Hybrid Deep Learning for Brain Tumor Segmentation in MRI Videos

DOI

10.2991/978-94-6239-727-9_20How to use a DOI?

Keywords

Brain Tumor Detection; Spatio-Temporal Features; 3D CNN - LSTM; Attention Mechanism

Abstract

Precise Brain Tumor Detection from MRI video scans is essential for effective treatment planning and diagnosis at early stage. Current methods often fight to model spatio-temporal dependencies, address class imbalance, and generalize across heterogeneous datasets. To overcome these limitations, this paper proposes deep learning framework for automated brain tumor segmentation in MRI video sequences. The proposed module employs a ResNet3D–LSTM architecture to extract discriminative spatio-temporal features, where ResNet3D acquires volumetric spatial information and LSTM develops temporal continuity across sequential MRI frames. For accurate tumor segmentation, a hybrid UNet–Feature Pyramid Network is applied to facilitate successful multi-scale feature fusion, capturing both local structural details and global contextual information. Experimental evaluations prove superior performance, with classification accuracies of 95% and 97% and Dice similarity coefficients ranging from 0.89 to 0.93 across multiple datasets. The proposed work confirms a strong and effective solution for MRI video-based brain tumor analysis, increasing diagnostic accuracy, generalization capability, and clinical applicability.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Swati V. Sakhare
PY  - 2026
DA  - 2026/07/22
TI  - Hybrid Deep Learning for Brain Tumor Segmentation in MRI Videos
BT  - Proceedings of the International Conference on Sustainable Micro-Nano Materials & Innovative Technology (ICSUMMIT 2026)
PB  - Atlantis Press
SP  - 266
EP  - 278
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-727-9_20
DO  - 10.2991/978-94-6239-727-9_20
ID  - Sakhare2026
ER  -