High Accuracy and Cost-Saving Active Learning 3D WD-UNet for Airway Segmentation

TL;DR

This paper introduces WD-UNet, a semi-supervised 3D deep learning model with active learning strategies that significantly reduces annotation costs and computational resources while maintaining high segmentation accuracy in medical CT scans.

Contribution

The paper presents a novel WD-UNet model that integrates Wasserstein discriminative learning with active learning, achieving high accuracy with less annotated data and computational cost.

Findings

WD-UNet outperforms state-of-the-art supervised models like 3DUNet and 3D CEUNet.

Using uncertainty metrics improves prediction accuracy.

Achieves better results with only 35% of annotated data.

Abstract

We propose a novel Deep Active Learning (DeepAL) model-3D Wasserstein Discriminative UNet (WD-UNet) for reducing the annotation effort of medical 3D Computed Tomography (CT) segmentation. The proposed WD-UNet learns in a semi-supervised way and accelerates learning convergence to meet or exceed the prediction metrics of supervised learning models. Our method can be embedded with different Active Learning (AL) strategies and different network structures. The model is evaluated on 3D lung airway CT scans for medical segmentation and show that the use of uncertainty metric, which is parametrized as an input of query strategy, leads to more accurate prediction results than some state-of-the-art Deep Learning (DL) supervised models, e.g.,3DUNet and 3D CEUNet. Compared to the above supervised DL methods, our WD-UNet not only saves the cost of annotation for radiologists but also saves computational resources. WD-UNet uses a limited amount of annotated data (35% of the total) to achieve better predictive metrics with a more efficient deep learning model algorithm.