Assessing Test-time Variability for Interactive 3D Medical Image Segmentation with Diverse Point Prompts

TL;DR

This paper investigates how variability in user prompts during test-time affects the accuracy of interactive 3D medical image segmentation, proposing strategies for optimal prompt selection to improve robustness.

Contribution

It introduces a systematic assessment of test-time prompt variability in medical image segmentation and proposes an effective prompt selection strategy based on experimental analysis.

Findings

Additional prompts improve segmentation accuracy.

Prompt placement significantly affects results.

Optimal prompt selection enhances robustness and consistency.

Abstract

Interactive segmentation model leverages prompts from users to produce robust segmentation. This advancement is facilitated by prompt engineering, where interactive prompts serve as strong priors during test-time. However, this is an inherently subjective and hard-to-reproduce process. The variability in user expertise and inherently ambiguous boundaries in medical images can lead to inconsistent prompt selections, potentially affecting segmentation accuracy. This issue has not yet been extensively explored for medical imaging. In this paper, we assess the test-time variability for interactive medical image segmentation with diverse point prompts. For a given target region, the point is classified into three sub-regions: boundary, margin, and center. Our goal is to identify a straightforward and efficient approach for optimal prompt selection during test-time based on three considerations: (1) benefits of additional prompts, (2) effects of prompt placement, and (3) strategies for optimal prompt selection. We conduct extensive experiments on the public Medical Segmentation Decathlon dataset for challenging colon tumor segmentation task. We suggest an optimal strategy for prompt selection during test-time, supported by comprehensive results. The code is publicly available at https://github.com/MedICL-VU/variability