Related Experiment Video
Updated: Apr 26, 2026
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
5.8K
Hybrid diagnostic framework for bone cancer detection using deep learning and radiomics analysis.
Ramesh Ramamoorthy1, R S Shanmugasundaram1, A Athiraja2
1Department of Computer Science and Engineering, Vinayaka Mission's Kirupananda Variyar Engineering College, Vinayaka Mission's Research Foundation (Deemed to be University), Salem, Tamilnadu, India.
Scientific Reports
|April 24, 2026
Summary
This study introduces TriMedNet, a novel hybrid framework for bone cancer classification using multi-modal data. Combining imaging, clinical notes, and patient metrics, it achieves high diagnostic accuracy, improving early detection and treatment outcomes.
Area of Science:
- Oncology
- Medical Imaging
- Artificial Intelligence
Background:
- Bone cancer diagnosis presents significant healthcare challenges, necessitating accurate and early detection for effective treatment.
- Current diagnostic methods often rely on single data types, potentially limiting accuracy.
Purpose of the Study:
- To develop and evaluate TriMedNet, a novel hybrid framework for bone cancer classification.
- To investigate the efficacy of integrating multi-modal data sources for improved diagnostic performance.
Main Methods:
- TriMedNet integrates Convolutional Neural Network (CNN) for MRI analysis, Bidirectional Encoder Representations from Transformers (BERT) for clinical notes, and dense layers for patient metrics.
- Features from these specialized branches are fused for final tumor classification.
- The framework was trained and validated on the Roboflow dataset, incorporating biopsy and blood test results.
Main Results:
- TriMedNet achieved a diagnostic accuracy of 98.5%, precision of 97.6%, and recall of 98.2%.
- The study confirmed that fusing multi-modal features significantly enhances diagnostic performance compared to single-modality approaches.
Conclusions:
- The TriMedNet framework demonstrates high accuracy and effectiveness in bone cancer diagnosis.
- Multi-modal data integration offers a promising avenue for advancing bone cancer detection and supporting clinical decision-making.
