Simple Linear Combination Inputs and Model Ensembling for Enhanced Brain Tumor Segmentation in Post-Surgical Glioma MRI

References

[1] K. R. Gh, “Enhancing Explainability and Performance in Brain Tumor Classification Using CNN and Scattering Networks on MRI Data,” 2025. Available: https://

[2] L. K. K. Rajendran, “Personalized Prediction of Lymph Node Involvement in Head and Neck Squamous Cell Carcinomas Using Mixture Hidden Markov Models Incorporating Tumor,” 2025. Available: https://

[3] P. Parashar, “Enhanced Visual Statistical Inference: Comparative Evaluation with Linear Model Testing,” 2025. Available: https://

[4] S. Korde, “AI-Driven Exercise Monitoring for Non- Surgical Obesity Treatment: A Deep Learning-Based Posture and Movement Optimization System,” 2025. Available: https://journals.femington.com/ijcrms/article/view/126.

[5] S. Tendulkar, “Enhancing Differential Privacy in Deep Learning: Efficient Techniques for Training Large Models,” 2025. Available: https://ieeexplore.ieee.org/document/11005164.

[6] V. Chitukoori, “Interpretable Neural Networks: Bridging Generalized Additive Models and Deep Learning for Enhanced Transparency and Flexibility,” 2025. Available: https://www.computer.org/csdl/proceedings- article/sera/2025/11154505/2a3zaIeuEJa.

[7] P. Patel, “Evaluating Ensemble Learning Strategies for Enhanced Medical Diagnostics: Insights from Real-World Datasets,” 2025. Available: https://

[8] R. Rajeev, “Verifying Sequential Programs in Untrusted Environments.”

[9] S. Bagde, “Ontology-Driven Integration of Urban Planning Data for Enhanced Civil Engineering Applications,” 2025. Available: https://

[10] M. Zawar, “Exploring the Role of Brownian Motion in Financial Modeling: A Stochastic Approach to the Black- Scholes Model for European Call Options,” 2025. Available: https://

[11] S. Malipeddi, “Securing Personal Cloud Storage: Introducing LAUXUS for Enhanced Data Privacy and Traceability,” 2025. Available: https://

[12] S. Reddy, “Exploring Mechanistic Interpretability in Large Language Models: Challenges, Approaches, and Insights,” 2025. Available: https://ieeexplore.ieee.org/document/11011640.

[13] O. Ladapo, “Revolutionizing Data Preparation and Access for Visual and Multi-Modal Business Analytics,” 2025. Available: https://

[14] K. Bhatt, “A Debiasing Framework for Graph Neural Networks Using Contrastive Learning,” 2025. Available: https://

[15] S. Hardia, “AI-Driven Brainwave Analysis for Anomalous Neurological Event Detection,” 2026. Available: https:// 9.

[16] P. S., “Efficient Nonlinear Solid Mechanics Computation via Krylov Subspace Methods in a Finite Volume Framework,” 2025. Available: https:// .

[17] A. Veluru, “Synergistic Integration of Linear Logic and Recurrent Neural Networks for Enhanced Sequence Modeling,” 2025. Available: https://

[18] R. Muthusivarajan, A. Celaya, M. Farhat, W. Talpur, H. Langshaw, V. White, et al., “Deep Learning-Based Automated Post-Operative Gross Tumor Volume Segmentation in Glioblastoma Patients,” arXiv preprint arXiv:2409.15177, 2024.

[19] R. H. Helland, A. Ferles, A. Pedersen, I. Kommers, H. Ardon, F. Barkhof, et al., “Segmentation of glioblastomas in early post-operative multimodal MRI with deep neural networks,” Scientific Reports, vol. 13, no. 1, p. 18897, 2023.

[20] T. Kabir, K. L. Hsieh, L. Nunez, Y. C. Hsu, J. C. Rodriguez Quintero, O. Arevalo, et al., “A Bayesian deep segmentation framework for glioblastoma tumor segmentation using follow-up MRIs,” Frontiers in Neuroimaging, vol. 4, p. 1630245, 2025.

@article{1724918,
      author = {Dilip Sharma},
      title = {Simple Linear Combination Inputs and Model Ensembling for Enhanced Brain Tumor Segmentation in Post-Surgical Glioma MRI},
      journal = {Iconic Research And Engineering Journals},
      year = {2022},
      volume = {6},
      number = {1},
      pages = {894-901},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1724918.pdf},
      abstract = {Segmentation is a critical task in medical imaging, often serving as an essential first step or prerequisite for the analysis of medical volumes. However, treatments such as surgery complicate the accurate delineation of regions of interest, particularly in the case of brain tumors. The BraTS Post-Treatment 2024 Challenge recently released the first public dataset for post-surgery glioma segmentation, aiming to advance automated segmentation tools for brain tumors in MRI data. In this work, we propose two straightforward yet effective approaches to enhance deep learning-based brain tumor segmentation. First, we introduce an additional input derived from a simple linear combination of the available MRI sequences, which effectively highlights enhancing tumor regions. Second, we apply various ensembling methods to strategically weight the contributions of multiple models. Our results demonstrate that these approaches significantly improve segmentation performance compared to baseline models, underscoring the effectiveness of simple, computationally efficient techniques in improving brain tumor segmentation in the challenging post-surgical setting.},
      month = {July},
      doi = {https://doi.org/10.64388/ire1724918}
  }