhibits excellent imaging performance when processing both numerical models.For simple objects,the model can accurately locate and preliminarily reconstruct the shape of the object,with an average relative error of 0.3012,while for the stroke models,it can effectively reconstruct the location and shape of the stroke area,and preliminarily reconstruct other brain tissues,with an average relative error of 0.077 8.The microwave imaging network based on deep convolutional autoencoder has great promise for fast and accurate image reconstruction,and the numerical example of stroke detection demonstrates its significant application potential in biomedical imaging.

Objective To investigate the protective effects of ulinastatin on express of GRP 78、CHOP and caspase-12, the molecules related to endoplasmic reticulum stress (ERS),after ischemia reperfusion injury in rats.Methods Ninety rats were equally randomized into 3 groups(n=30): Sham group (S group,n=30), Ischemia -reperfusion group (I/R group, n=30), Ulinastatin group (U group, n=30).Focal transient cerebral ischemia model was established with intralu-minal occlusion fo left meddle cerebral artery .Made through 2 hours of temporary middle cerebral artery occlusion , followed with 24 hours of reperfusion .The pathological results were investigated by HE staining and the cerebral injury situation was e -valuated by neurological deficit scores .Infract volume was measured by TTC staining , apoptosis was detected by TdT -medi-ated dUTP and nick end labeling (TUNEL), and expression of GRP78, CHOP and caspase -12 were meastured by western blot.Results Compared with the S group , the number of apoptotic cells were significantly increase in I /R group and U group (P<0.05);infarct volume and expression of GRP -78, CHOP and caspase-12 were significantly increased in I/R group and U group (P<0.05).The infarct volume and the number of apoptotic cells were significantly less in U group than in I/R group ( P<0.05 ) .GRP78 expression was higher in U group than in I/R group ( P<0.05 ) , however CHOP and caspase-12 expression was less in U group than in I/R group (P<0.05).Conclusion Ulinastatin has a protective effect on cerebral ischemia reperfusion injury , which may related to increased GRP 78, decreased CHOP and caspase -12 expres-sion and to inhibition of the ERS -induced apoptosis pathway .