Early diagnosis of osteoporosis using Artificial Neural Networks and Support Vector Machines
In the last decade, osteoporotic fractures became one of the most serious problems in public health. The life risk of suffering of an osteoporotic fracture is estimated to be 30% for 50 years old and in postmenopausal period woman. Early diagnosis is quite important for osteoporosis. A fall can be e...
Saved in:
| Published in: | 2012 20th Signal Processing and Communications Applications Conference (SIU) pp. 1 - 4 |
|---|---|
| Main Authors: | , , , , |
| Format: | Conference Proceeding |
| Language: | English |
| Published: |
IEEE
01-04-2012
|
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In the last decade, osteoporotic fractures became one of the most serious problems in public health. The life risk of suffering of an osteoporotic fracture is estimated to be 30% for 50 years old and in postmenopausal period woman. Early diagnosis is quite important for osteoporosis. A fall can be easily result in a fracture; these are common in the hip, at the neck of the femur, the wrist and the spine, if it's not treated sequences on time. Be inspiring from this problem we aimed to build up an image processing method for helping to early diagnosis. In this study we obtained features via wavelet transform from Computerized Tomography images. Classification is achieved by Artificial Neural Networks (ANN) and Support Vector Machines (SVM). As a result for ANN, we accomplished 70% correct osteoporosis classification from early period images. SVM classification increased the accuracy and we have reached up 86% correct classification. These successful results make a significant contribution to early diagnosis of osteoporosis. |
|---|---|
| ISBN: | 9781467300551 1467300551 |
| ISSN: | 2165-0608 2693-3616 |
| DOI: | 10.1109/SIU.2012.6204648 |