# No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial Attacks

arXiv: https://arxiv.org/abs/2003.03824 · HTML: https://mlsanity.com/paper/2003.03824/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2020.

## Built on by (most cited first, 10 of 10)

- [Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges](https://mlsanity.com/paper/2303.14133/) (2023)
- [Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging](https://mlsanity.com/paper/2107.09543/) (2021)
- [MedRDF: A Robust and Retrain-Less Diagnostic Framework for Medical Pretrained Models Against Adversarial Attack](https://mlsanity.com/paper/2111.14564/) (2021)
- [Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs](https://mlsanity.com/paper/2208.12428/) (2022)
- [Medical Artificial Intelligence for Early Detection of Lung Cancer: A Survey](https://mlsanity.com/paper/2410.14769/) (2024)
- [Masked conditional variational autoencoders for chromosome straightening](https://mlsanity.com/paper/2306.14129/) (2023)
- [Lung-CADex: Fully automatic Zero-Shot Detection and Classification of Lung Nodules in Thoracic CT Images](https://mlsanity.com/paper/2407.02625/) (2024)
- [Generation of synthetic data using breast cancer dataset and classification with resnet18](https://mlsanity.com/paper/2405.16286/) (2024)
- [Improving Lung Cancer Diagnosis and Survival Prediction with Deep Learning and CT Imaging](https://mlsanity.com/paper/2408.09367/) (2024)
- [Controllable Lung Nodule Synthesis via Histogram-Regularized Latent Diffusion Models](https://mlsanity.com/paper/2605.30631/) (2026)

## Abstract (arXiv)

Detecting malignant pulmonary nodules at an early stage can allow medical interventions which may increase the survival rate of lung cancer patients. Using computer vision techniques to detect nodules can improve the sensitivity and the speed of interpreting chest CT for lung cancer screening. Many studies have used CNNs to detect nodule candidates. Though such approaches have been shown to outperform the conventional image processing based methods regarding the detection accuracy, CNNs are also known to be limited to generalize on under-represented samples in the training set and prone to imperceptible noise perturbations. Such limitations can not be easily addressed by scaling up the dataset or the models. In this work, we propose to add adversarial synthetic nodules and adversarial attack samples to the training data to improve the generalization and the robustness of the lung nodule detection systems. To generate hard examples of nodules from a differentiable nodule synthesizer, we use projected gradient descent (PGD) to search the latent code within a bounded neighbourhood that would generate nodules to decrease the detector response. To make the network more robust to unanticipated noise perturbations, we use PGD to search for noise patterns that can trigger the network to give over-confident mistakes. By evaluating on two different benchmark datasets containing consensus annotations from three radiologists, we show that the proposed techniques can improve the detection performance on real CT data. To understand the limitations of both the conventional networks and the proposed augmented networks, we also perform stress-tests on the false positive reduction networks by feeding different types of artificially produced patches. We show that the augmented networks are more robust to both under-represented nodules as well as resistant to noise perturbations.