New coronal pneumonia patient rehabilitation time prediction method and system based on deep learning
user-607cde9d4c775e0497f57189(2020)
Abstract
The invention discloses a new coronavirus pneumonia patient rehabilitation time prediction method and system based on deep learning. The method comprises the steps: obtaining multi-day CT sequence images of a new coronavirus pneumonia patient, and carrying out the preprocessing of the multi-day CT sequence images; respectively inputting into a lung lobe segmentation model and a pneumonia segmentation model, and respectively extracting the lung lobe region area and the lesion region area of multiple days; calculating according to the ratio of the lesion area to the lung lobe area for multiple days to obtain a lesion area ratio value for multiple days; and fitting a Gaussian process model by using the lesion area proportion R of multiple days to predict the rehabilitation time of the novel coronavirus pneumonia patient. According to the lung lobe and pneumonia region segmentation method, the Densenet is used as the DeepLab V3 + framework and the 3D UNet framework of the backbone to segment the lung lobe and pneumonia region, the segmentation is quick and effective, the Gaussian process can accurately predict the rehabilitation time of the patient, and a reference is provided for medical resource allocation.
MoreTranslated text
Key words
Pneumonia,Segmentation,Lesion,Coronavirus,Coronal plane,Radiology,Rehabilitation,Deep learning,Medicine,Artificial intelligence,Multiple days
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined