Unleashing Diffusion and State Space Models for Medical Image Segmentation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wu, Rong, Chen, Ziqi, Zhong, Liming, Li, Heng, Shu, Hai
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908428489719808
author Wu, Rong
Chen, Ziqi
Zhong, Liming
Li, Heng
Shu, Hai
author_facet Wu, Rong
Chen, Ziqi
Zhong, Liming
Li, Heng
Shu, Hai
contents Existing segmentation models trained on a single medical imaging dataset often lack robustness when encountering unseen organs or tumors. Developing a robust model capable of identifying rare or novel tumor categories not present during training is crucial for advancing medical imaging applications. We propose DSM, a novel framework that leverages diffusion and state space models to segment unseen tumor categories beyond the training data. DSM utilizes two sets of object queries trained within modified attention decoders to enhance classification accuracy. Initially, the model learns organ queries using an object-aware feature grouping strategy to capture organ-level visual features. It then refines tumor queries by focusing on diffusion-based visual prompts, enabling precise segmentation of previously unseen tumors. Furthermore, we incorporate diffusion-guided feature fusion to improve semantic segmentation performance. By integrating CLIP text embeddings, DSM captures category-sensitive classes to improve linguistic transfer knowledge, thereby enhancing the model's robustness across diverse scenarios and multi-label tasks. Extensive experiments demonstrate the superior performance of DSM in various tumor segmentation tasks. Code is available at https://github.com/Rows21/k-Means_Mask_Mamba.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12747
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unleashing Diffusion and State Space Models for Medical Image Segmentation
Wu, Rong
Chen, Ziqi
Zhong, Liming
Li, Heng
Shu, Hai
Computer Vision and Pattern Recognition
Artificial Intelligence
Existing segmentation models trained on a single medical imaging dataset often lack robustness when encountering unseen organs or tumors. Developing a robust model capable of identifying rare or novel tumor categories not present during training is crucial for advancing medical imaging applications. We propose DSM, a novel framework that leverages diffusion and state space models to segment unseen tumor categories beyond the training data. DSM utilizes two sets of object queries trained within modified attention decoders to enhance classification accuracy. Initially, the model learns organ queries using an object-aware feature grouping strategy to capture organ-level visual features. It then refines tumor queries by focusing on diffusion-based visual prompts, enabling precise segmentation of previously unseen tumors. Furthermore, we incorporate diffusion-guided feature fusion to improve semantic segmentation performance. By integrating CLIP text embeddings, DSM captures category-sensitive classes to improve linguistic transfer knowledge, thereby enhancing the model's robustness across diverse scenarios and multi-label tasks. Extensive experiments demonstrate the superior performance of DSM in various tumor segmentation tasks. Code is available at https://github.com/Rows21/k-Means_Mask_Mamba.
title Unleashing Diffusion and State Space Models for Medical Image Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.12747