2020/08/17 by Pulkit Khandelwal, Khandelwal, Pulkit, Paul A. Yushkevich +1 · 3 citations
Computer Science · Engineering · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Medical Imaging and Analysis #Radiomics and Machine Learning in Medical Imaging #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2008.07724
openalex publication_date 2020/08/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep learning models perform best when tested on target (test) data domains\nwhose distribution is similar to the set of source (train) domains. However,\nmodel generalization can be hindered when there is significant difference in\nthe underlying statistics between the target and source domains. In this work,\nwe adapt a domain generalization method based on a model-agnostic meta-learning\nframework to biomedical imaging. The method learns a domain-agnostic feature\nrepresentation to improve generalization of models to the unseen test\ndistribution. The method can be used for any imaging task, as it does not\ndepend on the underlying model architecture. We validate the approach through a\ncomputed tomography (CT) vertebrae segmentation task across healthy and\npathological cases on three datasets. Next, we employ few-shot learning, i.e.\ntraining the generalized model using very few examples from the unseen domain,\nto quickly adapt the model to new unseen data distribution. Our results suggest\nthat the method could help generalize models across different medical centers,\nimage acquisition protocols, anatomies, different regions in a given scan,\nhealthy and diseased populations across varied imaging modalities.\n