SDF-Net: A Hybrid Detection Network for Mediastinal Lymph Node Detection on Contrast CT Images

TL;DR

This paper introduces SDF-Net, a hybrid detection network that combines segmentation and detection features with an auto-fusion module and shape-adaptive Gaussian kernels to improve mediastinal lymph node detection in contrast CT images.

Contribution

The paper presents a novel hybrid network architecture with feature fusion and shape-adaptive kernels for better lymph node detection without requiring mask annotations.

Findings

Demonstrates improved detection accuracy over existing methods.

Effectively handles lymph nodes of various shapes and sizes.

Provides promising results in complex detection scenarios.

Abstract

Accurate lymph node detection and quantification are crucial for cancer diagnosis and staging on contrast-enhanced CT images, as they impact treatment planning and prognosis. However, detecting lymph nodes in the mediastinal area poses challenges due to their low contrast, irregular shapes and dispersed distribution. In this paper, we propose a Swin-Det Fusion Network (SDF-Net) to effectively detect lymph nodes. SDF-Net integrates features from both segmentation and detection to enhance the detection capability of lymph nodes with various shapes and sizes. Specifically, an auto-fusion module is designed to merge the feature maps of segmentation and detection networks at different levels. To facilitate effective learning without mask annotations, we introduce a shape-adaptive Gaussian kernel to represent lymph node in the training stage and provide more anatomical information for effective learning. Comparative results demonstrate promising performance in addressing the complex lymph node detection problem.