Deep learning SPECT lung perfusion image classification method based on attention mechanism

Abstract

SPECT lung perfusion is an important functional imaging technology. It can capture the functional lesions of the lung in a non-invasive manner and has become an important clinical detection method for diseases such as pulmonary embolism. In order to realize the automatic detection of the degree of pulmonary embolism, this paper studies and constructs a deep classification model based on the attention mechanism. First, the normalization technique is used to convert the original lung perfusion file into a SPECT image; secondly, in view of the over-fitting phenomenon of the deep learning model caused by the small amount of medical image data and the unbalanced data, the image translation and rotation techniques are used to perform effective expansion; then, in order to improve the model’s feature extraction ability, the attention mechanism is combined with the depth classification model to build a SPECT lung perfusion image classification model; finally, a set of real SPECT lung perfusion images were used to carry out comparative experiments on various depth classification models. The experimental results show that the model proposed in this paper can effectively detect the extent of lung disease lesions, and the classification accuracy rate exceeds 88%, which verifies the effectiveness and reliability of the classification model.