AEPL: Automated and Editable Prompt Learning for Brain Tumor Segmentation

TL;DR

AEPL introduces an automated, editable prompt learning framework that integrates tumor grade information into brain tumor segmentation, improving accuracy and offering clinical flexibility.

Contribution

This work presents the first framework combining auto-generated prompts with manual editing for tumor segmentation, leveraging tumor grade for enhanced accuracy.

Findings

Achieves state-of-the-art results on BraTS 2018 dataset.

Effectively incorporates tumor grade into segmentation.

Allows manual prompt editing for fine-tuning.

Abstract

Brain tumor segmentation is crucial for accurate diagnosisand treatment planning, but the small size and irregular shapeof tumors pose significant challenges. Existing methods of-ten fail to effectively incorporate medical domain knowledgesuch as tumor grade, which correlates with tumor aggres-siveness and morphology, providing critical insights for moreaccurate detection of tumor subregions during segmentation.We propose an Automated and Editable Prompt Learning(AEPL) framework that integrates tumor grade into the seg-mentation process by combining multi-task learning andprompt learning with automatic and editable prompt gen-eration. Specifically, AEPL employs an encoder to extractimage features for both tumor-grade prediction and segmen-tation mask generation. The predicted tumor grades serveas auto-generated prompts, guiding the decoder to produceprecise segmentation masks. This eliminates the need formanual prompts while allowing clinicians to manually editthe auto-generated prompts to fine-tune the segmentation,enhancing both flexibility and precision. The proposed AEPLachieves state-of-the-art performance on the BraTS 2018dataset, demonstrating its effectiveness and clinical potential.The source code can be accessed online.