Dermatological images are typically diagnosed based on visual analysis of the skin lesion acquired using a dermoscope. However, the final quality of the acquired image is highly dependent on the illumination conditions during the acquisition phase. This variability in the light source can affect the dermatologist's diagnosis and decrease the accuracy of computer-aided diagnosis systems. Color constancy algorithms have proven to be a powerful tool to address this issue by allowing the standardization of the image illumination source, but the most commonly used algorithms still present some inherent limitations due to assumptions made on the original image. In this work, we propose a novel Dermatological Color Constancy Generative Adversarial Network (DermoCC-GAN) algorithm to overcome the current limitations by formulating the color constancy task as an image-to-image translation problem.

DermoCC-GAN: A new approach for standardizing dermatological images using generative adversarial networks / Salvi, Massimo; Branciforti, Francesco; Veronese, Federica; Zavattaro, Elisa; Tarantino, Vanessa; Savoia, Paola; Meiburger, Kristen M. - In: COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE. - ISSN 0169-2607. - 225:(2022). [10.1016/j.cmpb.2022.107040]

DermoCC-GAN: A new approach for standardizing dermatological images using generative adversarial networks

Salvi, Massimo;Branciforti, Francesco;Meiburger, Kristen M
2022

Abstract

Dermatological images are typically diagnosed based on visual analysis of the skin lesion acquired using a dermoscope. However, the final quality of the acquired image is highly dependent on the illumination conditions during the acquisition phase. This variability in the light source can affect the dermatologist's diagnosis and decrease the accuracy of computer-aided diagnosis systems. Color constancy algorithms have proven to be a powerful tool to address this issue by allowing the standardization of the image illumination source, but the most commonly used algorithms still present some inherent limitations due to assumptions made on the original image. In this work, we propose a novel Dermatological Color Constancy Generative Adversarial Network (DermoCC-GAN) algorithm to overcome the current limitations by formulating the color constancy task as an image-to-image translation problem.
File in questo prodotto:
File Dimensione Formato  
(2022) paper - dermoCC-GAN.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 5.88 MB
Formato Adobe PDF
5.88 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
manuscript.docx

embargo fino al 25/07/2023

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Creative commons
Dimensione 15.37 MB
Formato Microsoft Word XML
15.37 MB Microsoft Word XML   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2970648