International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Multimodal Deep Learning in Bone Oncology: A Review on Cancer and Metastasis Detection |
|---|---|
| ABSTRACT | Bone cancer and bone metastasis are severe and potentially life-threatening conditions that require early detection and accurate diagnosis for effective treatment planning. Traditionally, diagnosis has relied on individual imaging modalities such as X-ray, CT, MRI, or SPECT. However, each modality provides only partial information—X-rays offer basic structural details, CT scans provide better bone resolution, MRI captures soft tissue variations, and SPECT highlights functional or metabolic activity. Relying on a single modality often limits the ability to fully understand the complexity of bone lesions. In recent years, rapid advancements in deep learning and multimodal machine learning have opened new possibilities for integrating heterogeneous medical imaging data. By combining multiple imaging modalities, it becomes possible to capture complementary anatomical and functional characteristics, leading to improved diagnostic accuracy and robustness. Deep learning models, particularly convolutional neural networks (CNNs) and hybrid architectures, have demonstrated significant success in feature extraction and classification tasks within medical imaging. This review presents a comprehensive and plagiarism-free synthesis of existing research focused on multimodal deep learning approaches for the detection of bone cancer and bone metastasis. It discusses how different imaging modalities such as X-ray, CT, MRI, and SPECT can be effectively fused using early fusion, late fusion, and hybrid fusion strategies. Furthermore, the review highlights commonly used datasets, pre-processing techniques, and evaluation metrics such as accuracy, sensitivity, specificity, and AUC. In addition, key challenges such as data scarcity, modality misalignment, high computational requirements, and lack of standardized benchmarks are critically analysed. The review also outlines future research directions, including the use of explainable AI, transfer learning, and real-time clinical decision support systems. Overall, this work aims to serve as a valuable reference for researchers, students, and healthcare professionals interested in applying advanced machine learning techniques to improve bone cancer diagnosis. |
| AUTHOR | SONAL S. MOHITE, PROF. DR. DEIPALI V. GORE M. Tech Student, Department of Computer Engineering, P. E. S.’s Modern College of Engineering, Pune, India Associate Professor, Department of Computer Engineering, P. E. S.’s Modern College of Engineering, Pune, India |
| VOLUME | 183 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1404142 |
| pdf/142_Multimodal Deep Learning in Bone Oncology A Review on Cancer and Metastasis Detection.pdf | |
| KEYWORDS | |
| References | 1. Xu X., et al., “Deep CNN for Primary Bone Tumor Detection in Knee Radiographs,” Journal of Digital Imaging, 2023. 2. Song L., et al., “MRI-based Bone Tumor Classification Using Deep Learning,” Medical Physics, 2024. 3. Zhang Y., et al., “EfficientNetB0 for Lung Nodule Detection in CT,” IEEE Access, 2024. 4. Li H., et al., “Multimodal CNN Fusion for Brain Tumor Classification,” Frontiers in Neuroscience, 2025. 5. Huo T., et al., “Adaptive Attention Fusion for MRI & CT Diagnosis,” Neural Networks, 2025. 6. Shang R., et al., “Multimodal Image Fusion for Tumor Boundary Delineation,” SPIE Proceedings, 2025. 7. Selvaraju R.R., et al., “Grad-CAM: Visual Explanations from Deep Networks,” ICCV, 2020. 8. Sundararajan M., et al., “Axiomatic Attribution for Deep Networks,” ICML, 2017. 9. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770–778. 10. G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 4700–4708. 11. M. Tan and Q. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proc. Int. Conf. Mach. Learn. (ICML), 2019, pp. 6105–6114. 12. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent. (MICCAI), 2015, pp. 234–241. 13. A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, 2017. 14. H. Greenspan, B. van Ginneken, and R. M. Summers, “Guest editorial: Deep learning in medical imaging: Overview and future promise of an exciting new technique,” IEEE Trans. Med. Imaging, vol. 35, no. 5, pp. 1153–1159, 2016. 15. R. Yamashita, M. Nishio, R. K. Do, and K. Togashi, “Convolutional neural networks: An overview and application in radiology,” Insights into Imaging, vol. 9, no. 4, pp. 611–629, 2018 |
