CLoPA: Continual Low Parameter Adaptation of Interactive Segmentation for Medical Image Annotation

TL;DR

CLoPA is a continual adaptation method that fine-tunes a small part of an interactive segmentation model during annotation, significantly improving performance across diverse medical imaging tasks without altering the inference process.

Contribution

It introduces a parameter-efficient continual adaptation strategy for interactive segmentation models, enhancing their accuracy in medical image annotation tasks.

Findings

Rapid performance improvement after a single training episode.

Effectiveness varies with task complexity and data regimes.

Deeper feature tuning needed for complex geometries.

Abstract

Interactive segmentation enables clinicians to guide annotation, but existing zero-shot models like nnInteractive fail to consistently reach expert-level performance across diverse medical imaging tasks. Because annotation campaigns produce a growing stream of task-specific labelled data, online adaptation of the segmentation model is a natural complement to zero-shot inference. We propose CLoPA, a continual adaptation strategy that tunes a small fraction of nnInteractive's parameters on the annotation cache, triggered by lightweight episode scheduling. CLoPA requires no new parameters or changes to the inference pipeline, and operates entirely within the existing annotation workflow. Across eight Medical Segmentation Decathlon tasks spanning diverse anatomical targets and imaging characteristics, CLoPA rapidly elevates performance to expert-level, even for tasks where nnInteractive previously failed, with the majority of gains realised after a single training episode. We show that the benefits of tuning different parameter groups depends on task characteristics and data regimes. Also, that for targets with complex geometries (e.g., hepatic vessels), instance normalisation and low-level feature tuning saturates, suggesting a need for deeper feature-representation alignment in the most challenging scenarios.