MobileTurkerNeXt: investigating the detection of Bankart and SLAP lesions using magnetic resonance images
Article
Gurger, Murat, Esmez, Omer, Key, Sefa, Hafeez-Baig, Abdul, Dogan, Sengul and Tuncer, Turker. 2025. "MobileTurkerNeXt: investigating the detection of Bankart and SLAP lesions using magnetic resonance images." Radiological Physics and Technology. https://doi.org/10.1007/s12194-025-00918-x
| Article Title | MobileTurkerNeXt: investigating the detection of Bankart and SLAP lesions using magnetic resonance images |
|---|---|
| ERA Journal ID | 214038 |
| Article Category | Article |
| Authors | Gurger, Murat, Esmez, Omer, Key, Sefa, Hafeez-Baig, Abdul, Dogan, Sengul and Tuncer, Turker |
| Journal Title | Radiological Physics and Technology |
| Number of Pages | 17 |
| Year | 2025 |
| Publisher | Springer |
| Place of Publication | Japan |
| ISSN | 1865-0333 |
| 1865-0341 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1007/s12194-025-00918-x |
| Web Address (URL) | https://link.springer.com/article/10.1007/s12194-025-00918-x |
| Abstract | The landscape of computer vision is predominantly shaped by two groundbreaking methodologies: transformers and convolutional neural networks (CNNs). In this study, we aim to introduce an innovative mobile CNN architecture designed for orthopedic imaging that efficiently identifies both Bankart and SLAP lesions. Our approach involved the collection of two distinct magnetic resonance (MR) image datasets, with the primary goal of automating the detection of Bankart and SLAP lesions. A novel mobile CNN, dubbed MobileTurkerNeXt, forms the cornerstone of this research. This newly developed model, comprising roughly 1 million trainable parameters, unfolds across four principal stages: the stem, main, downsampling, and output phases. The stem phase incorporates three convolutional layers to initiate feature extraction. In the main phase, we introduce an innovative block, drawing inspiration from ConvNeXt, EfficientNet, and ResNet architectures. The downsampling phase utilizes patchify average pooling and pixel-wise convolution to effectively reduce spatial dimensions, while the output phase is meticulously engineered to yield classification outcomes. Our experimentation with MobileTurkerNeXt spanned three comparative scenarios: Bankart versus normal, SLAP versus normal, and a tripartite comparison of Bankart, SLAP, and normal cases. The model demonstrated exemplary performance, achieving test classification accuracies exceeding 96% across these scenarios. The empirical results underscore the MobileTurkerNeXt's superior classification process in differentiating among Bankart, SLAP, and normal conditions in orthopedic imaging. This underscores the potential of our proposed mobile CNN in advancing diagnostic capabilities and contributing significantly to the field of medical image analysis. |
| Keywords | Bankart detection; MobileTurkerNeXt ; SLAP detection; CNN ; Biomedical image classifcation |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 4601. Applied computing |
| Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
| Byline Affiliations | School of Business |
| School of Health and Medical Sciences | |
| Centre for Health Research |
Permalink -
https://research.usq.edu.au/item/zy91q/mobileturkernext-investigating-the-detection-of-bankart-and-slap-lesions-using-magnetic-resonance-images
40
total views0
total downloads1
views this month0
downloads this month