Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classification
This work addresses efficiency and explainability issues in lung cancer diagnosis models, which is incremental as it combines existing techniques like NAS and CBAM for a specific medical domain.
The authors tackled the problem of high computational complexity and lack of explainability in deep learning models for pulmonary nodule classification by developing an efficient and partially explainable model using neural architecture search and attention modules, achieving comparable performance with less than 1/40 parameters compared to previous state-of-the-art methods.
Automatic pulmonary nodules classification is significant for early diagnosis of lung cancers. Recently, deep learning techniques have enabled remarkable progress in this field. However, these deep models are typically of high computational complexity and work in a black-box manner. To combat these challenges, in this work, we aim to build an efficient and (partially) explainable classification model. Specially, we use \emph{neural architecture search} (NAS) to automatically search 3D network architectures with excellent accuracy/speed trade-off. Besides, we use the convolutional block attention module (CBAM) in the networks, which helps us understand the reasoning process. During training, we use A-Softmax loss to learn angularly discriminative representations. In the inference stage, we employ an ensemble of diverse neural networks to improve the prediction accuracy and robustness. We conduct extensive experiments on the LIDC-IDRI database. Compared with previous state-of-the-art, our model shows highly comparable performance by using less than 1/40 parameters. Besides, empirical study shows that the reasoning process of learned networks is in conformity with physicians' diagnosis. Related code and results have been released at: https://github.com/fei-hdu/NAS-Lung.