Representation Disentanglement for Multi-task Learning with application to Fetal Ultrasound

Autor: Qingjie Meng, Nick Pawlowski, Bernhard Kainz, Daniel Rueckert
Jazyk: angličtina
Rok vydání: 2019
Předmět:
FOS: Computer and information sciences
Computer Science - Machine Learning
Computer science
Multi-task learning
Machine Learning (stat.ML)
02 engineering and technology
Machine learning
computer.software_genre
Regularization (mathematics)
Image properties
Synthetic data
Machine Learning (cs.LG)
030218 nuclear medicine & medical imaging
03 medical and health sciences
0302 clinical medicine
Statistics - Machine Learning
FOS: Electrical engineering
electronic engineering
information engineering

0202 electrical engineering
electronic engineering
information engineering

Artificial Intelligence & Image Processing
business.industry
Deep learning
Image and Video Processing (eess.IV)
Electrical Engineering and Systems Science - Image and Video Processing
Deep neural networks
020201 artificial intelligence & image processing
Artificial intelligence
business
computer
Zdroj: Smart Ultrasound Imaging and Perinatal, Preterm and Paediatric Image Analysis ISBN: 9783030328740
SUSI/PIPPI@MICCAI
Smart Ultrasound Imaging and Perinatal, Preterm and Paediatric Image Analysis
Popis: One of the biggest challenges for deep learning algorithms in medical image analysis is the indiscriminate mixing of image properties, e.g. artifacts and anatomy. These entangled image properties lead to a semantically redundant feature encoding for the relevant task and thus lead to poor generalization of deep learning algorithms. In this paper we propose a novel representation disentanglement method to extract semantically meaningful and generalizable features for different tasks within a multi-task learning framework. Deep neural networks are utilized to ensure that the encoded features are maximally informative with respect to relevant tasks, while an adversarial regularization encourages these features to be disentangled and minimally informative about irrelevant tasks. We aim to use the disentangled representations to generalize the applicability of deep neural networks. We demonstrate the advantages of the proposed method on synthetic data as well as fetal ultrasound images. Our experiments illustrate that our method is capable of learning disentangled internal representations. It outperforms baseline methods in multiple tasks, especially on images with new properties, e.g. previously unseen artifacts in fetal ultrasound.
Databáze: OpenAIRE