Development of automatic organ segmentation based on positron-emission tomography analysis system using Swin UNETR in breast cancer patients in Korea
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 metho...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ewha Womans University College of Medicine
2025-04-01
|
| Series: | The Ewha Medical Journal |
| Subjects: | |
| Online Access: | http://www.e-emj.org/upload/pdf/emj-2025-00094.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849223032954945536 |
|---|---|
| author | Dong Hyeok Choi Joonil Hwang Hai-Jeon Yoon So Hyun Ahn |
| author_facet | Dong Hyeok Choi Joonil Hwang Hai-Jeon Yoon So Hyun Ahn |
| author_sort | Dong Hyeok Choi |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-df9cb9cf003e4bf0a90b3ab06caf0402 |
| institution | Kabale University |
| issn | 2234-3180 2234-2591 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Ewha Womans University College of Medicine |
| record_format | Article |
| series | The Ewha Medical Journal |
| spelling | doaj-art-df9cb9cf003e4bf0a90b3ab06caf04022025-08-26T00:04:46ZengEwha Womans University College of MedicineThe Ewha Medical Journal2234-31802234-25912025-04-0148210.12771/emj.2025.000941613Development of automatic organ segmentation based on positron-emission tomography analysis system using Swin UNETR in breast cancer patients in KoreaDong Hyeok Choi0Joonil Hwang1Hai-Jeon Yoon2So Hyun Ahn3Department of Medicine, Yonsei University College of Medicine, Seoul, KoreaDepartment of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology, Daejeon, KoreaDepartment of Nuclear Medicine, Ewha Womans University School of Medicine, Seoul, KoreaDepartment of Biomedical Engineering, Ewha Womans University College of Medicine, Seoul, KoreaPurpose 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.http://www.e-emj.org/upload/pdf/emj-2025-00094.pdfartificial intelligencebreast neoplasmsdeep learningpositron emission tomographyprognosisrepublic of korea |
| spellingShingle | Dong Hyeok Choi Joonil Hwang Hai-Jeon Yoon So Hyun Ahn Development of automatic organ segmentation based on positron-emission tomography analysis system using Swin UNETR in breast cancer patients in Korea The Ewha Medical Journal artificial intelligence breast neoplasms deep learning positron emission tomography prognosis republic of korea |
| title | Development of automatic organ segmentation based on positron-emission tomography analysis system using Swin UNETR in breast cancer patients in Korea |
| title_full | Development of automatic organ segmentation based on positron-emission tomography analysis system using Swin UNETR in breast cancer patients in Korea |
| title_fullStr | Development of automatic organ segmentation based on positron-emission tomography analysis system using Swin UNETR in breast cancer patients in Korea |
| title_full_unstemmed | Development of automatic organ segmentation based on positron-emission tomography analysis system using Swin UNETR in breast cancer patients in Korea |
| title_short | Development of automatic organ segmentation based on positron-emission tomography analysis system using Swin UNETR in breast cancer patients in Korea |
| title_sort | development of automatic organ segmentation based on positron emission tomography analysis system using swin unetr in breast cancer patients in korea |
| topic | artificial intelligence breast neoplasms deep learning positron emission tomography prognosis republic of korea |
| url | http://www.e-emj.org/upload/pdf/emj-2025-00094.pdf |
| work_keys_str_mv | AT donghyeokchoi developmentofautomaticorgansegmentationbasedonpositronemissiontomographyanalysissystemusingswinunetrinbreastcancerpatientsinkorea AT joonilhwang developmentofautomaticorgansegmentationbasedonpositronemissiontomographyanalysissystemusingswinunetrinbreastcancerpatientsinkorea AT haijeonyoon developmentofautomaticorgansegmentationbasedonpositronemissiontomographyanalysissystemusingswinunetrinbreastcancerpatientsinkorea AT sohyunahn developmentofautomaticorgansegmentationbasedonpositronemissiontomographyanalysissystemusingswinunetrinbreastcancerpatientsinkorea |