XLSTM-HVED: Cross-Modal Brain Tumor Segmentation and MRI Reconstruction Method Using Vision Xlstm and Heteromodal Variational Encoder-Decoder

Neurogliomas are among the most aggressive forms of can-cer, presenting considerable challenges in both treatment and monitoring due to their unpredictable biological behav-ior. Magnetic resonance imaging (MRI) is currently the preferred method for diagnosing and monitoring gliomas. However, the lac...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (International Symposium on Biomedical Imaging) pp. 1 - 5
Main Authors: Zhu, Shenghao, Chen, Yifei, Jiang, Shuo, Chen, Weihong, Liu, Chang, Wang, Yuanhan, Chen, Xu, Ke, Yifan, Qin, Feiwei, Wang, Changmiao, Zhu, Zhu
Format: Conference Proceeding
Language:English
Published: IEEE 14.04.2025
Subjects:
Accuracy
Biological system modeling
Brain modeling
Brain Tumor Segmentation
Brain tumors
Image reconstruction
Image segmentation
Magnetic resonance imaging
Missing Modality
Monitoring
Multi-task Learning
Multimodal MRI
Multitasking
Neuroglioma
Technological innovation
ISSN:1945-8452
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neurogliomas are among the most aggressive forms of can-cer, presenting considerable challenges in both treatment and monitoring due to their unpredictable biological behav-ior. Magnetic resonance imaging (MRI) is currently the preferred method for diagnosing and monitoring gliomas. However, the lack of specific imaging techniques often com-promises the accuracy of tumor segmentation during the imaging process. To address this issue, we introduce the XLSTM-HVED model. This model integrates a hetero-modal encoder-decoder framework with the Vision XLSTM module to reconstruct missing MRI modalities. By deeply fusing spa-tial and temporal features, it enhances tumor segmentation performance. The key innovation of our approach is the Self-Attention Variational Encoder (SAVE) module, which im-proves the integration of modal features. Additionally, it op-timizes the interaction of features between segmentation and reconstruction tasks through the Squeeze-Fusion-Excitation Cross Awareness (SFECA) module. Our experiments using the BraTS 2024 dataset demonstrate that our model signif-icantly outperforms existing advanced methods in handling cases where modalities are missing. Our source code is available at https://github.com/Quanat0607/XLSTM-HVED.
ISSN:1945-8452
DOI:10.1109/ISBI60581.2025.10981275