Transfer Learning for Effective Urolithiasis Detection
Purpose Urolithiasis is a common disease that can cause acute pain and complications. The objective of this study was to develop a deep learning model utilizing transfer learning for the rapid and accurate detection of urinary tract stones. By employing this method, we aim to improve the efficiency...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Korean Continence Society
2023-05-01
|
| Series: | International Neurourology Journal |
| Subjects: | |
| Online Access: | http://einj.org/upload/pdf/inj-2346110-055.pdf |
| _version_ | 1797809942279749632 |
|---|---|
| author | Hyoung-Sun Choi Jae-Seoung Kim Taeg-Keun Whangbo Khae Hawn Kim |
| author_facet | Hyoung-Sun Choi Jae-Seoung Kim Taeg-Keun Whangbo Khae Hawn Kim |
| author_sort | Hyoung-Sun Choi |
| collection | DOAJ |
| description | Purpose Urolithiasis is a common disease that can cause acute pain and complications. The objective of this study was to develop a deep learning model utilizing transfer learning for the rapid and accurate detection of urinary tract stones. By employing this method, we aim to improve the efficiency of medical staff and contribute to the progress of deep learning-based medical image diagnostic technology. Methods The ResNet50 model was employed to develop feature extractors for detecting urinary tract stones. Transfer learning was applied by utilizing the weights of pretrained models as initial values, and the models were fine-tuned with the provided data. The model’s performance was evaluated using accuracy, precision-recall, and receiver operating characteristic curve metrics. Results The ResNet-50-based deep learning model demonstrated high accuracy and sensitivity, outperforming traditional methods. Specifically, it enabled a rapid diagnosis of the presence or absence of urinary tract stones, thereby assisting doctors in their decision-making process. Conclusions This research makes a meaningful contribution by accelerating the clinical implementation of urinary tract stone detection technology utilizing ResNet-50. The deep learning model can swiftly identify the presence or absence of urinary tract stones, thereby enhancing the efficiency of medical staff. We expect that this study will contribute to the advancement of medical imaging diagnostic technology based on deep learning. |
| first_indexed | 2024-03-13T07:00:32Z |
| format | Article |
| id | doaj.art-d098b2106cc04199bbf372f25bfda328 |
| institution | Directory Open Access Journal |
| issn | 2093-4777 2093-6931 |
| language | English |
| last_indexed | 2024-03-13T07:00:32Z |
| publishDate | 2023-05-01 |
| publisher | Korean Continence Society |
| record_format | Article |
| series | International Neurourology Journal |
| spelling | doaj.art-d098b2106cc04199bbf372f25bfda3282023-06-07T04:12:54ZengKorean Continence SocietyInternational Neurourology Journal2093-47772093-69312023-05-0127Suppl 1S212610.5213/inj.2346110.0551051Transfer Learning for Effective Urolithiasis DetectionHyoung-Sun Choi0Jae-Seoung Kim1Taeg-Keun Whangbo2Khae Hawn Kim3 Department of Computer Science, Gachon University, Seongnam, Korea Health IT Research center, Gachon University Gil Medical Center, Incheon, Korea Department of Computer Science, Gachon University, Seongnam, Korea Department of Urology, Chungnam National University Sejong Hospital, Chugnam National University College of Medicine, Sejong, KoreaPurpose Urolithiasis is a common disease that can cause acute pain and complications. The objective of this study was to develop a deep learning model utilizing transfer learning for the rapid and accurate detection of urinary tract stones. By employing this method, we aim to improve the efficiency of medical staff and contribute to the progress of deep learning-based medical image diagnostic technology. Methods The ResNet50 model was employed to develop feature extractors for detecting urinary tract stones. Transfer learning was applied by utilizing the weights of pretrained models as initial values, and the models were fine-tuned with the provided data. The model’s performance was evaluated using accuracy, precision-recall, and receiver operating characteristic curve metrics. Results The ResNet-50-based deep learning model demonstrated high accuracy and sensitivity, outperforming traditional methods. Specifically, it enabled a rapid diagnosis of the presence or absence of urinary tract stones, thereby assisting doctors in their decision-making process. Conclusions This research makes a meaningful contribution by accelerating the clinical implementation of urinary tract stone detection technology utilizing ResNet-50. The deep learning model can swiftly identify the presence or absence of urinary tract stones, thereby enhancing the efficiency of medical staff. We expect that this study will contribute to the advancement of medical imaging diagnostic technology based on deep learning.http://einj.org/upload/pdf/inj-2346110-055.pdfurolithiasisurinary calculideep learningmachine learningartificial intelligence |
| spellingShingle | Hyoung-Sun Choi Jae-Seoung Kim Taeg-Keun Whangbo Khae Hawn Kim Transfer Learning for Effective Urolithiasis Detection International Neurourology Journal urolithiasis urinary calculi deep learning machine learning artificial intelligence |
| title | Transfer Learning for Effective Urolithiasis Detection |
| title_full | Transfer Learning for Effective Urolithiasis Detection |
| title_fullStr | Transfer Learning for Effective Urolithiasis Detection |
| title_full_unstemmed | Transfer Learning for Effective Urolithiasis Detection |
| title_short | Transfer Learning for Effective Urolithiasis Detection |
| title_sort | transfer learning for effective urolithiasis detection |
| topic | urolithiasis urinary calculi deep learning machine learning artificial intelligence |
| url | http://einj.org/upload/pdf/inj-2346110-055.pdf |
| work_keys_str_mv | AT hyoungsunchoi transferlearningforeffectiveurolithiasisdetection AT jaeseoungkim transferlearningforeffectiveurolithiasisdetection AT taegkeunwhangbo transferlearningforeffectiveurolithiasisdetection AT khaehawnkim transferlearningforeffectiveurolithiasisdetection |