Abstract | ||
---|---|---|
Bone mineral density (BMD) is a clinically critical indicator of osteoporosis, usually measured by dual-energy X-ray absorptiometry (DEXA). Due to the limited accessibility of DEXA machines and examinations, osteoporosis is often under-diagnosed and under-treated, leading to increased fragility fracture risks. Thus it is highly desirable to obtain BMDs with alternative cost-effective and more accessible medical imaging examinations such as X-ray plain films. In this work, we formulate the BMD estimation from plain hip X-ray images as a regression problem. Specifically, we propose a new semi-supervised self-training algorithm to train a BMD regression model using images coupled with DEXA measured BMDs and unlabeled images with pseudo BMDs. Pseudo BMDs are generated and refined iteratively for unlabeled images during self-training. We also present a novel adaptive triplet loss to improve the model's regression accuracy. On an in-house dataset of 1,090 images (819 unique patients), our BMD estimation method achieves a high Pearson correlation coefficient of 0.8805 to ground-truth BMDs. It offers good feasibility to use the more accessible and cheaper X-ray imaging for opportunistic osteoporosis screening. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/978-3-030-87240-3_4 | MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT V |
Keywords | DocType | Volume |
Bone mineral density estimation, Hip X-ray, Semi-supervised learning | Conference | 12905 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 11 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kang Zheng | 1 | 0 | 0.34 |
Yirui Wang | 2 | 0 | 2.03 |
Xiao-Yun Zhou | 3 | 7 | 8.03 |
Fakai Wang | 4 | 0 | 1.35 |
Le Lu | 5 | 1297 | 86.78 |
Chi-Hung Lin | 6 | 217 | 34.67 |
Lingyun Huang | 7 | 0 | 3.04 |
Guotong Xie | 8 | 0 | 0.68 |
Jing Xiao | 9 | 0 | 1.35 |
Chang-Fu Kuo | 10 | 0 | 1.35 |
Shun Miao | 11 | 143 | 17.54 |