Citation :

Rathla Roopsingh, D. Vasumathi, "Multi-Modal Treatment Response Prediction and Recurrence Risk Analysis for Bone Tumors Using A Hybrid Longitudinal Deep Reinforcement Model," International Journal of Electronics and Communication Engineering, vol. 13, no. 7, pp. 35-50, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I7P103

Abstract

Predicting treatment response and recurrence risk in bone tumor patients is crucial to the choice of effective therapeutic strategies and the enhancement of clinical outcome. However, currently available prognosis and decision-support tools are largely based on fixed imaging or univariate clinical measures, and are unable to learn over time disease dynamics and therapies' interaction. It is based on progress in tumor segmentation and grading and presents a new Hybrid Longitudinal Deep Reinforcement Model (HL-DRM) that was specifically created to predict multi-modal treatment responses and predict recurrence in bone tumors. The suggested model combines sequential CT/MRI images, radiomic features, and patient clinical history with a Temporal Fusion Transformer to learn patterns of tumor progression over time. A policy agent of reinforcement-learning predicts optimal treatment pathways (surgery, radiotherapy, chemotherapy, or combinations of those) by maximizing the survival reward signals. Moreover, a Recurrence-Aware Survival Module based on Cox neutral modelling is used to predict personalized recurrence probabilities and survival curves. Experimental analysis of a longitudinal bone tumor data set shows that HL-DRM is far more effective at predicting prognosis, response, and estimating risk of recurrence, as compared to standard prognosis models. This direction promotes the AI-based precision oncology and helps clinicians make evidence-based, personalized treatment choices.

Keywords

Multi-modal deep learning, Longitudinal medical imaging, Treatment response prediction, Recurrence risk analysis, Reinforcement learning, Temporal Fusion Transformer.

References

1. Liwen Song et al., “A Deep Learning Model to Enhance the Classification of Primary Bone Tumors based on Incomplete Multimodal Images in X-Ray, CT, and MRI,” Cancer Imaging, vol. 24, pp. 1-13, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Hang Sang et al., “Multimodal Deep Learning for Bone Tumor Diagnosis with Clinical Imaging, Pathology, and Blood Biomarkers,” Journal of Bone Oncology, vol. 55, pp. 1-9, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Abdalla Ibrahim et al., “Deep Learning-Based Identification of Bone Scintigraphies Containing Metastatic Bone Disease Foci,” Cancer Imaging, vol. 23, pp. 1-9, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Eatedal Alabdulkreem et al., “Bone Cancer Detection and Classification Using Owl Search Algorithm with Deep Learning on X-Ray Images,” IEEE Access, vol. 11, pp. 109095-109103, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Lakshmi Naga Jayaprada Gavarraju et al., “Integrating Multimodal Medical Imaging Data for Enhanced Bone Cancer Detection: A Deep Learning-Based Feature Fusion Approach,” Journal of Theoretical and Applied Information Technology, vol. 102, no. 18, pp. 6761-6773, 2024.
   [Google Scholar] [Publisher Link]
6. Chidiebere Ogbonna, and Ernest E. Onuiri, “Predictive Diagnostic Model for Early Osteoporosis Detection using Deep Learning and Multimodal Imaging Data: A Systematic Review and Meta-Analysis,” Asian Journal of Engineering and Applied Technologies, vol. 13, no. 2, pp. 28-35, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Chengquan Guo, Yan Chen, and Jianjun Li, “Radiographic Imaging and Diagnosis of Spinal Bone Tumors: AlexNet and ResNet for the Classification of Tumor Malignancy,” Journal of Bone Oncology, vol. 48, pp. 1-10, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Platon S. Papageorgiou et al., “Artificial Intelligence in Primary Malignant Bone Tumor Imaging: A Narrative Review,” Diagnostics, vol. 15, no. 13, pp. 1-24, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Bin Zhang et al., “Deep Learning of Lumbar Spine X-Ray for Osteopenia and Osteoporosis Screening: A Multicenter Retrospective Cohort Study,” Bone, vol. 140, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Guanfeng Chen et al., “Predicting Bone Metastasis Risk of Colorectal Tumors using Radiomics and Deep Learning ViT Model,” Journal of Bone Oncology, vol. 51, pp. 1-10, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Sebastian Breden et al., “Deep Learning-Based Detection of Bone Tumors around the Knee in X-Rays of Children,” Journal of Clinical Medicine, vol. 12, no. 18, pp. 1-9, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Zhi Wang et al., “Bone Density Measurement in Patients with Spinal Metastatic Tumors using Chest Quantitative CT Deep Learning Model,” Journal of Bone Oncology, vol. 49, pp. 1-7, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Claudio E. von Schacky et al., “Multitask Deep Learning for Segmentation and Classification of Primary Bone Tumors on Radiographs,” Radiology, vol. 301, no. 2, pp. 398-406, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Feyisope R. Eweje et al., “Deep Learning for Classification of Bone Lesions on Routine MRI,” EBioMedicine, vol. 68, pp. 1-9, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Jan Wuestemann et al., “Analysis of Bone Scans in Various Tumor Entities using a Deep-Learning-Based Artificial Neural Network Algorithm—Evaluation of Diagnostic Performance,” Cancers, vol. 12, no. 9, pp. 1-13, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Xiaowen Zhou et al., “Emerging Applications of Deep Learning in Bone Tumors: Current Advances and Challenges,” Frontiers in Oncology, vol. 12, pp. 1-13, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
17.  Yu He et al., “Deep Learning-Based Classification of Primary Bone Tumors on Radiographs: A Preliminary Study,” EBioMedicine, vol. 62, pp. 1-8, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
18.  Canyu Pan et al., “FemurTumorNet: Bone Tumor Classification in the Proximal Femur using DenseNet Model Based on Radiographs,” Journal of Bone Oncology, vol. 42, pp. 1-7, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Joseph M. Rich et al., “Deep Learning Image Segmentation approaches for Malignant Bone Lesions: A Systematic Review and Meta-Analysis,” Frontiers in Radiology, vol. 3, pp. 1-11, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Kanimozhi Sampath, Sivakumar Rajagopal, and Ananthakrishna Chintanpalli, “A Comparative Analysis of CNN-based Deep Learning Architectures for Early Diagnosis of Bone Cancer using CT Images,” Scientific Reports, vol. 14, pp. 1-9, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Nikolaos Papandrianos et al., “A Deep-Learning Approach for Diagnosis of Metastatic Breast Cancer in Bones from Whole-Body Scans,” Applied Sciences, vol. 10, no. 3, pp. 1-27, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Chen-I Hsieh et al., “Automated Bone Mineral Density Prediction and Fracture Risk Assessment using Plain Radiographs via Deep Learning,” Nature Communications, vol. 12, pp. 1-9, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Tao Peng et al., “A Study on Whether Deep Learning Models based on CT Images for Bone Density Classification and Prediction can be Used for Opportunistic Osteoporosis Screening,” Osteoporosis International, vol. 35, pp. 117-128, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Samira Masoudi et al., “Deep Learning-Based Staging of Bone Lesions from Computed Tomography Scans,” IEEE Access, vol. 9, pp. 87531-87542, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Hasan Hosseini et al., “Bone Tumors: A Systematic Review of Prevalence, Risk Determinants, and Survival Patterns,” BMC Cancer, vol. 25, pp. 1-11, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]