A Shape-Aware Lightweight Framework for Real-Time Object Detection in Nuclear Medicine Imaging Equipment
Source abstract
Abstract
Manual calibration of nuclear medicine scanners currently relies on handling phantoms containing radioactive sources, exposing personnel to high radiation doses and elevating cancer risk. We designed an automated detection framework for robotic inspection on the YOLOv8n foundation. It pairs a lightweight backbone with a shape-aware geometric attention module and an anchor-free head. Facing a small training set, we produced extra images with a GAN and then fine-tuned a pretrained network on these augmented data. Evaluations on a custom dataset consisting of PET/CT gantry and table images showed that the SAM-YOLOv8n model achieved a precision of 93.6% and a recall of 92.8%. These results demonstrate fast, accurate, real-time detection, offering a safer and more efficient alternative to manual calibration of nuclear medicine equipment.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Advanced X-ray and CT Imaging · Medical Image Segmentation Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China
Jiangsu Institute of Metrology, Nanjing 210023, China
College of Automation & College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing 210023, China
Funding
Science and Technology Program of State Administration for Market Regulation of China
References (51)
Show source-provided references
1. Yao, Y., Tian, J., Zhang, R., Liu, P., Gao, X., Zhou, W., and Luo, L. (2025). Nanobody-Based Radiotracers in Nuclear Medicine: Advances, Challenges, and Future Perspectives. Chin. Chem. Lett.10.1016/j.cclet.2025.111517 ↗
2. Lee, J., and Kim, T. (2025). Current Status and Future Perspectives of Nuclear Medicine in Prostate Cancer from Imaging to Therapy: A Comprehensive Review. Biomedicines, 13.10.3390/biomedicines13051132 ↗
3. Smolyarchuk Equipment Quality Control during Patient Radiation Protection Optimisation in Radionuclide Diagnostics10.21514/1998-426X-2023-16-3-81-90 ↗
4. Landscape of Nuclear Medicine in China and Its Progress on Theranostics10.2967/jnumed.123.266968 ↗
5. Bayareh-Mancilla, R., Medina-Ramos, L.A., Toriz-Vázquez, A., Hernández-Rodríguez, Y.M., and Cigarroa-Mayorga, O.E. (2023). Automated Computer-Assisted Medical Decision-Making System Based on Morphological Shape and Skin Thickness Analysis for Asymmetry Detection in Mammographic Images. Diagnostics, 13.10.3390/diagnostics13223440 ↗
6. The Quality Assurance for the PET/CT in Nuclear Medicine—Evaluation of the Daily Quality Control of The Positron Emission Tomography10.13005/bpj/2497 ↗
7. Ansari, S., Ansari, A., Shaikh, F.A.A., Patne, S., Sheikh, S., Joseph, S., Malik, M.A.A.S., and Khan, N. (2024, January 7–9). From Legacy Systems to Intelligent Automation: Bridging the Gap in Industrial Applications (A Survey). Proceedings of the International Conference on Industrial Engineering and Operations Management, Hyderabad, India.10.46254/IN04.20240053 ↗
8. Computer Vision-Based Robotic Arm for Object Color, Shape, and Size Detection10.18196/jrc.v3i2.13906 ↗
9. The Vision-Based Target Recognition, Localization, and Control for Harvesting Robots: A Review10.1007/s12541-023-00911-7 ↗
10. Vision-Based Target Detection and Positioning Approach for Underwater Robots10.1109/JPHOT.2023.3334263 ↗
11. Real-Time Object Detection Using a Lightweight Two-Stage Detection Network with Efficient Data Representation
12. Real-Time Object Detection Using Deep Learning10.22214/ijraset.2022.42820 ↗
13. Deep Learning-Based Drone Detection in Infrared Imagery with Limited Training Data
14. Deep Learning for Breast MRI Style Transfer with Limited Training Data10.1007/s10278-022-00755-z ↗
15. Training Strategies for Radiology Deep Learning Models in Data-Limited Scenarios10.1148/ryai.2021210014 ↗
16. Real-Time Robotic Mirrored Behavior of Facial Expressions and Head Motions Based on Lightweight Networks10.1109/JIOT.2022.3205123 ↗
17. Mwitta, C., Rains, G.C., and Prostko, E. (2024). Evaluation of Inference Performance of Deep Learning Models for Real-Time Weed Detection in an Embedded Computer. Ital. Natl. Conf. Sens., 2.10.3390/s24020514 ↗
18. Fathurrahman, A., Bejo, A., and Ardiyanto, I. (2022, January 29–30). Lightweight Convolution Neural Network for Image-Based Malware Classification on Embedded Systems. Proceedings of the 2021 International Seminar on Machine Learning, Optimization, and Data Science (ISMODE), Jakarta, Indonesia.10.1109/ISMODE53584.2022.9743111 ↗
19. Sun, Q., Li, P., He, C., Song, Q., Chen, J., Kong, X., and Luo, Z. (2024). A Lightweight and High-Precision Passion Fruit YOLO Detection Model for Deployment in Embedded Devices. Sensors, 24.10.20944/preprints202405.1950.v1 ↗
20. Beckham, C., Laradji, I., López, P.R., Vázquez, D., Nowrouzezahrai, D., and Pal, C. (2022). Overcoming Challenges in Leveraging GANs for Few-Shot Data Augmentation. arXiv.
21. Li, S., Yue, C., and Zhou, H. (2025). Few-Shot Face Recognition: Leveraging GAN for Effective Data Augmentation. Electronics, 14.10.3390/electronics14102003 ↗
22. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
23. Jocher, G.R., Liu, C., Hogan, A., Yu, L., Rai, P., and Sullivan, T. (2020). Ultralytics/Yolov5: Initial Release, Zenodo.
24. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23–28). End-to-End Object Detection with Transformers. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58452-8_13 ↗
25. Tian, Z., Shen, C., Chen, H., and He, T. (2019, January 27–28). FCOS: Fully Convolutional One-Stage Object Detection. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.10.1109/ICCV.2019.00972 ↗
26. A Comparative Analysis of Modern Object Detection Algorithms: YOLO vs. SSD vs. Faster R-CNN
27. Dahirou, Z., and Zheng, M. (2021, January 23–25). Motion Detection and Object Detection: Yolo (You Only Look Once). Proceedings of the 2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC), Guiyang, China.10.1109/ICNISC54316.2021.00053 ↗
28. A Comprehensive Survey on Object Detection YOLO
29. Ryspayeva, M., and Nishan, A. (2024, January 3–4). Enhancing Grayscale Image Synthesis with Deep Conditional GAN and Transfer Learning. Proceedings of the 2024 IEEE AITU: Digital Generation, Astana, Kazakhstan.10.1109/IEEECONF61558.2024.10585479 ↗
30. Güçlü, E., Akın, E., Aydın, İ., Topkaya, A., Onan, M., and Şener, T.K. (2024, January 17–19). Real-Time Detection of Terminal Burn Defects Using YOLOv7 and TensorRT. Proceedings of the 2024 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), Sakhir, Bahrain.10.1109/3ict64318.2024.10824255 ↗
31. Belhaoua, A., Kimpe, T.R., Crul, S., Rettmann, M.E., and Siewerdsen, J.H. (2024, January 18–22). TensorRT-Based Surgical Instrument Detection Assessment for Deep Learning on Edge Computing. Proceedings of the Image-Guided Procedures, Robotic Interventions, and Modeling, San Diego, CA, USA.10.1117/12.3004788 ↗
32. B, G.P., G, R.M.L., Rishekeeshan, A. (2024, January 16–18). Accelerating Native Inference Model Performance in Edge Devices Using TensorRT. Proceedings of the 2024 IEEE Recent Advances in Intelligent Computational Systems (RAICS), Kothamangalam, India.10.1109/RAICS61201.2024.10690032 ↗
33. Evaluating the Efficacy of Deep Learning Architectures in Predicting Traffic Patterns for Smart City Development10.54216/JAIM.060203 ↗
34. Efficacy of Deep Learning Models in the Prognosis Task10.1149/10701.15207ecst ↗
35. Wang, W., Chen, W., Luo, Y., Long, Y., Lin, Z., Zhang, L., Lin, B., Cai, D., and He, X. (2024). Model Compression and Efficient Inference for Large Language Models: A Survey. arXiv.
36. Multidimensional Pruning and Its Extension: A Unified Framework for Model Compression
37. Malihi, L., and Heidemann, G. (2023). Efficient and Controllable Model Compression through Sequential Knowledge Distillation and Pruning. Big Data Cogn. Comput., 7.10.3390/bdcc7030154 ↗
38. A Lightweight Road Traffic Sign Detection Algorithm Based on Adaptive Sparse Channel Pruning10.1088/1361-6501/ad9517 ↗
39. A Lightweight Real-Time System for Object Detection in Enterprise Information Systems for Frequency-Based Feature Separation10.4018/IJSWIS.330015 ↗
40. Towards a Complete and Detail-Preserved Salient Object Detection
41. Adaptive Edge-Aware Semantic Interaction Network for Salient Object Detection in Optical Remote Sensing Images
42. Cai, J., and Lin, S. (2020, January 6–8). A Novel Hybrid Model for Video Salient Object Detection. Proceedings of the 2020 International Conference on Computer Engineering and Intelligent Control (ICCEIC), Chongqing, China.10.1109/ICCEIC51584.2020.00059 ↗
43. EM-Trans: Edge-Aware Multimodal Transformer for RGB-D Salient Object Detection10.1109/TNNLS.2024.3358858 ↗
44. Thomas, H., Qi, C.R., Deschaud, J.-E., Marcotegui, B., Goulette, F., and Guibas, L.J. (November, January 27). KPConv: Flexible and Deformable Convolution for Point Clouds. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00651 ↗
45. Fast Parameter-Free Multi-View Subspace Clustering With Consensus Anchor Guidance10.1109/TIP.2021.3131941 ↗
46. FAA-Det: Feature Augmentation and Alignment for Anchor-Free Oriented Object Detection
47. Tong, L., Fan, C., Peng, Z., Wei, C., Sun, S., and Han, J. (2024). WTBD-YOLOv8: An Improved Method for Wind Turbine Generator Defect Detection. Sustainability, 16.10.3390/su16114467 ↗
48. Preclinical SPECT and PET: Joint EANM and ESMI Procedure Guideline for Implementing an Efficient Quality Control Programme10.1007/s00259-024-06824-5 ↗
49. Zhang, T., Jia, X., Cui, Y., and Zhang, H. (2025). GGD-YOLOv8n: A Lightweight Architecture for Edge-Computing-Optimized Allergenic Pollen Recognition with Cross-Scale Feature Fusion. Symmetry, 17.10.3390/sym17060849 ↗
50. Automated Real-Time Sugarcane Node Detection System Using YOLOv8 and Edge Computing10.22214/ijraset.2025.70235 ↗
51. Alomar, K., Aysel, H.I., and Cai, X. (2023). Data Augmentation in Classification and Segmentation: A Survey and New Strategies. J. Imaging, 9.10.3390/jimaging9020046 ↗