METGAN: Generative Tumour Inpainting and Modality Synthesis in Light Sheet Microscopy

04/22/2021
by   Izabela Horvath, et al.
7

Novel multimodal imaging methods are capable of generating extensive, super high resolution datasets for preclinical research. Yet, a massive lack of annotations prevents the broad use of deep learning to analyze such data. So far, existing generative models fail to mitigate this problem because of frequent labeling errors. In this paper, we introduce a novel generative method which leverages real anatomical information to generate realistic image-label pairs of tumours. We construct a dual-pathway generator, for the anatomical image and label, trained in a cycle-consistent setup, constrained by an independent, pretrained segmentor. The generated images yield significant quantitative improvement compared to existing methods. To validate the quality of synthesis, we train segmentation networks on a dataset augmented with the synthetic data, substantially improving the segmentation over baseline.

READ FULL TEXT

page 2

page 9

page 15

page 16

research
04/14/2022

Sketch guided and progressive growing GAN for realistic and editable ultrasound image synthesis

Ultrasound (US) imaging is widely used for anatomical structure inspecti...
research
03/28/2022

Cycle-Consistent Counterfactuals by Latent Transformations

CounterFactual (CF) visual explanations try to find images similar to th...
research
05/09/2018

SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting

In this paper, we focus on image inpainting task, aiming at recovering t...
research
06/08/2022

Accelerating Score-based Generative Models for High-Resolution Image Synthesis

Score-based generative models (SGMs) have recently emerged as a promisin...
research
05/25/2020

SegAttnGAN: Text to Image Generation with Segmentation Attention

In this paper, we propose a novel generative network (SegAttnGAN) that u...
research
09/20/2018

C4Synth: Cross-Caption Cycle-Consistent Text-to-Image Synthesis

Generating an image from its description is a challenging task worth sol...
research
10/13/2021

DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning

Automatic font generation based on deep learning has aroused a lot of in...

Please sign up or login with your details

Forgot password? Click here to reset