BrainSegDMlF: A Dynamic Fusion-enhanced SAM for Brain Lesion Segmentation

TL;DR

BrainSegDMlF is an automated, multi-modal brain lesion segmentation model that enhances detection accuracy, especially for small lesions, by integrating dynamic fusion and automatic mask generation, overcoming limitations of existing methods.

Contribution

The paper introduces BrainSegDMlF, a novel model with dynamic multi-modal fusion, layer-wise decoding, and automatic segmentation, advancing brain lesion segmentation accuracy and automation.

Findings

Improved detection of small lesions in brain images.

Effective multi-modal data integration during encoding.

Automatic segmentation masks without manual prompts.

Abstract

The segmentation of substantial brain lesions is a significant and challenging task in the field of medical image segmentation. Substantial brain lesions in brain imaging exhibit high heterogeneity, with indistinct boundaries between lesion regions and normal brain tissue. Small lesions in single slices are difficult to identify, making the accurate and reproducible segmentation of abnormal regions, as well as their feature description, highly complex. Existing methods have the following limitations: 1) They rely solely on single-modal information for learning, neglecting the multi-modal information commonly used in diagnosis. This hampers the ability to comprehensively acquire brain lesion information from multiple perspectives and prevents the effective integration and utilization of multi-modal data inputs, thereby limiting a holistic understanding of lesions. 2) They are constrained by the amount of data available, leading to low sensitivity to small lesions and difficulty in detecting subtle pathological changes. 3) Current SAM-based models rely on external prompts, which cannot achieve automatic segmentation and, to some extent, affect diagnostic efficiency.To address these issues, we have developed a large-scale fully automated segmentation model specifically designed for brain lesion segmentation, named BrainSegDMLF. This model has the following features: 1) Dynamic Modal Interactive Fusion (DMIF) module that processes and integrates multi-modal data during the encoding process, providing the SAM encoder with more comprehensive modal information. 2) Layer-by-Layer Upsampling Decoder, enabling the model to extract rich low-level and high-level features even with limited data, thereby detecting the presence of small lesions. 3) Automatic segmentation masks, allowing the model to generate lesion masks automatically without requiring manual prompts.