Whole Image Synthesis Using a Deep Encoder-Decoder Network

Vasileios Sevetlidis, Mario Valerio Giuffrida, Sotirios A. Tsaftaris

SASHIMI 2016, in Conjunction with MICCAI (2016)

Vasileios Sevetlidis, Mario Valerio Giuffrida, Sotirios A. Tsaftaris (2016) “Whole Image Synthesis Using a Deep Encoder-Decoder Network,” SASHIMI 2016, Held in Conjunction with MICCAI.

Sevetlidis et al. (2015)
wp-content/uploads/2020/10/tex.png
Get Paper
@Inbook{Sevetlidis2016,
author="Sevetlidis, Vasileios and Giuffrida, Mario Valerio and Tsaftaris, Sotirios A.",
editor="Tsaftaris, Sotirios A. and Gooya, Ali and Frangi, Alejandro F. and Prince, Jerry L.",
title="Whole Image Synthesis Using a Deep Encoder-Decoder Network",
bookTitle="Simulation and Synthesis in Medical Imaging: First International Workshop, SASHIMI 2016, Held in Conjunction with MICCAI 2016, Athens, Greece, October 21, 2016, Proceedings",
year="2016",
publisher="Springer International Publishing",
address="Cham",
pages="127--137",
isbn="978-3-319-46630-9",
doi="10.1007/978-3-319-46630-9_13"
}

Abstract

The synthesis of medical images is an intensity transformation of a given modality in a way that represents an acquisition with a different modality (in the context of MRI this represents the synthesis of images originating from different MR sequences). Most methods follow a patch-based approach, which is computationally inefficient during synthesis and requires some sort of ?fusion? to synthesize a whole image from patch-level results. In this paper, we present a whole image synthesis approach that relies on deep neural networks. Our architecture resembles those of encoder-decoder networks, which aims to synthesize a source MRI modality to an other target MRI modality. The proposed method is computationally fast, it doesn?t require extensive amounts of memory, and produces comparable results to recent patch-based approaches.