Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classification

19 Jan 2021  ·  Hanliang Jiang, Fuhao Shen, Fei Gao, Weidong Han ·

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.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Neural Architecture Search LIDC-IDRI NASLung (ours) Specificity (VEB+) 95.04 # 1
F1 score 0.8929 # 1
Lung Nodule Classification LIDC-IDRI NASLung (ours) Accuracy 90.77 # 4

Methods


No methods listed for this paper. Add relevant methods here