Anatomically Constrained Semi-supervised Learning for Echocardiography Segmentation
Thierry Judge, Arnaud Judge, Pierre-marc Jodoin
Deep convolutional neural networks (CNNs) have had great success for medical imaging segmentation. Many methods attained nearly perfect Dice scores, sometimes within inter-expert variability. However, CNNs require large amounts of labeled data and are not immune to producing anatomically implausible results, especially when applied to ultrasound images. In this paper, we propose a method that tackles both of these problems simultaneously. Our method optimizes anatomical segmentation metrics on both labeled and unlabeled data using a training scheme analogous to adversarial training. Our method allows the optimization of several hand-made non-differentiable metrics for any segmentation model and drastically reduces the number of anatomical errors.
Thursday 7th July
Poster Session 2.2 - onsite 11:00 - 12:00, virtual 15:20 - 16:20 (UTC+2)