MSDet: Receptive Field Enhanced Multiscale Detection for Tiny Pulmonary Nodule

2024-09-21

arXiv.org

AI Summary

To address the high false-negative and false-positive rates in detecting tiny pulmonary nodules (≤6 mm) in chest CT scans, this paper proposes a Multi-Scale Receptive Field Enhancement Network (MRFEN). Methodologically, we introduce an Extended Receptive Domain (ERD) strategy to mitigate fine-detail loss during downsampling; design a Position-Channel Joint Attention Mechanism (PCAM) to strengthen contextual modeling; and incorporate a lightweight Tiny Object Detection Branch (TODB) for voxel-level end-to-end detection. Unlike conventional FPN-based architectures, MRFEN enables dynamic receptive field expansion and adaptive multi-scale feature fusion. Evaluated on the LUNA16 benchmark, MRFEN achieves a new state-of-the-art mean Average Precision (mAP), outperforming YOLOv8 by 8.8%. It significantly improves both detection sensitivity and localization accuracy for sub-centimeter nodules, offering a clinically deployable AI-assisted solution for early lung cancer screening.

Technology Category

• Computer Vision: Object Detection & Categorization
• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Pulmonary nodules are critical indicators for the early diagnosis of lung cancer, making their detection essential for timely treatment. However, traditional CT imaging methods suffered from cumbersome procedures, low detection rates, and poor localization accuracy. The subtle differences between pulmonary nodules and surrounding tissues in complex lung CT images, combined with repeated downsampling in feature extraction networks, often lead to missed or false detections of small nodules. Existing methods such as FPN, with its fixed feature fusion and limited receptive field, struggle to effectively overcome these issues. To address these challenges, our paper proposed three key contributions: Firstly, we proposed MSDet, a multiscale attention and receptive field network for detecting tiny pulmonary nodules. Secondly, we proposed the extended receptive domain (ERD) strategy to capture richer contextual information and reduce false positives caused by nodule occlusion. We also proposed the position channel attention mechanism (PCAM) to optimize feature learning and reduce multiscale detection errors, and designed the tiny object detection block (TODB) to enhance the detection of tiny nodules. Lastly, we conducted thorough experiments on the public LUNA16 dataset, achieving state-of-the-art performance, with an mAP improvement of 8.8% over the previous state-of-the-art method YOLOv8. These advancements significantly boosted detection accuracy and reliability, providing a more effective solution for early lung cancer diagnosis. The code will be available at https://github.com/CaiGuoHui123/MSDet

Problem

• Lung Nodule Detection
• Computed Tomography (CT) Images
• Early Lung Cancer Diagnosis

Innovation

• MSDet
• Enhanced Region Detection (ERD)
• Position-aware Channel Attention Mechanism (PCAM)