Medical Image Segmentation via Unsupervised Convolutional Neural Network
This addresses the challenge of limited labeled data for medical imaging practitioners, though it is incremental as it adapts existing methods to a specific domain.
The paper tackles the problem of requiring large labeled datasets for medical image segmentation by proposing a model that can be trained semi- or unsupervised, achieving fast and high-quality bone segmentation in SPECT images.
For the majority of the learning-based segmentation methods, a large quantity of high-quality training data is required. In this paper, we present a novel learning-based segmentation model that could be trained semi- or un- supervised. Specifically, in the unsupervised setting, we parameterize the Active contour without edges (ACWE) framework via a convolutional neural network (ConvNet), and optimize the parameters of the ConvNet using a self-supervised method. In another setting (semi-supervised), the auxiliary segmentation ground truth is used during training. We show that the method provides fast and high-quality bone segmentation in the context of single-photon emission computed tomography (SPECT) image.