SPCF-YOLO: An Efficient Feature Optimization Model for Real-Time Lung Nodule Detection
- 2 June 2025
- journal article
- research article
- Published by Springer Nature in Interdisciplinary Sciences: Computational Life Sciences
- Vol. 18 (1) , 231-252
Abstract
Accurate pulmonary nodule detection in CT imaging remains challenging due to fragmented feature integration in conventional deep learning models. This paper proposes SPCF-YOLO, a real-time detection framework that synergizes hierarchical feature fusion with anatomical context modeling. First, the space-to-depth convolution (SPDConv) module preserves fine-grained features in low-resolution images through spatial dimension reorganization. Second, the shared feature pyramid convolution (SFPConv) module is designed to dynamically extract multi-scale contextual information using multi-dilation-rate convolutional layers. Incorporating a small object detection layer aims to improve sensitivity to small nodules. This is achieved in combination with the improved pyramid squeeze attention (PSA) module and the improved contextual transformer (CoTB) module, which enhance global channel dependencies and reduce feature loss. The model achieves 82.8% mean average precision (mAP) and 82.9% F1 score on LUNA16 at 151 frames per second (representing improvements of 17.5% and 82.9% over YOLOv8 respectively), demonstrating real-time clinical viability. Cross-modality validation on SIIM-COVID-19 shows 1.5% improvement, confirming robust generalization. Graphical AbstractKeywords
Funding Information
- National Natural Science Foundation of China (Nos.62272418)
- National Natural Science Foundation of China (62102058)
- Basic Public Welfare Research Program of Zhejiang Province (No.LGG18E050011)
- Major Open Project of Key Laboratory for Advanced Design and Intelligent Computing of the Ministry of Education (ADIC2023ZD001)
This publication has 51 references indexed in Scilit:
- SF2T:Leveraging Swin Transformer and Two-stream networks for lung nodule detectionBiomedical Signal Processing and Control, 2024
- Nodule-CLIP: Lung nodule classification based on multi-modal contrastive learningComputers in Biology and Medicine, 2024
- Random vector functional link network: Recent developments, applications, and future directionsApplied Soft Computing, 2023
- N-Net: an UNet architecture with dual encoder for medical image segmentationSignal, Image and Video Processing, 2023
- The 2021 SIIM-FISABIO-RSNA Machine Learning COVID-19 Challenge: Annotation and Standard Exam Classification of COVID-19 Chest RadiographsJournal of Digital Imaging, 2022
- Quantifying the impact of Pyramid Squeeze Attention mechanism and filtering approaches on Alzheimer's disease classificationComputers in Biology and Medicine, 2022
- Lung Nodule Detection based on Faster R-CNN FrameworkComputer Methods and Programs in Biomedicine, 2021
- Lung Nodule Detection based on Ensemble of Hand Crafted and Deep FeaturesJournal of Medical Systems, 2019
- Automated lung nodule detection and classification based on multiple classifiers votingMicroscopy Research and Technique, 2019
- SSD: Single Shot MultiBox Detector2016