Ewha Med J.
2025 Apr;48(2):e30. 10.12771/emj.2025.00094.
Development of automatic organ segmentation based on positron-emission tomography analysis system using Swin UNETR in breast cancer patients in Korea
- Affiliations
-
- 1Department of Medicine, Yonsei University College of Medicine, Seoul, Korea
- 2Medical Physics and Biomedical Engineering Lab, Yonsei University College of Medicine, Seoul, Korea
- 3Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Korea
- 4Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Korea
- 5Medical Image and Radiotherapy Lab, Korea Advanced Institute of Science and Technology, Daejeon, Korea
- 6Department of Nuclear Medicine, Ewha Womans University School of Medicine, Seoul, Korea
- 7Department of Biomedical Engineering, Ewha Womans University College of Medicine, Seoul, Korea
- 8Ewha Medical Research Institute, Ewha Womans University College of Medicine, Seoul, Korea
- 9Ewha Medical Artificial Intelligence Research Institute, Ewha Womans University College of Medicine, Seoul, Korea
- KMID: 2567582
- DOI: http://doi.org/10.12771/emj.2025.00094
Abstract
- Purpose
The standardized uptake value (SUV) is a key quantitative index in nuclear medicine imaging; however, variations in region‐of‐interest (ROI) determination exist across institutions. This study aims to standardize SUV evaluation by introducing a deep learning‐based quantitative analysis method that enhances diagnostic and prognostic accuracy.
Methods
We used the Swin UNETR model to automatically segment key organs (breast, liver, spleen, and bone marrow) critical for breast cancer prognosis. Tumor segmentation was performed iteratively based on predefined SUV thresholds, and prognostic information was extracted from the liver, spleen, and bone marrow (reticuloendothelial system). The artificial intelligence training process employed 3 datasets: a test dataset (40 patients), a validation dataset (10 patients), and an independent test dataset (10 patients). To validate our approach, we compared the SUV values obtained using our method with those produced by commercial software.
Results
In a dataset of 10 patients, our method achieved an auto‐segmentation accuracy of 0.9311 for all target organs. Comparison of maximum SUV and mean SUV values from our automated segmentation with those from traditional single‐ROI methods revealed differences of 0.19 and 0.16, respectively, demonstrating improved reliability and accuracy in whole‐organ SUV analysis.
Conclusion
This study successfully standardized SUV calculation in nuclear medicine imaging through deep learning‐based automated organ segmentation and SUV analysis, significantly enhancing accuracy in predicting breast cancer prognosis.
- Full Text Links
-
- Actions
-
Cited
- CITED
-
- Close
- Share
-
- Similar articles
-
- Extensive Multilabel Classification of Brain MRI Scans for Infarcts Using the Swin UNETR Architecture in Deep Learning Applications
- Occult Invasive Lobular Carcinoma of Breast Detected by Stomach Metastasis: A Case Report
- Definition of Tumor Volume Based on 18F-Fludeoxyglucose Positron Emission Tomography in Radiation Therapy for Liver Metastases: An Relational Analysis Study between Image Parameters and Image Segmentation Methods
- Potential Clinical Applications of ¹â¸F-Fluorodeoxyglucose Positron Emission Tomography/Magnetic Resonance Mammography in Breast Cancer
- 18F-2-Deoxy-2-Fluoro-D-Glucose Positron Emission Tomography: Computed Tomography for Preoperative Staging in Gastric Cancer Patients
