Improved Detection of Urolithiasis Using High-Resolution Computed Tomography Images by a Vision Transformer Model
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Purpose: Urinary stones cause lateral abdominal pain and are a prevalent condition among younger age groups. The diagnosis typically involves assessing symptoms, conducting physical examinations, performing urine tests, and utilizing radiological imaging. Artificial intelligence models have demonstrated remarkable capabilities in detecting stones. However, due to insufficient datasets, the performance of these models has not reached a level suitable for practical application. Consequently, this study introduces a vision transformer (ViT)-based pipeline for detecting urinary stones, using computed tomography images with augmentation. Methods: The super-resolution convolutional neural network (SRCNN) model was employed to enhance the resolution of a given dataset, followed by data augmentation using CycleGAN. Subsequently, the ViT model facilitated the detection and classification of urinary tract stones. The model’s performance was evaluated using accuracy, precision, and recall as metrics. Results: The deep learning model based on ViT showed superior performance compared to other existing models. Furthermore, the performance increased with the size of the backbone model. Conclusions: The study proposes a way to utilize medical data to improve the diagnosis of urinary tract stones. SRCNN was used for data preprocessing to enhance resolution, while CycleGAN was utilized for data augmentation. The ViT model was utilized for stone detection, and its performance was validated through metrics such as accuracy, sensitivity, specificity, and the F1 score. It is anticipated that this research will aid in the early diagnosis and treatment of urinary tract stones, thereby improving the efficiency of medical personnel.
Abstract
Purpose: Urinary stones cause lateral abdominal pain and are a prevalent condition among younger age groups. The diagnosis typically involves assessing symptoms, conducting physical examinations, performing urine tests, and utilizing radiological imaging. Artificial intelligence models have demonstrated remarkable capabilities in detecting stones. However, due to insufficient datasets, the performance of these models has not reached a level suitable for practical application. Consequently, this study introduces a vision transformer (ViT)-based pipeline for detecting urinary stones, using computed tomography images with augmentation. Methods: The super-resolution convolutional neural network (SRCNN) model was employed to enhance the resolution of a given dataset, followed by data augmentation using CycleGAN. Subsequently, the ViT model facilitated the detection and classification of urinary tract stones. The model’s performance was evaluated using accuracy, precision, and recall as metrics. Results: The deep learning model based on ViT showed superior performance compared to other existing models. Furthermore, the performance increased with the size of the backbone model. Conclusions: The study proposes a way to utilize medical data to improve the diagnosis of urinary tract stones. SRCNN was used for data preprocessing to enhance resolution, while CycleGAN was utilized for data augmentation. The ViT model was utilized for stone detection, and its performance was validated through metrics such as accuracy, sensitivity, specificity, and the F1 score. It is anticipated that this research will aid in the early diagnosis and treatment of urinary tract stones, thereby improving the efficiency of medical personnel.
참고문헌 (18)
- Fwu CW, "Emergency department visits, use of imaging, and drugs for urolithiasis have increased in the United States", Kidney Int, 83, pp.479~486 (2013)
- Sakhaee K, "Clinical review. Kidney stones 2012: pathogenesis, diagnosis, and management", J Clin Endocrinol Metab, 97, pp.1847~1860 (2012)
- 김아람, "What is the Cause of Recurrent Urinary Tract Infection? Contemporary Microscopic Concepts of Pathophysiology", International Neurourology Journal, 25(3), pp.192~201 (2021), 대한배뇨장애요실금학회[DOI]
- Parvivar F, "The influence of diet on urinary stone disease", J Urol, 155, pp.432~440 (1996)
- Dauw CA, "Provider variation in the quality of metabolic stone management", J Urol, 193, pp.885~890 (2015)
- Andrabi Y, "Advances in CT imaging for urolithiasis", Indian J Urol, 31, pp.185~193 (2015)
- LeCun Y, "Backpropagation applied to handwritten zip code recognition", Neural Comput, 1, pp.541~551 (1989)
- Dosovitskiy A, "An image is worth 16x16 words: transformers for image recognition at scale", ICLR 2021, 3(7) (2021)
- Ma FZ, "Detection and diagnosis of chronic kidney disease using deep learning-based heterogeneous modified artificial neural network", Future Gener Comput Syst, 111, pp.17~26 (2020)
- Parakh A, "Urinary stone detection on CT images using deep convolutional neural networks evaluation of model performance and generalization", Radiol Artif Intell, 1, pp.e180066~ (2019)
- 은성종, "A Study on the Optimal Artificial Intelligence Model for Determination of Urolithiasis", International Neurourology Journal, 26(3), pp.210~218 (2022), 대한배뇨장애요실금학회[DOI]
- 박종목, "Development and Evaluation of Urolithiasis Detection Technology Based on a Multimethod Algorithm", International Neurourology Journal, 27(1), pp.70~76 (2023), 대한배뇨장애요실금학회[DOI]
- Anastasiadis A, "Transforming urinary stone disease management by artificial intelligence-based methods : a comprehensive review", Asian J Urol, 10, pp.258~274 (2023)
- 오경진, "요로결석의 위험인자", 대한의사협회지, 63(11), pp.660~667 (2020), 대한의사협회
- Umehara K, "Application of super-resolution convolutional neural network for enhancing image resolution in chest CT", J Digit Imaging, 31, pp.441~450 (2018)
- Ayesha AS, "Investigation of histogram equalization filter for CT scan image enhancement", Biomedical Engineering, 31, pp.1950038~ (2019)
- Dong C, "Image super-resolution using deep convolutional networks", IEEE Trans Pattern Anal Mach Intell, 38, pp.295~307 (2016)
- Zhu JY, "Unpaired image-to-image translation using cycle-consistent adversarial networks", 2017 IEEE International Conference on Computer Vision (ICCV), pp.2242~2251 (2017)