Projects per year
Abstract
Accurate classification of bone fractures is essential for effective treatment, yet traditional methods can be error-prone and time-consuming. Transfer learning, particularly feature-based transfer learning, has shown promise in improving medical image analysis. This study investigates the effectiveness of DenseNet architectures combined with SVM classifiers with default hy-perparameter for classifying hairline and pathological fractures. A dataset of 500 bone fracture x-ray images was utilized from open source for this study. Features were extracted using DenseNet121, DenseNet169, and Dense-Net201 models. The findings indicated that the combination of DenseNet169 and SVM yielded the highest overall accuracy and generalization capacity, with a notable proficiency in differentiating hairline fractures. The classifica-tion performance of DenseNet121-SVM and DenseNet201-SVM was robust, although significantly less successful in identifying hairline fractures. The exceptional performance of the DenseNet169-SVM model highlights its promise as a dependable tool for automated bone fracture classification in medical imaging. This work emphasizes the efficacy of integrating advanced transfer learning techniques with conventional classifiers to enhance diag-nostic precision, hence facilitating improvements in medical procedures. Ad-ditional investigation is advised to authenticate these discoveries using more extensive, practical clinical datasets.
Original language | English |
---|---|
Title of host publication | International Conference on Intelligent Manufacturing and Robotics 2024 |
Subtitle of host publication | ICiMR 2024 |
Publication status | Accepted/In press - 2024 |
Event | 2nd International Conference on Intelligent Manufacturing and Robotics (ICiMR) - Taicang, China Duration: 22 Aug 2024 → 23 Aug 2024 |
Conference
Conference | 2nd International Conference on Intelligent Manufacturing and Robotics (ICiMR) |
---|---|
Country/Territory | China |
Period | 22/08/24 → 23/08/24 |
Fingerprint
Dive into the research topics of 'Enhancing Bone Fracture Detection: A Feature-Based Transfer Learning Approach Using DenseNet with SVM'. Together they form a unique fingerprint.-
Innovative Syntegrative Education with Haier: Enhancing the Industry-Led Module Delivery for Customer orientated Mass Customisation and Manufacturing Systems with Haier
9/04/24 → 31/08/26
Project: Internal Research Project
-
Digital Twins of Micro Air Vehicle with Artificial Intelligence and Human-in-the-Loop for Future Farming
1/09/22 → 31/08/25
Project: Internal Research Project
-
The Formulation of a Transfer Learning Pipeline for Bone Fracture Diagnosis
1/06/24 → 30/09/24
Project: Internal Research Project
Activities
-
Enhancing Bone Fracture Detection: A Feature-Based Transfer Learning Approach Using DenseNet with SVM
Yang Luo (Speaker), Xiaoyan Liu (Speaker), Fan Zhang (Speaker) & Andrew Huey Ping Tan (Speaker)
22 Aug 2024Activity: Talk or presentation › Presentation at conference/workshop/seminar
-
2nd International Conference on Intelligent Manufacturing and Robotics (ICiMR)
Anwar P.P. Abdul Majeed (Organiser), Yang Luo (Organiser), Fan Zhang (Organiser) & Wei Chen (Chair)
22 Aug 2024 → 24 Aug 2024Activity: Participating in or organising an event › Organising an event e.g. a conference, workshop, …