Knowledge-Guided Prompt Learning for Lifespan Brain MR Image Segmentation

TL;DR

This paper introduces a two-step brain MRI segmentation framework using Knowledge-Guided Prompt Learning, which improves accuracy across the lifespan by incorporating semantic knowledge and handling limited labeled data.

Contribution

The novel KGPL method combines large-scale pre-training with knowledge-driven embeddings to enhance brain MRI segmentation across diverse ages.

Findings

Achieves average DSC of 95.17% for tissue segmentation.

Demonstrates robustness across age groups.

Outperforms existing methods in accuracy.

Abstract

Automatic and accurate segmentation of brain MR images throughout the human lifespan into tissue and structure is crucial for understanding brain development and diagnosing diseases. However, challenges arise from the intricate variations in brain appearance due to rapid early brain development, aging, and disorders, compounded by the limited availability of manually-labeled datasets. In response, we present a two-step segmentation framework employing Knowledge-Guided Prompt Learning (KGPL) for brain MRI. Specifically, we first pre-train segmentation models on large-scale datasets with sub-optimal labels, followed by the incorporation of knowledge-driven embeddings learned from image-text alignment into the models. The introduction of knowledge-wise prompts captures semantic relationships between anatomical variability and biological processes, enabling models to learn structural feature embeddings across diverse age groups. Experimental findings demonstrate the superiority and robustness of our proposed method, particularly noticeable when employing Swin UNETR as the backbone. Our approach achieves average DSC values of 95.17% and 94.19% for brain tissue and structure segmentation, respectively. Our code is available at https://github.com/TL9792/KGPL.