Producción CyT

Supervision by Denoising

Artículo

Autoría:

Sean Young ; FERRANTE, ENZO ; Polina Goland ; Christopher Metzler ; Bruce Fischl ; Juan Eugenio Iglesias

Fecha:

2023

Editorial y Lugar de Edición:

IEEE Computer Society

Revista:

IEEE Transactions on Pattern Analysis and Machine Intelligence IEEE Computer Society

Resumen *

Learning-based image reconstruction models, such as those based on the U-Net, require a large set of labeled images if good generalization is to be guaranteed. In some imaging domains, however, labeled data with pixel- or voxel-level label accuracy are scarce due to the cost of acquiring them. This problem is exacerbated further in domains like medical imaging, where there is no single ground truth label, resulting in large amounts of repeat variability in the labels. Therefore, training reconstruction networks to generalize better by learning from both labeled and unlabeled examples (called semi-supervised learning) is problem of practical and theoretical interest. However, traditional semi-supervised learning methods for image reconstruction often necessitate handcrafting a differentiable regularizer specific to some given imaging problem, which can be extremely time-consuming. In this work, we propose “supervision by denoising” (SUD), a framework to supervise reconstruction models using their own denoised output as labels. SUD unifies stochastic averaging and spatial denoising techniques under a spatio-temporal denoising framework and alternates denoising and model weight update steps in an optimization framework for semi-supervision. As example applications, we apply SUD to two problems from biomedical imaging—anatomical brain reconstruction (3D) and cortical parcellation (2D)—to demonstrate a significant improvement in reconstruction over supervised-only and ensembling baselines. Our code available at https://github.com/seannz/sud . Información suministrada por el agente en SIGEVA

Palabras Clave

regularizationdeep learningmedical image segmentation