EMONAS: Efficient multiobjective neural architecture search framework for 3D medical image segmentation

Maria G. Baldeon Calisto, Susana K. Lai-Yuen

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

1 Cita (Scopus)

Resumen

Deep learning plays a critical role in medical image segmentation. Nevertheless, manually designing a neural network for a specific segmentation problem is a very difficult and time-consuming task due to the massive hyperparameter search space, long training time and large volumetric data. Therefore, most designed networks are highly complex, task specific and over-parametrized. Recently, multiobjective neural architecture search (NAS) methods have been proposed to automate the design of accurate and efficient segmentation architectures. However, they only search for either the macro- or micro-structure of the architecture, do not use the information produced during the optimization process to increase the efficiency of the search, and do not consider the volumetric nature of medical images. In this work, we propose EMONAS, an Efficient MultiObjective Neural Architecture Search framework for 3D medical image segmentation. EMONAS is composed of a search space that considers both the macro- and micro-structure of the architecture, and a surrogate-assisted multiobjective evolutionary based algorithm that efficiently searches for the best hyperparameters using a Random Forest surrogate and guiding selection probabilities. EMONAS is evaluated on the task of cardiac segmentation from the ACDC MICCAI challenge. The architecture found is ranked within the top 10 submissions in all evaluation metrics, performing better or comparable to other approaches while reducing the search time by more than 50% and having considerably fewer number of parameters.

Idioma originalInglés
Título de la publicación alojadaMedical Imaging 2021
Subtítulo de la publicación alojadaImage Processing
EditoresIvana Isgum, Bennett A. Landman
EditorialSPIE
ISBN (versión digital)9781510640214
DOI
EstadoPublicada - 2021
Publicado de forma externa
EventoMedical Imaging 2021: Image Processing - Virtual, Online, Estados Unidos
Duración: 15 feb. 202119 feb. 2021

Serie de la publicación

NombreProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volumen11596
ISSN (versión impresa)1605-7422

Conferencia

ConferenciaMedical Imaging 2021: Image Processing
País/TerritorioEstados Unidos
CiudadVirtual, Online
Período15/02/2119/02/21

Huella

Profundice en los temas de investigación de 'EMONAS: Efficient multiobjective neural architecture search framework for 3D medical image segmentation'. En conjunto forman una huella única.

Citar esto