The lack of labeled image data poses a serious challenge to the application of artificial intelligence(AI)in medical image diagnosis.Medical image notes contain valuable patient information that could be used to label...The lack of labeled image data poses a serious challenge to the application of artificial intelligence(AI)in medical image diagnosis.Medical image notes contain valuable patient information that could be used to label images for machine learning tasks.However,most image note texts are unstructured with heterogeneity and short-paragraph characters,which fail traditional keyword-based techniques.We utilized a deep learning approach to recover missing labels for medical image notes automatically by using a combination of deep word embedding and deep neural network classifiers.Bidirectional encoder representations from transformers trained on medical image notes corpus(MinBERT)were proposed.We applied the proposed techniques to two typical classification tasks:Medical image type identification and clinical diagnosis identification.The two methods significantly outperformed baseline methods and presented high accuracies of 99.56%and 99.72%in image type identification and of 94.56%and 92.45%in clinical diagnosis identification.Visualization analysis further indicated that word embedding could efficiently capture semantic similarities and regularities across diverse expressions.Results indicated that our proposed framework could accurately recover the missing label information of medical images through the automatic extraction of electronic medical record information.Hence,it could serve as a powerful tool for exploring useful training data in various medical AI applications.展开更多
Atorvastatin, a lipid-lowering medication, provides neuroprotective effects, although the precise mechanisms of action remain unclear. Our previous studies confirmed activated autophagy following spinal cord injury, w...Atorvastatin, a lipid-lowering medication, provides neuroprotective effects, although the precise mechanisms of action remain unclear. Our previous studies confirmed activated autophagy following spinal cord injury, which was conducive to recovery of neurological functions. We hypothesized that atorvastatin could also activate autophagy after spinal cord injury, and subsequently improve recovery of neurological functions. A rat model of spinal cord injury was established based on the Allen method. Atorvastatin(5 mg/kg) was intraperitoneally injected at 1 and 2 days after spinal cord injury. At 7 days post-injury, western blot assay, reverse transcription-polymerase chain reaction, and terminal deoxynucleotidyl transferase-mediated dU TP nick-end labeling(TUNEL) staining results showed increased Beclin-1 and light chain 3B gene and protein expressions in the spinal cord injury + atorvastatin group. Additionally, caspase-9 and caspase-3 expression was decreased, and the number of TUNEL-positive cells was reduced. Compared with the spinal cord injury + saline group, Basso, Beattie, and Bresnahan locomotor rating scale scores significantly increased in the spinal cord injury + atorvastatin group at 14–42 days post-injury. These findings suggest that atorvastatin activated autophagy after spinal cord injury, inhibited apoptosis, and promoted recovery of neurological function.展开更多
基金This work was supported in part by the Shenzhen Science and Technology Program(No.JCYJ20180703145002040)the Strategic Priority Research Program of Chinese Academy of Sciences(No.XDB38050100)the Shenzhen Science and Technology Program(No.JCYJ20180507182818013).
文摘The lack of labeled image data poses a serious challenge to the application of artificial intelligence(AI)in medical image diagnosis.Medical image notes contain valuable patient information that could be used to label images for machine learning tasks.However,most image note texts are unstructured with heterogeneity and short-paragraph characters,which fail traditional keyword-based techniques.We utilized a deep learning approach to recover missing labels for medical image notes automatically by using a combination of deep word embedding and deep neural network classifiers.Bidirectional encoder representations from transformers trained on medical image notes corpus(MinBERT)were proposed.We applied the proposed techniques to two typical classification tasks:Medical image type identification and clinical diagnosis identification.The two methods significantly outperformed baseline methods and presented high accuracies of 99.56%and 99.72%in image type identification and of 94.56%and 92.45%in clinical diagnosis identification.Visualization analysis further indicated that word embedding could efficiently capture semantic similarities and regularities across diverse expressions.Results indicated that our proposed framework could accurately recover the missing label information of medical images through the automatic extraction of electronic medical record information.Hence,it could serve as a powerful tool for exploring useful training data in various medical AI applications.
基金supported by the National Natural Science Foundation of China,No.81471854
文摘Atorvastatin, a lipid-lowering medication, provides neuroprotective effects, although the precise mechanisms of action remain unclear. Our previous studies confirmed activated autophagy following spinal cord injury, which was conducive to recovery of neurological functions. We hypothesized that atorvastatin could also activate autophagy after spinal cord injury, and subsequently improve recovery of neurological functions. A rat model of spinal cord injury was established based on the Allen method. Atorvastatin(5 mg/kg) was intraperitoneally injected at 1 and 2 days after spinal cord injury. At 7 days post-injury, western blot assay, reverse transcription-polymerase chain reaction, and terminal deoxynucleotidyl transferase-mediated dU TP nick-end labeling(TUNEL) staining results showed increased Beclin-1 and light chain 3B gene and protein expressions in the spinal cord injury + atorvastatin group. Additionally, caspase-9 and caspase-3 expression was decreased, and the number of TUNEL-positive cells was reduced. Compared with the spinal cord injury + saline group, Basso, Beattie, and Bresnahan locomotor rating scale scores significantly increased in the spinal cord injury + atorvastatin group at 14–42 days post-injury. These findings suggest that atorvastatin activated autophagy after spinal cord injury, inhibited apoptosis, and promoted recovery of neurological function.