Article Details

Title · Authors · Abstract · Keywords · DOI · References

Pulmonary Nodule Detection Algorithm Based on Improved YOLOv8s

GUO Xiangjun, JIANG Chaogen

(School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China)

Section：Artificial Intelligence · Vol. 2025, Issue 7 · Pages：87-92 · 2096-4706（2025）07-0087-06 · CLC number：TP391.4；TP183 · Document code：A · DOI：10.19850/j.cnki.2096-4706.2025.07.016

Abstract

Lung cancer has become one of the common cancers with high mortality worldwide. Pulmonary nodules are the early manifestations of lung cancer. Aiming at the difficulty of pulmonary nodule detection in CT images, a pulmonary nodule detection algorithm based on improved YOLOv8s is proposed. The backbone network uses improved YOLOv8s, and uses Space-to-Depth Convolution to replace the traditional step-size convolution and pooling layer to avoid the loss of fine-grained information caused by step-size convolution and pooling layer when processing low-resolution images or small objects. The coordinate attention module is added to consider the inter-channel relationship and position information of the pulmonary nodule image, so that the model can locate and identify the target area more accurately. Focal Loss is used to replace the cross-entropy loss function to solve the problem of small number of sample labels in the dataset. The adaptive activation function can not only improve the stability of the network, but also improve the accuracy of the network. The LUNA16 dataset is used to verify the performance of the algorithm. The detection accuracy of the improved pulmonary nodule detection algorithm reaches 77.8%, which is 3.7% and 8.6% higher than that of Faster R-CNN and YOLOv8s detection algorithms, respectively.

Keywords

pulmonary nodule detection; YOLOv8s; no more strided convolution; adaptive activation function; spatial attention mechanism

References

  1. [1] SHARMA P，MEHTA M，DHANJAL D S，et al. Emerging Trends in the Novel Drug Delivery Approaches for the Treatment of Lung Cancer [J/OL].Chemico-Biological Interactions，2019，309：108720[2024-10-03]. https://doi.org/10.1016/j.cbi.2019.06.033.
  2. [2] SCHABATH M B，COTE M L. Cancer Progress and Priorities: Lung Cancer [J]. Cancer Epidemiology, Biomarkers & Prevention，2019，28（10）：1563-1579.
  3. [3] GIRSHICK R，DONAHUE J，DARRELL T，et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation [C]//2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus：IEEE，2014：580-587.
  4. [4] GIRSHICK R. Fast R-CNN [C]//2015 IEEE International Conference on Computer Vision (ICCV).Santiago：IEEE，2015：1440-448.
  5. [5] LIU W，ANGUELOV D，ERHAN D，et al. SSD: Single Shot MultiBox Detector [C]//Computer Vision - ECCV 2016.Amsterdam：Springer，2016：21-37.
  6. [6] TERVEN J，CÓRDOVA-ESPARZA D M，ROMERO-GONZÁLEZ J A. A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS [J].Machine Learning & Knowledge Extraction，2023，5（4）：1680-1716.
  7. [7] ZHU X Z，SU W J，LU L W，et al. Deformable DETR: Deformable Transformers for End-to-End Object Detection [J/OL].arXiv:2010.04159 [cs.CV].[2024-09-22].https://doi.org/10.48550/arXiv.2010.04159.
  8. [8] VARGHESE R，SAMBATH M.YOLOv8: A Novel Object Detection Algorithm with Enhanced Performance and Robustness [C]//2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS).Chennai：IEEE，2024：1-6.
  9. [9] SUNKARA R，LUO T. No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects [C]//Machine Learning and Knowledge Discovery in Databases.Grenoble：Springer，2022：443-459.
  10. [10] HOU Q B，ZHOU D Q，FENG J S. Coordinate Attention for Efficient Mobile Network Design [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Nashville：IEEE，2021：13713-13722.
  11. [11] ROSS T Y，DOLLÁR G. Focal Loss for Dense Object Detection [C]//IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，4（2）：2980-2988.
  12. [12] MA N N，ZHANG X Y，LIU M，et al. Activate or Not: Learning Customized Activation [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Nashville：2021：8032-8042.

About the authors

Guo Xiangjun (1997-), male, Han ethnicity, from Kaizhou, Chongqing, currently pursuing a master's degree in computer vision; Corresponding author: Jiang Chaogen (1960-), male, Han ethnicity, from Jinhua, Zhejiang, professor, master's degree, research direction: embedded systems and their applications, wireless sensor networks.