A software program for automated compressive vertebral fracture detection on elderly women's lateral chest radiograph: Ofeye 1.0

Xiao, Ben-Heng1; Zhu, Michael S. Y.2; Du, Er-Zhu3; Liu, Wei-Hong4,5; Ma, Jian-Bing6; Huang, Hua7; Gong, Jing-Shan8,9; Diacinti, Davide10,11; Zhang, Kun12; Gao, Bo13; Liu, Heng14; Jiang, Ri-Feng15; Ji, Zhong-You16; Xiong, Xiao-Bao17; He, Lai-Chang18; Wu, Lei19; Xu, Chuan-Jun20; Du, Mei-Mei21,22; Wang, Xiao-Rong23; Chen, Li-Mei1; Wu, Kong-Yang1,24; Yang, Liu1; Xu, Mao-Sheng19; Diacinti, Daniele10; Dou, Qi25; Kwok, Timothy Y. C.26; Wang, Yi Xiang J.1

2022-05-01

10.21037/qims-22-433

Quantitative Imaging in Medicine and Surgery   影响因子和分区

2223-4292

2223-4306

["Background: Because osteoporotic vertebral fracture (OVF) on chest radiographs is commonly missed in radiological reports, we aimed to develop a software program which offers automated detection of compressive vertebral fracture (CVF) on lateral chest radiographs, and which emphasizes CVF detection specificity with a low false positivity rate.","Methods: For model training, we retrieved 3,991 spine radiograph cases and 1,979 chest radiograph cases from 16 sources, with among them in total 1,404 cases had OVF For model testing, we retrieved 542 chest radiograph cases and 162 spine radiograph cases from four independent clinics, with among them 215 cases had OVF. All cases were female subjects, and except for 31 training data cases which were spine trauma cases, all the remaining cases were post-menopausal women. Image data included DICOM (Digital Imaging and Communications in Medicine) format, hard film scanned PNG (Portable Network Graphics) format, DICOM exported PNG format, and PACS (Picture Archiving and Communication System) downloaded resolution reduced DICOM format. OW classification included: minimal and mild grades with <20% or >= 20-25% vertebral height lass respectively, moderate grade with >= 25-40% vertebral height loss, severe grade with >= 40%-2/3 vertebral height loss, and collapsed grade with >= 2/3 vertebral height loss. The CVF detection base model was mainly composed of convolution layers that include convolution kernels of different sizes, pooling layers, up-sampling layers, feature merging layers, and residual modules. When the model loss function could not be further decreased with additional training, the model was considered to be optimal and termed 'base-model 1.0'. A user-friendly interface was also developed, with the synthesized software termed 'Ofeye 1.0'.","Results: Counting cases and with minimal and mild OVFs included, base-model 1.0 demonstrated a specificity of 97.1%, a sensitivity of 86%, and an accuracy of 93.9% for the 704 testing cases. In total, 33 OVFs in 30 cases had a false negative reading, which constituted a false negative rate of 14.0% (30/215) by counting all OW cases. Eighteen OVFs in 15 cases had OVFs of >= moderate grades missed, which constituted a false negative rate of 7.0% (15/215, i.e., sensitivity 93%) if only counting cases with >= moderate grade OVFs missed. False positive reading was recorded in 13 vertebrae in 13 cases (one vertebra in each case), which constituted a false positivity rate of 2.7% (13/489). These vertebrae with false positivity labeling could be readily differentiated from a true OVF by a human reader. The software Ofeye 1.0 allows 'batch processing', for example, 100 radiographs can be processed in a single operation. This software can be integrated into hospital PACS, or installed in a standalone personal computer.","Conclusions: A user-friendly software program was developed for CVF detection on elderly women's lateral chest radiographs. It has an overall low false positivity rate, and for moderate and severe CVFs an acceptably low false negativity rate. The integration of this software into radiological practice is expected to improve osteoporosis management for elderly women."]

Osteoporosis vertebral fracture radiograph chest artificial intelligence deep learning

SCI

英语

其他

Hong Kong ITSP project[ITS/334/18]

Radiology, Nuclear Medicine & Medical Imaging

Radiology, Nuclear Medicine & Medical Imaging

WOS:000810608400001

AME PUBL CO

Web of Science

1.Chinese Univ Hong Kong, Fac Med, Dept Imaging & Intervent Radiol, Hong Kong, Peoples R China
2.Yingran Med Co Ltd, Hong Kong, Peoples R China
3.Dongguan Tradit Chinese Med Hosp, Dept Radiol, Dongguan, Peoples R China
4.Gen Hosp China Resources, Dept Radiol, Wuhan, Peoples R China
5.Wuhan Iron & Steel Corp, Wuhan, Peoples R China
6.Jiaxing Univ, Affiliated Hosp, Hosp Jiaxing 1, Dept Radiol, Jiaxing, Peoples R China
7.Southern Univ Sci & Technol, Affiliated Hosp 2, Peoples Hosp Shenzhen 3, Dept Radiol,Natl Clin Res Ctr Infect Dis, Shenzhen, Peoples R China
8.Jinan Univ, Shenzhen Peoples Hosp, Clin Med Coll 2, Dept Radiol, Shenzhen, Peoples R China
9.Southern Univ Sci & Technol, Affiliated Hosp 1, Shenzhen, Peoples R China
10.Sapienza Univ Rome, Dept Radiol Sci Oncol & Pathol, Rome, Italy
11.Univ Fdn Hosp Tor Vergata, Dept Diagnost & Mol Imaging Radiol & Radiotherapy, Rome, Italy
12.Hunan Univ Chinese Med, Affiliated Hosp 1, Dept Radiol, Changsha, Peoples R China
13.Guizhou Med Univ, Affiliated Hosp, Dept Radiol, Guiyang, Peoples R China
14.Zunyi Med Univ, Affiliated Hosp, Dept Radiol, Zunyi, Guizhou, Peoples R China
15.Fujian Med Univ, Union Hosp, Dept Radiol, Fuzhou, Peoples R China
16.Fujian Med Univ, Union Hosp, PET CT Ctr, Fuzhou, Peoples R China
17.Zhejiang Prov Tongde Hosp, Dept Radiol, Hangzhou, Peoples R China
18.Nanchang Univ, Affiliated Hosp 1, Dept Radiol, Nanchang, Jiangxi, Peoples R China
19.Zhejiang Chinese Med Univ, Affiliated Hosp 1, Dept Radiol, Hangzhou, Peoples R China
20.Nanjing Univ Chinese Med, Hosp Nanjing 2, Dept Radiol, Nanjing, Peoples R China
21.Wenzhou Med Univ, Affiliated Hosp 2, Dept Radiol, Wenzhou, Peoples R China
22.Wenzhou Med Univ, Yuying Childrens Hosp, Wenzhou, Peoples R China
23.Ningbo First Hosp, Dept Radiol, Ningbo, Peoples R China
24.Jinan Univ, Coll Elect & Informat Engn, Guangzhou, Peoples R China
25.Chinese Univ Hong Kong, Fac Engn, Dept Comp Sci & Engn, Hong Kong, Peoples R China
26.Chinese Univ Hong Kong, Fac Med, JC Ctr Osteoporosis Care & Control, Hong Kong, Peoples R China

Xiao, Ben-Heng,Zhu, Michael S. Y.,Du, Er-Zhu,et al. A software program for automated compressive vertebral fracture detection on elderly women's lateral chest radiograph: Ofeye 1.0[J]. Quantitative Imaging in Medicine and Surgery,2022.

Xiao, Ben-Heng.,Zhu, Michael S. Y..,Du, Er-Zhu.,Liu, Wei-Hong.,Ma, Jian-Bing.,...&Wang, Yi Xiang J..(2022).A software program for automated compressive vertebral fracture detection on elderly women's lateral chest radiograph: Ofeye 1.0.Quantitative Imaging in Medicine and Surgery.

Xiao, Ben-Heng,et al."A software program for automated compressive vertebral fracture detection on elderly women's lateral chest radiograph: Ofeye 1.0".Quantitative Imaging in Medicine and Surgery (2022).