Automated hip dysplasia detection using novel FlexiLBPHOG model with ultrasound images
This study focuses on automatically detecting developmental hip dysplasia (DHD) using a novel feature engineering model, FlexiLBPHOG, inspired by the FlexiViT model. The model utilizes five patch types for feature extraction with local binary pattern (LBP) and histogram of oriented gradients (HOG) t...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Ain Shams Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2090447924006166 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526260809859072 |
|---|---|
| author | Sefa Key Huseyin Kurum Omer Esmez Abdul Hafeez Baig Rena Hajiyeva Sengul Dogan Turker Tuncer |
| author_facet | Sefa Key Huseyin Kurum Omer Esmez Abdul Hafeez Baig Rena Hajiyeva Sengul Dogan Turker Tuncer |
| author_sort | Sefa Key |
| collection | DOAJ |
| description | This study focuses on automatically detecting developmental hip dysplasia (DHD) using a novel feature engineering model, FlexiLBPHOG, inspired by the FlexiViT model. The model utilizes five patch types for feature extraction with local binary pattern (LBP) and histogram of oriented gradients (HOG) techniques. During feature extraction, five feature vectors are generated. In the next stage, three feature selection methods—Neighborhood Component Analysis (NCA), Chi-square (Chi2), and ReliefF (RF)—are used to select the top 500 features. Classification is performed using support vector machine (SVM) and k-nearest neighbors (kNN), resulting in 30 outcomes. Information fusion through iterative majority voting (IMV) and a greedy algorithm yields 58 outcomes, from which the best is selected. The FlexiLBPHOG model achieved a classification accuracy of 94.38% in detecting DHD in ultrasound images from a private dataset. The study confirms the effectiveness of the proposed model in image classification by integrating shallow image descriptors. |
| format | Article |
| id | doaj-art-37e0cbbe70ca42fa98c361a59d652503 |
| institution | Kabale University |
| issn | 2090-4479 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ain Shams Engineering Journal |
| spelling | doaj-art-37e0cbbe70ca42fa98c361a59d6525032025-01-17T04:49:26ZengElsevierAin Shams Engineering Journal2090-44792025-01-01161103235Automated hip dysplasia detection using novel FlexiLBPHOG model with ultrasound imagesSefa Key0Huseyin Kurum1Omer Esmez2Abdul Hafeez Baig3Rena Hajiyeva4Sengul Dogan5Turker Tuncer6Orthopedics and Traumatology Department, Firat University Hospital, Firat University, Elazığ, TurkeyOrthopedics and Traumatology Department, Elazig Fethi Sekin City Hospital, 23100 Elazig, TurkeyOrthopedics and Traumatology Department, Elazig Fethi Sekin City Hospital, 23100 Elazig, TurkeySchool of Business, University of Southern Queensland, West Street Toowoomba, QLD, AustraliaWestern Caspian University, Department of Information Technologies, Baku, AzerbaijanDepartment of Digital Forensics Engineering, Technology Faculty, Firat University, Elazig, Turkey; Corresponding author.Department of Digital Forensics Engineering, Technology Faculty, Firat University, Elazig, TurkeyThis study focuses on automatically detecting developmental hip dysplasia (DHD) using a novel feature engineering model, FlexiLBPHOG, inspired by the FlexiViT model. The model utilizes five patch types for feature extraction with local binary pattern (LBP) and histogram of oriented gradients (HOG) techniques. During feature extraction, five feature vectors are generated. In the next stage, three feature selection methods—Neighborhood Component Analysis (NCA), Chi-square (Chi2), and ReliefF (RF)—are used to select the top 500 features. Classification is performed using support vector machine (SVM) and k-nearest neighbors (kNN), resulting in 30 outcomes. Information fusion through iterative majority voting (IMV) and a greedy algorithm yields 58 outcomes, from which the best is selected. The FlexiLBPHOG model achieved a classification accuracy of 94.38% in detecting DHD in ultrasound images from a private dataset. The study confirms the effectiveness of the proposed model in image classification by integrating shallow image descriptors.http://www.sciencedirect.com/science/article/pii/S2090447924006166Development hip dysplasia detectionFlexiLBPHOGMultiple feature selectionInformation fusionUltrasound |
| spellingShingle | Sefa Key Huseyin Kurum Omer Esmez Abdul Hafeez Baig Rena Hajiyeva Sengul Dogan Turker Tuncer Automated hip dysplasia detection using novel FlexiLBPHOG model with ultrasound images Ain Shams Engineering Journal Development hip dysplasia detection FlexiLBPHOG Multiple feature selection Information fusion Ultrasound |
| title | Automated hip dysplasia detection using novel FlexiLBPHOG model with ultrasound images |
| title_full | Automated hip dysplasia detection using novel FlexiLBPHOG model with ultrasound images |
| title_fullStr | Automated hip dysplasia detection using novel FlexiLBPHOG model with ultrasound images |
| title_full_unstemmed | Automated hip dysplasia detection using novel FlexiLBPHOG model with ultrasound images |
| title_short | Automated hip dysplasia detection using novel FlexiLBPHOG model with ultrasound images |
| title_sort | automated hip dysplasia detection using novel flexilbphog model with ultrasound images |
| topic | Development hip dysplasia detection FlexiLBPHOG Multiple feature selection Information fusion Ultrasound |
| url | http://www.sciencedirect.com/science/article/pii/S2090447924006166 |
| work_keys_str_mv | AT sefakey automatedhipdysplasiadetectionusingnovelflexilbphogmodelwithultrasoundimages AT huseyinkurum automatedhipdysplasiadetectionusingnovelflexilbphogmodelwithultrasoundimages AT omeresmez automatedhipdysplasiadetectionusingnovelflexilbphogmodelwithultrasoundimages AT abdulhafeezbaig automatedhipdysplasiadetectionusingnovelflexilbphogmodelwithultrasoundimages AT renahajiyeva automatedhipdysplasiadetectionusingnovelflexilbphogmodelwithultrasoundimages AT senguldogan automatedhipdysplasiadetectionusingnovelflexilbphogmodelwithultrasoundimages AT turkertuncer automatedhipdysplasiadetectionusingnovelflexilbphogmodelwithultrasoundimages |