PE-MED: Prompt Enhancement for Interactive Medical Image Segmentation

TL;DR

PE-MED introduces a novel interactive medical image segmentation framework that leverages prompt enhancement techniques, including a Self-Loop strategy, Prompt Attention Learning Module, and Time Series Information Propagation, to improve accuracy and stability.

Contribution

The paper presents a new framework with prompt enhancement components that better utilize user interactions and temporal information for improved segmentation performance.

Findings

Outperforms state-of-the-art methods in accuracy

Demonstrates increased stability in segmentation results

Effectively utilizes multi-interaction temporal data

Abstract

Interactive medical image segmentation refers to the accurate segmentation of the target of interest through interaction (e.g., click) between the user and the image. It has been widely studied in recent years as it is less dependent on abundant annotated data and more flexible than fully automated segmentation. However, current studies have not fully explored user-provided prompt information (e.g., points), including the knowledge mined in one interaction, and the relationship between multiple interactions. Thus, in this paper, we introduce a novel framework equipped with prompt enhancement, called PE-MED, for interactive medical image segmentation. First, we introduce a Self-Loop strategy to generate warm initial segmentation results based on the first prompt. It can prevent the highly unfavorable scenarios, such as encountering a blank mask as the initial input after the first interaction. Second, we propose a novel Prompt Attention Learning Module (PALM) to mine useful prompt information in one interaction, enhancing the responsiveness of the network to user clicks. Last, we build a Time Series Information Propagation (TSIP) mechanism to extract the temporal relationships between multiple interactions and increase the model stability. Comparative experiments with other state-of-the-art (SOTA) medical image segmentation algorithms show that our method exhibits better segmentation accuracy and stability.