Rapid model transfer for medical image segmentation via iterative human-in-the-loop update: from labelled public to unlabelled clinical datasets for multi-organ segmentation in CT

TL;DR

This paper introduces a human-in-the-loop transfer learning scheme for multi-organ CT segmentation that significantly reduces manual annotation time and improves model accuracy during dataset transfer.

Contribution

It proposes a novel iterative human-in-the-loop framework with igniter and sustainer networks for efficient model transfer from labeled to unlabeled datasets in medical imaging.

Findings

Model accuracy improved by 19.7% Dice score.

Manual labeling time reduced from 13.87 to 1.51 minutes per CT.

Framework demonstrates clinical usefulness and efficiency.

Abstract

Despite the remarkable success on medical image analysis with deep learning, it is still under exploration regarding how to rapidly transfer AI models from one dataset to another for clinical applications. This paper presents a novel and generic human-in-the-loop scheme for efficiently transferring a segmentation model from a small-scale labelled dataset to a larger-scale unlabelled dataset for multi-organ segmentation in CT. To achieve this, we propose to use an igniter network which can learn from a small-scale labelled dataset and generate coarse annotations to start the process of human-machine interaction. Then, we use a sustainer network for our larger-scale dataset, and iteratively updated it on the new annotated data. Moreover, we propose a flexible labelling strategy for the annotator to reduce the initial annotation workload. The model performance and the time cost of annotation in each subject evaluated on our private dataset are reported and analysed. The results show that our scheme can not only improve the performance by 19.7% on Dice, but also expedite the cost time of manual labelling from 13.87 min to 1.51 min per CT volume during the model transfer, demonstrating the clinical usefulness with promising potentials.