Mammo-Mamba: A Hybrid State-Space and Transformer Architecture with Sequential Mixture of Experts for Multi-View Mammography

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bayatmakou, Farnoush, Taleei, Reza, Simone, Nicole, Mohammadi, Arash
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915406664433664
author Bayatmakou, Farnoush
Taleei, Reza
Simone, Nicole
Mohammadi, Arash
author_facet Bayatmakou, Farnoush
Taleei, Reza
Simone, Nicole
Mohammadi, Arash
contents Breast cancer (BC) remains one of the leading causes of cancer-related mortality among women, despite recent advances in Computer-Aided Diagnosis (CAD) systems. Accurate and efficient interpretation of multi-view mammograms is essential for early detection, driving a surge of interest in Artificial Intelligence (AI)-powered CAD models. While state-of-the-art multi-view mammogram classification models are largely based on Transformer architectures, their computational complexity scales quadratically with the number of image patches, highlighting the need for more efficient alternatives. To address this challenge, we propose Mammo-Mamba, a novel framework that integrates Selective State-Space Models (SSMs), transformer-based attention, and expert-driven feature refinement into a unified architecture. Mammo-Mamba extends the MambaVision backbone by introducing the Sequential Mixture of Experts (SeqMoE) mechanism through its customized SecMamba block. The SecMamba is a modified MambaVision block that enhances representation learning in high-resolution mammographic images by enabling content-adaptive feature refinement. These blocks are integrated into the deeper stages of MambaVision, allowing the model to progressively adjust feature emphasis through dynamic expert gating, effectively mitigating the limitations of traditional Transformer models. Evaluated on the CBIS-DDSM benchmark dataset, Mammo-Mamba achieves superior classification performance across all key metrics while maintaining computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17662
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mammo-Mamba: A Hybrid State-Space and Transformer Architecture with Sequential Mixture of Experts for Multi-View Mammography
Bayatmakou, Farnoush
Taleei, Reza
Simone, Nicole
Mohammadi, Arash
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Breast cancer (BC) remains one of the leading causes of cancer-related mortality among women, despite recent advances in Computer-Aided Diagnosis (CAD) systems. Accurate and efficient interpretation of multi-view mammograms is essential for early detection, driving a surge of interest in Artificial Intelligence (AI)-powered CAD models. While state-of-the-art multi-view mammogram classification models are largely based on Transformer architectures, their computational complexity scales quadratically with the number of image patches, highlighting the need for more efficient alternatives. To address this challenge, we propose Mammo-Mamba, a novel framework that integrates Selective State-Space Models (SSMs), transformer-based attention, and expert-driven feature refinement into a unified architecture. Mammo-Mamba extends the MambaVision backbone by introducing the Sequential Mixture of Experts (SeqMoE) mechanism through its customized SecMamba block. The SecMamba is a modified MambaVision block that enhances representation learning in high-resolution mammographic images by enabling content-adaptive feature refinement. These blocks are integrated into the deeper stages of MambaVision, allowing the model to progressively adjust feature emphasis through dynamic expert gating, effectively mitigating the limitations of traditional Transformer models. Evaluated on the CBIS-DDSM benchmark dataset, Mammo-Mamba achieves superior classification performance across all key metrics while maintaining computational efficiency.
title Mammo-Mamba: A Hybrid State-Space and Transformer Architecture with Sequential Mixture of Experts for Multi-View Mammography
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2507.17662