OsteoNet—A Framework for Identifying Osteoporosis in Bone Radiograph Images Using Attention-Based VGG Network
Diagnosing osteoporosis from X-ray images poses a significant challenge due to the visual similarities between images from healthy subjects and patients. In this paper, we present a novel method for detecting osteoporosis. Our approach utilizes local phase quantization (LPQ) to identify fine texture...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10872902/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823857126955548672 |
|---|---|
| author | Abdul Wahab Muzaffar Farhan Riaz Muhammad Tahir |
| author_facet | Abdul Wahab Muzaffar Farhan Riaz Muhammad Tahir |
| author_sort | Abdul Wahab Muzaffar |
| collection | DOAJ |
| description | Diagnosing osteoporosis from X-ray images poses a significant challenge due to the visual similarities between images from healthy subjects and patients. In this paper, we present a novel method for detecting osteoporosis. Our approach utilizes local phase quantization (LPQ) to identify fine texture variations that indicate changes in bone density, which are characteristic of osteoporosis. Furthermore, we augment the VGG network with an attention mechanism that incorporates both channel and spatial attentions. Channel attention is applied by calculating the mean and variance across channels, followed by a softmax operation to highlight essential features in the channel. Spatial attention is achieved through average pooling followed by exponential weighting to focus on relevant spatial regions within the images. A comparative analysis of the proposed method on ISBI 2014 challenge dataset against existing methods revealed that hand-crafted features mimicking gradients outperform those based on statistics, and CNN-based methods generally exhibit better performance. Our proposed method achieved an accuracy of 74.1%. These findings elucidate on the efficacy of integrating differential image features with attention mechanisms to improve the accuracy of osteoporosis identification from X-ray images. |
| format | Article |
| id | doaj-art-50fd4742fff3478cb0b2830adf082755 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-50fd4742fff3478cb0b2830adf0827552025-02-12T00:02:12ZengIEEEIEEE Access2169-35362025-01-0113251752518510.1109/ACCESS.2025.353882810872902OsteoNet—A Framework for Identifying Osteoporosis in Bone Radiograph Images Using Attention-Based VGG NetworkAbdul Wahab Muzaffar0https://orcid.org/0000-0001-7910-0378Farhan Riaz1Muhammad Tahir2https://orcid.org/0000-0002-7450-5840College of Computing and Informatics, Saudi Electronic University, Riyadh, Saudi ArabiaSchool of Engineering and Physical Sciences, University of Lincoln, Lincoln, U.K.College of Computing and Informatics, Saudi Electronic University, Riyadh, Saudi ArabiaDiagnosing osteoporosis from X-ray images poses a significant challenge due to the visual similarities between images from healthy subjects and patients. In this paper, we present a novel method for detecting osteoporosis. Our approach utilizes local phase quantization (LPQ) to identify fine texture variations that indicate changes in bone density, which are characteristic of osteoporosis. Furthermore, we augment the VGG network with an attention mechanism that incorporates both channel and spatial attentions. Channel attention is applied by calculating the mean and variance across channels, followed by a softmax operation to highlight essential features in the channel. Spatial attention is achieved through average pooling followed by exponential weighting to focus on relevant spatial regions within the images. A comparative analysis of the proposed method on ISBI 2014 challenge dataset against existing methods revealed that hand-crafted features mimicking gradients outperform those based on statistics, and CNN-based methods generally exhibit better performance. Our proposed method achieved an accuracy of 74.1%. These findings elucidate on the efficacy of integrating differential image features with attention mechanisms to improve the accuracy of osteoporosis identification from X-ray images.https://ieeexplore.ieee.org/document/10872902/Osteoporosisconvolutional neural networksbone radiograph image |
| spellingShingle | Abdul Wahab Muzaffar Farhan Riaz Muhammad Tahir OsteoNet—A Framework for Identifying Osteoporosis in Bone Radiograph Images Using Attention-Based VGG Network IEEE Access Osteoporosis convolutional neural networks bone radiograph image |
| title | OsteoNet—A Framework for Identifying Osteoporosis in Bone Radiograph Images Using Attention-Based VGG Network |
| title_full | OsteoNet—A Framework for Identifying Osteoporosis in Bone Radiograph Images Using Attention-Based VGG Network |
| title_fullStr | OsteoNet—A Framework for Identifying Osteoporosis in Bone Radiograph Images Using Attention-Based VGG Network |
| title_full_unstemmed | OsteoNet—A Framework for Identifying Osteoporosis in Bone Radiograph Images Using Attention-Based VGG Network |
| title_short | OsteoNet—A Framework for Identifying Osteoporosis in Bone Radiograph Images Using Attention-Based VGG Network |
| title_sort | osteonet x2014 a framework for identifying osteoporosis in bone radiograph images using attention based vgg network |
| topic | Osteoporosis convolutional neural networks bone radiograph image |
| url | https://ieeexplore.ieee.org/document/10872902/ |
| work_keys_str_mv | AT abdulwahabmuzaffar osteonetx2014aframeworkforidentifyingosteoporosisinboneradiographimagesusingattentionbasedvggnetwork AT farhanriaz osteonetx2014aframeworkforidentifyingosteoporosisinboneradiographimagesusingattentionbasedvggnetwork AT muhammadtahir osteonetx2014aframeworkforidentifyingosteoporosisinboneradiographimagesusingattentionbasedvggnetwork |