3DAGNet: 3D Deep Attention and Global Search Network for Pulmonary Nodule Detection

Abstract

In traditional clinical medicine, respiratory physicians or radiologists often identify the location of lung nodules by highlighting targets in consecutive CT slices, which is labor-intensive and easy-to-misdiagnose work. To achieve intelligent detection and diagnosis of CT lung nodules, we designed a 3D convolutional neural network, called 3DAGNet, for pulmonary nodule detection. Inspired by the diagnostic process of lung nodule localization by physicians, the 3DGNet includes a spatial attention and a global search module. A multi-scale cascade module has also been introduced to enhance the model detection using attention enhancement, global information search, and contextual feature fusion. The experimental results showed that the proposed network achieved accurate detection of lung nodule information, and our method achieves a high sensitivity of 88.08% of the average FROC score on the LUNA16 dataset. In addition, ablation experiments also demonstrated the effectiveness of our method.

Attention Mechanisms in Convolutional Neural Networks for Nitrogen Treatment Detection in Tomato Leaves Using Hyperspectral Images

“…In terms of SSC estimation, the classifier achieved a coefficient of determination (R 2 ) of 0.901, and for firmness estimation, the classifier achieved an R 2 of 0.532. Other recent works have proposed the use of CNN networks using different types of sensors adapted to the specific needs of each application, such as computed tomography [16], Doppler radar [17], and EEG signals [18].…”