CVLGSep 8, 2024

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

arXiv:2409.05200v16 citationsh-index: 1
Originality Incremental advance
AI Analysis

This addresses the challenge of detecting rare lung nodules in clinical CT data, which is crucial for early cancer diagnosis, but it is incremental as it adapts existing methods to a specific domain.

The paper tackled lung nodule detection in CT scans by reframing it as an anomaly detection problem to handle sparse nodule occurrences, achieving state-of-the-art performance with an F1 score of 94.2% on the LUNA16 dataset.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes