Deep Learning for Discrimination of Early Spinal Tuberculosis from Acute Osteoporotic Vertebral Fracture on CT
Wenjun Liu,1 Jin Wang,2 Yiting Lei,1 Peng Liu,3 Zhenghan Han,1 Shichu Wang,1 Bo Liu1 1Department of Orthopedics, First Affiliated Hospital, Chongqing Medical University, Chongqing, People’s Republic of China; 2College of Medical Informatics, Chongqing Medical University, Chongqing, People’s Republic...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dove Medical Press
2025-01-01
|
| Series: | Infection and Drug Resistance |
| Subjects: | |
| Online Access: | https://www.dovepress.com/deep-learning-for-discrimination-of-early-spinal-tuberculosis-from-acu-peer-reviewed-fulltext-article-IDR |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841558985095774208 |
|---|---|
| author | Liu W Wang J Lei Y Liu P Han Z Wang S Liu B |
| author_facet | Liu W Wang J Lei Y Liu P Han Z Wang S Liu B |
| author_sort | Liu W |
| collection | DOAJ |
| description | Wenjun Liu,1 Jin Wang,2 Yiting Lei,1 Peng Liu,3 Zhenghan Han,1 Shichu Wang,1 Bo Liu1 1Department of Orthopedics, First Affiliated Hospital, Chongqing Medical University, Chongqing, People’s Republic of China; 2College of Medical Informatics, Chongqing Medical University, Chongqing, People’s Republic of China; 3Department of Orthopedics, Daping Hospital, Army Medical University, Chongqing, People’s Republic of ChinaCorrespondence: Bo Liu, Department of Orthopedics, First Affiliated Hospital, Chongqing Medical University, Chongqing, People’s Republic of China, Tel +8613996065698, Email boliu@hospital.cqmu.edu.cnBackground: Early differentiation between spinal tuberculosis (STB) and acute osteoporotic vertebral compression fracture (OVCF) is crucial for determining the appropriate clinical management and treatment pathway, thereby significantly impacting patient outcomes.Objective: To evaluate the efficacy of deep learning (DL) models using reconstructed sagittal CT images in the differentiation of early STB from acute OVCF, with the aim of enhancing diagnostic precision, reducing reliance on MRI and biopsies, and minimizing the risks of misdiagnosis.Methods: Data were collected from 373 patients, with 302 patients recruited from a university-affiliated hospital serving as the training and internal validation sets, and an additional 71 patients from another university-affiliated hospital serving as the external validation set. MVITV2, Efficient-Net-B5, ResNet101, and ResNet50 were used as the backbone networks for DL model development, training, and validation. Model evaluation was based on accuracy, precision, sensitivity, F1 score, and area under the curve (AUC). The performance of the DL models was compared with the diagnostic accuracy of two spine surgeons who performed a blinded review.Results: The MVITV2 model outperformed other architectures in the internal validation set, achieving accuracy of 98.98%, precision of 100%, sensitivity of 97.97%, F1 score of 98.98%, and AUC of 0.997. The performance of the DL models notably exceeded that of the spine surgeons, who achieved accuracy rates of 77.38% and 93.56%. The external validation confirmed the models’ robustness and generalizability.Conclusion: The DL models significantly improved the differentiation between STB and OVCF, surpassing experienced spine surgeons in diagnostic accuracy. These models offer a promising alternative to traditional imaging and invasive procedures, potentially promoting early and accurate diagnosis, reducing healthcare costs, and improving patient outcomes. The findings underscore the potential of artificial intelligence for revolutionizing spinal disease diagnostics, and have substantial clinical implications.Keywords: deep learning, spinal tuberculosis, osteoporotic vertebral fractures, CT imaging, diagnostic accuracy |
| format | Article |
| id | doaj-art-bd6e05fb8b084889a103d36a8c0bd2dd |
| institution | Kabale University |
| issn | 1178-6973 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Dove Medical Press |
| record_format | Article |
| series | Infection and Drug Resistance |
| spelling | doaj-art-bd6e05fb8b084889a103d36a8c0bd2dd2025-01-05T16:36:04ZengDove Medical PressInfection and Drug Resistance1178-69732025-01-01Volume 18314298923Deep Learning for Discrimination of Early Spinal Tuberculosis from Acute Osteoporotic Vertebral Fracture on CTLiu WWang JLei YLiu PHan ZWang SLiu BWenjun Liu,1 Jin Wang,2 Yiting Lei,1 Peng Liu,3 Zhenghan Han,1 Shichu Wang,1 Bo Liu1 1Department of Orthopedics, First Affiliated Hospital, Chongqing Medical University, Chongqing, People’s Republic of China; 2College of Medical Informatics, Chongqing Medical University, Chongqing, People’s Republic of China; 3Department of Orthopedics, Daping Hospital, Army Medical University, Chongqing, People’s Republic of ChinaCorrespondence: Bo Liu, Department of Orthopedics, First Affiliated Hospital, Chongqing Medical University, Chongqing, People’s Republic of China, Tel +8613996065698, Email boliu@hospital.cqmu.edu.cnBackground: Early differentiation between spinal tuberculosis (STB) and acute osteoporotic vertebral compression fracture (OVCF) is crucial for determining the appropriate clinical management and treatment pathway, thereby significantly impacting patient outcomes.Objective: To evaluate the efficacy of deep learning (DL) models using reconstructed sagittal CT images in the differentiation of early STB from acute OVCF, with the aim of enhancing diagnostic precision, reducing reliance on MRI and biopsies, and minimizing the risks of misdiagnosis.Methods: Data were collected from 373 patients, with 302 patients recruited from a university-affiliated hospital serving as the training and internal validation sets, and an additional 71 patients from another university-affiliated hospital serving as the external validation set. MVITV2, Efficient-Net-B5, ResNet101, and ResNet50 were used as the backbone networks for DL model development, training, and validation. Model evaluation was based on accuracy, precision, sensitivity, F1 score, and area under the curve (AUC). The performance of the DL models was compared with the diagnostic accuracy of two spine surgeons who performed a blinded review.Results: The MVITV2 model outperformed other architectures in the internal validation set, achieving accuracy of 98.98%, precision of 100%, sensitivity of 97.97%, F1 score of 98.98%, and AUC of 0.997. The performance of the DL models notably exceeded that of the spine surgeons, who achieved accuracy rates of 77.38% and 93.56%. The external validation confirmed the models’ robustness and generalizability.Conclusion: The DL models significantly improved the differentiation between STB and OVCF, surpassing experienced spine surgeons in diagnostic accuracy. These models offer a promising alternative to traditional imaging and invasive procedures, potentially promoting early and accurate diagnosis, reducing healthcare costs, and improving patient outcomes. The findings underscore the potential of artificial intelligence for revolutionizing spinal disease diagnostics, and have substantial clinical implications.Keywords: deep learning, spinal tuberculosis, osteoporotic vertebral fractures, CT imaging, diagnostic accuracyhttps://www.dovepress.com/deep-learning-for-discrimination-of-early-spinal-tuberculosis-from-acu-peer-reviewed-fulltext-article-IDRdeep learningspinal tuberculosisosteoporotic vertebral fracturesct imagingdiagnostic accuracy |
| spellingShingle | Liu W Wang J Lei Y Liu P Han Z Wang S Liu B Deep Learning for Discrimination of Early Spinal Tuberculosis from Acute Osteoporotic Vertebral Fracture on CT Infection and Drug Resistance deep learning spinal tuberculosis osteoporotic vertebral fractures ct imaging diagnostic accuracy |
| title | Deep Learning for Discrimination of Early Spinal Tuberculosis from Acute Osteoporotic Vertebral Fracture on CT |
| title_full | Deep Learning for Discrimination of Early Spinal Tuberculosis from Acute Osteoporotic Vertebral Fracture on CT |
| title_fullStr | Deep Learning for Discrimination of Early Spinal Tuberculosis from Acute Osteoporotic Vertebral Fracture on CT |
| title_full_unstemmed | Deep Learning for Discrimination of Early Spinal Tuberculosis from Acute Osteoporotic Vertebral Fracture on CT |
| title_short | Deep Learning for Discrimination of Early Spinal Tuberculosis from Acute Osteoporotic Vertebral Fracture on CT |
| title_sort | deep learning for discrimination of early spinal tuberculosis from acute osteoporotic vertebral fracture on ct |
| topic | deep learning spinal tuberculosis osteoporotic vertebral fractures ct imaging diagnostic accuracy |
| url | https://www.dovepress.com/deep-learning-for-discrimination-of-early-spinal-tuberculosis-from-acu-peer-reviewed-fulltext-article-IDR |
| work_keys_str_mv | AT liuw deeplearningfordiscriminationofearlyspinaltuberculosisfromacuteosteoporoticvertebralfractureonct AT wangj deeplearningfordiscriminationofearlyspinaltuberculosisfromacuteosteoporoticvertebralfractureonct AT leiy deeplearningfordiscriminationofearlyspinaltuberculosisfromacuteosteoporoticvertebralfractureonct AT liup deeplearningfordiscriminationofearlyspinaltuberculosisfromacuteosteoporoticvertebralfractureonct AT hanz deeplearningfordiscriminationofearlyspinaltuberculosisfromacuteosteoporoticvertebralfractureonct AT wangs deeplearningfordiscriminationofearlyspinaltuberculosisfromacuteosteoporoticvertebralfractureonct AT liub deeplearningfordiscriminationofearlyspinaltuberculosisfromacuteosteoporoticvertebralfractureonct |