Academic Journal
Development and multi-center validation of a software program, Ofeye 3.0, for automated all-inclusive vertebral fracture detection with chest/abdominal CT images.
| Title: | Development and multi-center validation of a software program, Ofeye 3.0, for automated all-inclusive vertebral fracture detection with chest/abdominal CT images. |
|---|---|
| Authors: | Xiao BH; Department of Imaging and Interventional Radiology, Faculty of Medicine, the Chinese University of Hong Kong, Hong Kong Special Administrative Region of China., Gao ZH; Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China., Li CY; Department of Imaging and Interventional Radiology, Faculty of Medicine, the Chinese University of Hong Kong, Hong Kong Special Administrative Region of China., Leng XM; Universal Medical Imaging Diagnostic Center of Guangzhou, Guangzhou, China., Du EZ; Department of Radiology, Dongguan Traditional Chinese Medicine Hospital, Dongguan, Guangdong province, China., Ma JB; Department of Radiology, The First Hospital of Jiaxing, the Affiliated Hospital of Jiaxing University, Jiaxing, Zhejiang, China., Liu FS; Shandong Healthcare Group Xinwen Center Hospital, Tai'an, Shandong, China., Gong JS; Department of Radiology, Shenzhen People's Hospital, the Second Clinical Medical College, Jinan University, Shenzhen, China., Ju ZG; College of Medical Imaging, Shanghai University of Medicine and Health Science, Shanghai, China., Yuan MY; Department of Radiology, Affiliated Zhoupu Hospital, Shanghai University of Medicine and Health Sciences, Shanghai, China., Zhu HM; The Sixth People's Hospital of Huizhou, Huizhou, Guangdong, China., Zhu MSY; Yingran Medicals Co. Ltd, Hong Kong Special Administrative Region of China., Kwok TY; JC Centre for Osteoporosis Care and Control, Faculty of Medicine, the Chinese University of Hong Kong, Hong Kong Special Administrative Region of China., Wáng YXJ; Department of Imaging and Interventional Radiology, Faculty of Medicine, the Chinese University of Hong Kong, Hong Kong Special Administrative Region of China. |
| Source: | Journal of orthopaedic translation [J Orthop Translat] 2025 Sep 13; Vol. 55, pp. 192-203. Date of Electronic Publication: 2025 Sep 13 (Print Publication: 2025). |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: Elsevier Country of Publication: Singapore NLM ID: 101625127 Publication Model: eCollection Cited Medium: Print ISSN: 2214-031X (Print) Linking ISSN: 2214031X NLM ISO Abbreviation: J Orthop Translat Subsets: PubMed not MEDLINE |
| Imprint Name(s): | Original Publication: Singapore : Elsevier, [2013]- |
| Abstract: | Background: Missing report for fragility vertebral fracture (VF) on chest/abdominal CT is common when the indication is not spine disorders. This represents a missed opportunity to alert patients to take preventive measures to improve bone health and prevent further severe fractures. In this study, we aim to develop a software program for automated detection of VF with existing chest/abdominal CT scans and validate its detection performance. Methods: An automated sagittal Central Slab reconstruction (CSR) method for CT axial images was developed. For reference VF reading, VFs inclusive of those of with <20 % vertebral height loss and those of endplate fracture with minimal vertebral height loss were identified. VFs were also differentiated from osteoarthritic wedging and endplatitis short vertebrae. Prior knowledge of VF detection models for lateral radiograph were transferred to a new 'Ofeye 3.0' model optimized for VF detection on CT image. Training CT images were obtained from nine centers, totaling 3313 cases without VF and 835 cases with VF. For external validation, CT images were from five centers totaling 732 cases without VF and 224 cases with VF. Results: The automated CSR method showed advantages in demonstrating structural changes of the endplate and adjacent structures. For detecting VF in chest/abdominal CT scans, counting case-by-case and compared with the reference reading, the average performance of Ofeye 3.0 was accuracy 0.967, sensitivity 0.906, and specificity 0.986. Most of false negative or false positive cases were minimal or mild VF, or with image artifacts, or with VF close to the peripheral of CSR images. Conclusions: Despite the challenging requirements for the software to detect all-inclusive VF, our results compare favorably with other published automated VF detection models. The Translational Potential of This Article: We developed a software program for automated all-inclusive VF detection on chest and/or abdominal CT image data and conducted a multi-center external validation study. This software is proved to have high VF detection precision. By alerting patients of the VFs likely related to osteoporosis and in turn the patients taking measures to prevent further fracture, the integration of this software into radiological practice will improve patient outcomes and reduce healthcare costs. (© 2025 The Authors.) |
| Competing Interests: | YXJW is the founder of Yingran Medicals Ltd, which develops medical image-based diagnostics software, including Ofeye 1.0, Ofeye 2.0, Ofeye 3.0. BHX and MSYZ contributed to the development of Ofeye 1.0, Ofeye 3.0. The other authors have no conflicts of interest to declare. |
| References: | Quant Imaging Med Surg. 2024 Mar 15;14(3):2725-2733. (PMID: 38545052) Orthop Surg. 2022 Oct;14(10):2462-2469. (PMID: 36017769) Quant Imaging Med Surg. 2022 Aug;12(8):4259-4271. (PMID: 35919046) J Orthop Translat. 2018 Sep 06;15:35-49. (PMID: 30306044) Ther Adv Musculoskelet Dis. 2021 Jul 10;13:1759720X211024029. (PMID: 34290831) JBMR Plus. 2023 Mar 15;7(5):e10736. (PMID: 37197322) Comput Biol Med. 2018 Jul 1;98:8-15. (PMID: 29758455) J Am Coll Radiol. 2019 Oct;16(10):1473-1479. (PMID: 30982683) Radiology. 2017 Sep;284(3):788-797. (PMID: 28301777) Rheumatology (Oxford). 2022 Aug 3;61(8):3269-3278. (PMID: 34850864) Bone. 1994 Jul-Aug;15(4):437-42. (PMID: 7917584) Eur Radiol. 2008 Aug;18(8):1696-702. (PMID: 18418607) Ann Transl Med. 2020 Mar;8(6):398. (PMID: 32355842) Skeletal Radiol. 2025 May;54(5):925-936. (PMID: 39284928) BMJ Open. 2022 May 24;12(5):e050343. (PMID: 35613783) Quant Imaging Med Surg. 2021 Jun;11(6):2486-2498. (PMID: 34079718) Radiology. 2013 Jul;268(1):120-6. (PMID: 23449956) J Bone Miner Res. 2023 Dec;38(12):1856-1866. (PMID: 37747147) J Bone Miner Res. 2020 Oct;35(10):1942-1951. (PMID: 32539162) Quant Imaging Med Surg. 2023 Jun 1;13(6):4044-4049. (PMID: 37284078) Quant Imaging Med Surg. 2024 Sep 1;14(9):6922-6933. (PMID: 39281176) J Bone Miner Res. 1993 Sep;8(9):1137-48. (PMID: 8237484) J Clin Densitom. 2021 Apr-Jun;24(2):183-189. (PMID: 32546345) J Bone Miner Res. 2014 Feb;29(2):392-8. (PMID: 23821454) Quant Imaging Med Surg. 2024 Jun 1;14(6):4288-4303. (PMID: 38846309) J Bone Miner Res. 2020 Dec;35(12):2307-2312. (PMID: 32749735) Ann Transl Med. 2023 Aug 30;11(10):374. (PMID: 37675328) Osteoporos Int. 2013 Aug;24(8):2135-52. (PMID: 23589162) Aging Clin Exp Res. 2023 Nov;35(11):2583-2591. (PMID: 37646923) Acta Chir Belg. 2006 Jul-Aug;106(4):393-6. (PMID: 17017690) Bone. 2017 Aug;101:230-235. (PMID: 28511873) Age Ageing. 2010 Mar;39(2):203-9. (PMID: 20075035) Osteoporos Int. 2024 Jan;35(1):143-152. (PMID: 37674097) Skeletal Radiol. 2024 Dec;53(12):2563-2574. (PMID: 38662094) Semin Musculoskelet Radiol. 2024 Oct;28(5):628-640. (PMID: 39406225) AJR Am J Roentgenol. 2017 Aug;209(2):395-402. (PMID: 28570093) Quant Imaging Med Surg. 2017 Oct;7(5):555-591. (PMID: 29184768) Osteoporos Int. 2021 May;32(5):921-926. (PMID: 33170309) Arch Osteoporos. 2017 Dec;12(1):71. (PMID: 28785996) Osteoporos Int. 2007 Jun;18(6):761-70. (PMID: 17245546) Quant Imaging Med Surg. 2022 Jul;12(7):3495-3514. (PMID: 35782246) Radiol Bras. 2024 May 03;57:e20230102. (PMID: 38993956) |
| Contributed Indexing: | Keywords: Machine learning; Osteoporosis; Tomograph; Vertebral fracture |
| Entry Date(s): | Date Created: 20260116 Date Completed: 20260116 Latest Revision: 20260118 |
| Update Code: | 20260130 |
| PubMed Central ID: | PMC12799497 |
| DOI: | 10.1016/j.jot.2025.08.011 |
| PMID: | 41542100 |
| Database: | MEDLINE |
| ISSN: | 2214-031X |
|---|---|
| DOI: | 10.1016/j.jot.2025.08.011 |