Scale-aware Test-time Click Adaptation for Pulmonary Nodule and Mass Segmentation

TL;DR

This paper introduces a scale-aware test-time adaptation method using lesion clicks to improve pulmonary nodule and mass segmentation, especially for large lesions, demonstrating consistent effectiveness across datasets.

Contribution

It proposes a novel multi-scale neural network with test-time click adaptation that enhances segmentation performance for lesions of various sizes in lung imaging.

Findings

Improved segmentation accuracy for large lesions.

Effective across multiple datasets and models.

Seamless integration into existing networks.

Abstract

Pulmonary nodules and masses are crucial imaging features in lung cancer screening that require careful management in clinical diagnosis. Despite the success of deep learning-based medical image segmentation, the robust performance on various sizes of lesions of nodule and mass is still challenging. In this paper, we propose a multi-scale neural network with scale-aware test-time adaptation to address this challenge. Specifically, we introduce an adaptive Scale-aware Test-time Click Adaptation method based on effortlessly obtainable lesion clicks as test-time cues to enhance segmentation performance, particularly for large lesions. The proposed method can be seamlessly integrated into existing networks. Extensive experiments on both open-source and in-house datasets consistently demonstrate the effectiveness of the proposed method over some CNN and Transformer-based segmentation methods. Our code is available at https://github.com/SplinterLi/SaTTCA