AUTHOR=Liu Xindong , Wang Mengnan , Aftab Rukhma 

TITLE=Study on the Prediction Method of Long-term Benign and Malignant Pulmonary Lesions Based on LSTM

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2022.791424

DOI=10.3389/fbioe.2022.791424

ISSN=2296-4185

ABSTRACT=In order to more accurately and comprehensively characterize the changes and develop- ment rules of lesion characteristics in pulmonary medical images in different periods, the study was conducted to predict the evolution of pulmonary nodules in the longitudinal dimension of time, and a benign and malignant prediction model of pulmonary lesions in different periods was constructed under multi-scale 3-dimensional feature fusion. Ac- cording to the sequence of CT images of patients at different stages, three-dimensional interpolation was conducted to generate three-dimensional lung CT images. 3D features of different size lesions in the lungs were extracted using 3DCNNs for fusion features. A time-modulated LSTM was constructed to predict the benign and malignant lesions by using the improved time-length memory method to learn the feature vectors of lung lesions with temporal and spatial characteristics in different periods. The experiment shows that the AUC of the proposed method is 92.71%, which is higher than the traditional method.