Cargando…

The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild

SIMPLE SUMMARY: Understanding the relationship between the skin cancerization field and actinic keratosis (AK) is crucial for identifying high-risk individuals, implementing early interventions, and preventing the progression to more aggressive forms of skin cancer. Currently, the clinical tools for...

Descripción completa

Detalles Bibliográficos
Autores principales: Derekas, Panagiotis, Spyridonos, Panagiota, Likas, Aristidis, Zampeta, Athanasia, Gaitanis, Georgios, Bassukas, Ioannis
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10571759/
https://www.ncbi.nlm.nih.gov/pubmed/37835555
http://dx.doi.org/10.3390/cancers15194861
_version_ 1785120076661260288
author Derekas, Panagiotis
Spyridonos, Panagiota
Likas, Aristidis
Zampeta, Athanasia
Gaitanis, Georgios
Bassukas, Ioannis
author_facet Derekas, Panagiotis
Spyridonos, Panagiota
Likas, Aristidis
Zampeta, Athanasia
Gaitanis, Georgios
Bassukas, Ioannis
author_sort Derekas, Panagiotis
collection PubMed
description SIMPLE SUMMARY: Understanding the relationship between the skin cancerization field and actinic keratosis (AK) is crucial for identifying high-risk individuals, implementing early interventions, and preventing the progression to more aggressive forms of skin cancer. Currently, the clinical tools for grading field cancerization primarily involve assessing AK burden. In addition to their inherent subjectivity, these grading systems are limited by the high degree of AK lesions’ recurrence. The present study proposes a method based on deep learning and semantic segmentation to improve the monitoring of the AK burden in clinical settings with enhanced automation and precision. The experimental results highlight the effectiveness of the proposed method, paving the way for more effective and reliable evaluation, continuous monitoring of condition progression, and assessment of treatment responses. ABSTRACT: AK is a common precancerous skin condition that requires effective detection and treatment monitoring. To improve the monitoring of the AK burden in clinical settings with enhanced automation and precision, the present study evaluates the application of semantic segmentation based on the U-Net architecture (i.e., AKU-Net). AKU-Net employs transfer learning to compensate for the relatively small dataset of annotated images and integrates a recurrent process based on convLSTM to exploit contextual information and address the challenges related to the low contrast and ambiguous boundaries of AK-affected skin regions. We used an annotated dataset of 569 clinical photographs from 115 patients with actinic keratosis to train and evaluate the model. From each photograph, patches of 512 × 512 pixels were extracted using translation lesion boxes that encompassed lesions in different positions and captured different contexts of perilesional skin. In total, 16,488 translation-augmented crops were used for training the model, and 403 lesion center crops were used for testing. To demonstrate the improvements in AK detection, AKU-Net was compared with plain U-Net and U-Net++ architectures. The experimental results highlighted the effectiveness of AKU-Net, improving upon both automation and precision over existing approaches, paving the way for more effective and reliable evaluation of actinic keratosis in clinical settings.
format Online
Article
Text
id pubmed-10571759
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-105717592023-10-14 The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild Derekas, Panagiotis Spyridonos, Panagiota Likas, Aristidis Zampeta, Athanasia Gaitanis, Georgios Bassukas, Ioannis Cancers (Basel) Article SIMPLE SUMMARY: Understanding the relationship between the skin cancerization field and actinic keratosis (AK) is crucial for identifying high-risk individuals, implementing early interventions, and preventing the progression to more aggressive forms of skin cancer. Currently, the clinical tools for grading field cancerization primarily involve assessing AK burden. In addition to their inherent subjectivity, these grading systems are limited by the high degree of AK lesions’ recurrence. The present study proposes a method based on deep learning and semantic segmentation to improve the monitoring of the AK burden in clinical settings with enhanced automation and precision. The experimental results highlight the effectiveness of the proposed method, paving the way for more effective and reliable evaluation, continuous monitoring of condition progression, and assessment of treatment responses. ABSTRACT: AK is a common precancerous skin condition that requires effective detection and treatment monitoring. To improve the monitoring of the AK burden in clinical settings with enhanced automation and precision, the present study evaluates the application of semantic segmentation based on the U-Net architecture (i.e., AKU-Net). AKU-Net employs transfer learning to compensate for the relatively small dataset of annotated images and integrates a recurrent process based on convLSTM to exploit contextual information and address the challenges related to the low contrast and ambiguous boundaries of AK-affected skin regions. We used an annotated dataset of 569 clinical photographs from 115 patients with actinic keratosis to train and evaluate the model. From each photograph, patches of 512 × 512 pixels were extracted using translation lesion boxes that encompassed lesions in different positions and captured different contexts of perilesional skin. In total, 16,488 translation-augmented crops were used for training the model, and 403 lesion center crops were used for testing. To demonstrate the improvements in AK detection, AKU-Net was compared with plain U-Net and U-Net++ architectures. The experimental results highlighted the effectiveness of AKU-Net, improving upon both automation and precision over existing approaches, paving the way for more effective and reliable evaluation of actinic keratosis in clinical settings. MDPI 2023-10-05 /pmc/articles/PMC10571759/ /pubmed/37835555 http://dx.doi.org/10.3390/cancers15194861 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Derekas, Panagiotis
Spyridonos, Panagiota
Likas, Aristidis
Zampeta, Athanasia
Gaitanis, Georgios
Bassukas, Ioannis
The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild
title The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild
title_full The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild
title_fullStr The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild
title_full_unstemmed The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild
title_short The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild
title_sort promise of semantic segmentation in detecting actinic keratosis using clinical photography in the wild
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10571759/
https://www.ncbi.nlm.nih.gov/pubmed/37835555
http://dx.doi.org/10.3390/cancers15194861
work_keys_str_mv AT derekaspanagiotis thepromiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild
AT spyridonospanagiota thepromiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild
AT likasaristidis thepromiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild
AT zampetaathanasia thepromiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild
AT gaitanisgeorgios thepromiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild
AT bassukasioannis thepromiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild
AT derekaspanagiotis promiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild
AT spyridonospanagiota promiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild
AT likasaristidis promiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild
AT zampetaathanasia promiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild
AT gaitanisgeorgios promiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild
AT bassukasioannis promiseofsemanticsegmentationindetectingactinickeratosisusingclinicalphotographyinthewild