A latent space exploration for microscopic skin lesion augmentations with VQ-VAE-2 and PixelSNAIL

Alessio Gallucci, Nicola Pezzotti, Dmitry Znamenskiy, Milan Petkovic

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

3 Citaten (Scopus)


Skin cancer affects more than 3 million people only in the US. Comprehensive microscopic databases include around 30 thousand samples, limiting the richness of patterns that can be presented to machine learning. To this end, generative models such as GANs have been proposed for creating realistic synthetic images but, despite their popularity, they are often difficult to train and control. Recently an autoregressive approach based on a quantized autoencoder showed state of the art performances while being simple to train and provide synthetic data generation opportunities. In the first part of this paper we evaluate the training of VQ-VAE-2 with different latent space configuration. In the second part, we show how to use a learned prior over the latent space with PixelSNAIL to generate and modify skin lesions. We show how this process can be used for powerful data augmentation and visualization for skin health, evaluating it on a downstream application that classifies malignant lesions

Originele taal-2Engels
TitelMedical Imaging 2021
SubtitelImage Processing
RedacteurenIvana Isgum, Bennett A. Landman
ISBN van elektronische versie9781510640214
StatusGepubliceerd - 2021
EvenementSPIE Medical Imaging 2021 - Online, Verenigde Staten van Amerika
Duur: 15 feb. 202119 feb. 2021

Publicatie series

NaamProceedings of SPIE
ISSN van geprinte versie1605-7422


CongresSPIE Medical Imaging 2021
Land/RegioVerenigde Staten van Amerika

Bibliografische nota

Publisher Copyright:
© 2021 SPIE.


Duik in de onderzoeksthema's van 'A latent space exploration for microscopic skin lesion augmentations with VQ-VAE-2 and PixelSNAIL'. Samen vormen ze een unieke vingerafdruk.

Citeer dit