Self-supervised dynamic MRI reconstruction
| Autor: | Mert Acar, Tolga Çukur, Ilkay Oksuz |
|---|---|
| Přispěvatelé: | Acar, Mert, Çukur, Tolga |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Self-supervised learning
Training set business.industry Computer science Reliability (computer networking) Deep learning Construct (python library) Working hypothesis Machine learning computer.software_genre Convolutional neural network Network output ComputingMethodologies_PATTERNRECOGNITION Dynamic reconstruction Dynamic contrast-enhanced MRI Convolutional neural networks Artificial intelligence business computer Cardiac MRI |
| Zdroj: | Lecture Notes in Computer Science Machine Learning for Medical Image Reconstruction ISBN: 9783030885519 MLMIR@MICCAI |
| Popis: | Conference Name: International Workshop on Machine Learning for Medical Image Reconstruction, MLMIR 2021 Date of Conference: 1 October 2021 Deep learning techniques have recently been adopted for accelerating dynamic MRI acquisitions. Yet, common frameworks for model training rely on availability of large sets of fully-sampled MRI data to construct a ground-truth for the network output. This heavy reliance is undesirable as it is challenging to collect such large datasets in many applications, and even impossible for high spatiotemporal-resolution protocols. In this paper, we introduce self-supervised training to deep neural architectures for dynamic reconstruction of cardiac MRI. We hypothesize that, in the absence of ground-truth data, elevating complexity in self-supervised models can instead constrain model performance due to the deficiencies in training data. To test this working hypothesis, we adopt self-supervised learning on recent state-of-the-art deep models for dynamic MRI, with varying degrees of model complexity. Comparison of supervised and self-supervised variants of deep reconstruction models reveals that compact models have a remarkable advantage in reliability against performance loss in self-supervised settings. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|