# Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classification

arXiv: https://arxiv.org/abs/2101.07429 · HTML: https://mlsanity.com/paper/2101.07429/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 41 references that are in the map.
- First posted on arXiv 19 Jan 2021.

## Builds on (most cited first, 14 of 14)

- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI](https://mlsanity.com/paper/1907.07374/) (2019)
- [Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?](https://mlsanity.com/paper/1706.00712/) (2017)
- [Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation](https://mlsanity.com/paper/1805.08298/) (2018)
- [End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis](https://mlsanity.com/paper/1901.10623/) (2019)
- [MDNet: A Semantically and Visually Interpretable Medical Image Diagnosis Network](https://mlsanity.com/paper/1707.02485/) (2017)
- [C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation](https://mlsanity.com/paper/1912.09628/) (2019)
- [Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search](https://mlsanity.com/paper/1903.03777/) (2019)
- [DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification](https://mlsanity.com/paper/1801.09555/) (2018)
- [On Exploring Undetermined Relationships for Visual Relationship Detection](https://mlsanity.com/paper/1905.01595/) (2019)
- [Scalable Neural Architecture Search for 3D Medical Image Segmentation](https://mlsanity.com/paper/1906.05956/) (2019)
- [Deep Learning for Lung Cancer Detection: Tackling the Kaggle Data Science Bowl 2017 Challenge](https://mlsanity.com/paper/1705.09435/) (2017)
- [Relational Learning between Multiple Pulmonary Nodules via Deep Set Attention Transformers](https://mlsanity.com/paper/2004.05640/) (2020)

## Built on by (most cited first, 7 of 7)

- [Learning from Ambiguous Labels for Lung Nodule Malignancy Prediction](https://mlsanity.com/paper/2104.11436/) (2021)
- [Prior-Guided One-shot Neural Architecture Search](https://mlsanity.com/paper/2206.13329/) (2022)
- [Believe The HiPe: Hierarchical Perturbation for Fast, Robust, and Model-Agnostic Saliency Mapping](https://mlsanity.com/paper/2103.05108/) (2021)
- [Probeable DARTS with Application to Computational Pathology](https://mlsanity.com/paper/2108.06859/) (2021)
- [M3Net: A Macro-to-Meso-to-Micro Clinical-inspired Hierarchical 3D Network for Pulmonary Nodule Classification](https://mlsanity.com/paper/2605.12570/) (2026)
- [Towards Reliable and Explainable AI Model for Solid Pulmonary Nodule Diagnosis](https://mlsanity.com/paper/2204.04219/) (2022)
- [DGSAN: Dual-Graph Spatiotemporal Attention Network for Pulmonary Nodule Malignancy Prediction](https://mlsanity.com/paper/2512.20898/) (2025)

## Abstract (arXiv)

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 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.