High Accuracy and Cost-Saving Active Learning 3D WD-UNet for Airway Segmentation
This work addresses the cost and resource challenges in medical image segmentation for radiologists, though it appears incremental as it builds on existing active learning and network structures.
The paper tackles the problem of reducing annotation effort for 3D CT segmentation by proposing a deep active learning model called WD-UNet, which uses only 35% of annotated data to achieve better predictive metrics than supervised models like 3DUNet and 3D CEUNet.
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.