Pulmonary nodule detection method based on multi-data fusion, electronic equipment and storage medium
The invention discloses a pulmonary nodule detection method based on multi-data fusion, electronic equipment and a storage medium, and belongs to the technical field of medical image analysis. In order to improve the accuracy of lung nodule detection, lung CT image data are collected, six kinds of g...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a pulmonary nodule detection method based on multi-data fusion, electronic equipment and a storage medium, and belongs to the technical field of medical image analysis. In order to improve the accuracy of lung nodule detection, lung CT image data are collected, six kinds of gene state data and three kinds of medical history information data corresponding to each piece of lung CT image data are collected, and a multi-data fusion lung nodule detection data set is established; dividing into a training set and a test set according to a ratio of 8: 2; constructing a pulmonary nodule detection model based on multi-data fusion, the system comprises a ResNet50 module, a Bert1 module, a Bert2 module, a self-attention mechanism module, and a full connection layer and softmax layer module. Training the constructed pulmonary nodule detection model based on multi-data fusion by using the training set; and carrying out pulmonary nodule detection prediction on the trained pulmonary nodule detection m |
---|