# Lung-DETR: Deformable Detection Transformer for Sparse Lung Nodule Anomaly Detection

arXiv: https://arxiv.org/abs/2409.05200 · HTML: https://mlsanity.com/paper/2409.05200/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 15 references that are in the map.
- First posted on arXiv 8 Sep 2024.

## Builds on (most cited first, 5 of 5)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [Automatic Pulmonary Nodule Detection in CT Scans Using Convolutional Neural Networks Based on Maximum Intensity Projection](https://mlsanity.com/paper/1904.05956/) (2019)
- [MetaFusion: Controlled False-Negative Reduction of Minority Classes in Semantic Segmentation](https://mlsanity.com/paper/1912.07420/) (2019)

## Built on by (most cited first, 3 of 3)

- [Fast Multi-Organ Fine Segmentation in CT Images with Hierarchical Sparse Sampling and Residual Transformer](https://mlsanity.com/paper/2511.08509/) (2025)
- [Nodule-DETR: A Novel DETR Architecture with Frequency-Channel Attention for Ultrasound Thyroid Nodule Detection](https://mlsanity.com/paper/2601.01908/) (2026)
- [Prior-Guided DETR for Ultrasound Nodule Detection](https://mlsanity.com/paper/2601.02212/) (2026)

## Abstract (arXiv)

Accurate lung nodule detection for computed tomography (CT) scan imagery is challenging in real-world settings due to the sparse occurrence of nodules and similarity to other anatomical structures. In a typical positive case, nodules may appear in as few as 3% of CT slices, complicating detection. To address this, we reframe the problem as an anomaly detection task, targeting rare nodule occurrences in a predominantly normal dataset. We introduce a novel solution leveraging custom data preprocessing and Deformable Detection Transformer (Deformable- DETR). A 7.5mm Maximum Intensity Projection (MIP) is utilized to combine adjacent lung slices into single images, reducing the slice count and decreasing nodule sparsity. This enhances spatial context, allowing for better differentiation between nodules and other structures such as complex vascular structures and bronchioles. Deformable-DETR is employed to detect nodules, with a custom focal loss function to better handle the imbalanced dataset. Our model achieves state-of-the-art performance on the LUNA16 dataset with an F1 score of 94.2% (95.2% recall, 93.3% precision) on a dataset sparsely populated with lung nodules that is reflective of real-world clinical data.