Early and accurate discovery of brain tumours is crucial for timely diagnosis and effective treatment planning. In this work, we put forward an explainable multimodal CNN–Transformer framework, kind of merges MRI and CT cues in a complementary way, using attention-guided multimodal fusion so that tumour classification and localisation can happen at the same time. Instead of most existing multimodal CNN–Transformer methods, which mostly linger on feature merging for classification only, this proposal does a bit more. It uses modality-specific CNN encoders, a Transformer based cross-modal attention module, and several fusion recipes—early fusion, late fusion, and attention-driven fusion. On top of that we do quantitative Grad-CAM checking against expert radiologist annotations, plus a computational efficiency examination, all inside a single coherent architecture. Overall this should boost interpretability and make the approach more clinically usable. For training and evaluation, the framework was tested with a carefully curated dataset of 1,986 patient-level MRI–CT pairs collected from BraTS 2021 and the TCIA Brain Tumour CT Archive. The dataset includes glioma, meningioma, pituitary tumour, and healthy controls. We used a patient-wise split: 70% for training, 15% for validation, and 15% for testing. When we looked at the attention based fusion approach, it delivered classification accuracy of 96.2 ± 0.3% and an AUC of 0.98. For localisation, Grad-CAM alignment produced a Dice overlap of 0.84 ± 0.04 versus annotations from three radiologists, across five separate experimental runs (reported as mean ± SD). Beyond the metrics, the framework also looks practical for real-world deployment. Inference time was 0.18 s per image, computational complexity reached 9.3 GFLOPs, and GPU memory use was 5.6 GB. So, these findings suggest that the proposed framework delivers an accurate, understandable, and compute friendly solution for multimodal brain tumour diagnosis, with clear benefits for clinical decision support.
Diptee Ghusse, Harshala Shingne, A. Yenkikar et al.· Discover Computing· 0 citations
Personalized cancer care depends on the seamless integration of genetic profiles, medical histories, and continuous patient monitoring to optimize therapeutic outcomes. Current clinical strategies struggle to combine these disparate, highly heterogeneous data streams, frequently resulting in incomplete diagnostic evaluations and suboptimal treatment selections. Factors such as poor cross-platform compatibility, low prediction precision, and the omission of real-time clinical parameters limit the practical deployment of precision medicine. To address these limitations, this study introduces BigCancerNet (BCN), a robust big data framework that merges multi-source information and uses a Graph Neural Network for Cancer Treatment Optimization (GNN-CTO) to accurately forecast individual drug responses and patient survival trajectories. This initiative is driven by the aspiration to boost treatment success, reduce toxic side effects, and permit flexible, patient-centric therapeutic adaptations. The processing pipeline comprises collecting genomic, clinical, and real-time biometric data from numerous repositories, including The Cancer Genome Atlas (TCGA), Gene Expression Omnibus (GEO), Cancer Dependency Map (DepMap), and hospital Electronic Health Records (EHRs). Data preprocessing applies Deep Embedding Networks (D2EN) to regularize genomic sequences, handle missing values, and standardize clinical features. The Hybrid Multi-Omics Fusion Algorithm (HMOFA) integrates these diverse datasets, harmonizing genomic, clinical, and wearable information while minimizing batch effects. The GNN-CTO model captures complex, nonlinear relationships among mutations, clinical factors, and drug responses, while Real-Time Model Adaptation with Dynamic Feedback Loop (RT-MADFL) continuously updates predictions. Results demonstrate reduced RMSE (0.160-0.245) and MAE (0.110-0.180), high stability with fold accuracy variance below 0.3%, fast training (12-15s per epoch), and prediction metrics exceeding 91%. Future work includes expanding to multi-cancer cohorts and integrating explainable AI to support transparent clinical decision-making.
A. M. Chimanna, Harshala Shingne, Shabana Pathan et al.· Cancer Investigation· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
