A Deep Learning Approach on Segmentation of Bone for BMD Measurement from DEXA Scan Images
Authors:
- 1 February 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Osteoporosis is a silent disease which increases fracture risk condition in the body. The disease is noticed more in women, but can affect both men and women in all ages. The disease is alarmed by means of a parameter called Bone Mineral Density (BMD). BMD is estimated in both X-ray and DEXA images by means of various image processing algorithms and machine learning algorithms. Lot of literature also exists for the detection of osteoporosis condition. In recent years, deep learning methods show its face for the measurement of BMD. The paper focusses with the measurement of BMD and segmentation of bone region in DEXA image using U net architecture. The parameters used in the architecture shown better results in terms of Dice, F1 score.Keywords
This publication has 5 references indexed in Scilit:
- Simulating Dual-Energy X-Ray Absorptiometry in CT Using Deep-Learning Segmentation CascadeJournal of the American College of Radiology, 2019
- Automated detection of bone splinters in DEXA phantoms using deep neural networksCurrent Directions in Biomedical Engineering, 2019
- Estimation of t-score and BMD values from X-ray images for detection of osteoporosis2019
- Femur segmentation in DXA imaging using a machine learning decision treeJournal of X-Ray Science and Technology, 2018
- Measuring Bone Density Connectivity Using Dual Energy X-Ray Absorptiometry ImagesInternational Journal of Fuzzy Logic and Intelligent Systems, 2017