Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classification

TL;DR

This paper presents an efficient, partially explainable deep learning model for pulmonary nodule classification that uses neural architecture search, attention modules, and ensemble methods, achieving high accuracy with significantly fewer parameters.

Contribution

It introduces a neural architecture search-based approach combined with attention mechanisms and ensemble learning for efficient and explainable pulmonary nodule classification.

Findings

Achieves comparable performance with less than 1/40 parameters of previous models.

Uses attention modules to enhance interpretability of the model.

Ensemble of diverse networks improves accuracy and robustness.

Abstract

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.