Deep Learning Model for Automated Cutaneous Squamous Cell Carcinoma Grading

Accurate and efficient grading of cutaneous squamous cell carcinoma (cSCC) is critical for effective treatment and prognosis, but traditional manual grading methods are subjective and time-consuming. This study aimed to develop and validate a deep learning (DL) model for automated cSCC grading, pot...

Full description

Saved in:
Bibliographic Details
Main Authors: Alexandra BURUIANĂ, Mircea-Sebastian ŞERBĂNESCU, Bogdan-Alexandru GHEBAN
Format: Article
Language:English
Published: Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca 2025-05-01
Series:Applied Medical Informatics
Subjects:
Online Access:https://ami.info.umfcluj.ro/index.php/AMI/article/view/1180
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850101881139888128
author Alexandra BURUIANĂ
Mircea-Sebastian ŞERBĂNESCU
Bogdan-Alexandru GHEBAN
author_facet Alexandra BURUIANĂ
Mircea-Sebastian ŞERBĂNESCU
Bogdan-Alexandru GHEBAN
author_sort Alexandra BURUIANĂ
collection DOAJ
description Accurate and efficient grading of cutaneous squamous cell carcinoma (cSCC) is critical for effective treatment and prognosis, but traditional manual grading methods are subjective and time-consuming. This study aimed to develop and validate a deep learning (DL) model for automated cSCC grading, potentially improving diagnostic accuracy and efficiency. Three different deep neural network (DNN) architectures (AlexNet, GoogLeNet, and ResNet-18) were trained using transfer learning on a dataset of 300 histopathological images of cSCC. The performance of the models was evaluated based on accuracy, sensitivity, specificity, and area under the curve (AUC). A clinical validation was conducted on 60 images, comparing the DNNs' predictions with those made by a panel of pathologists. The DL models achieved high performance metrics (accuracy >85%, sensitivity >85%, specificity >92%, AUC >97%), demonstrating their potential for objective and efficient cSCC grading. The strong agreement observed between the DNNs and the panel of pathologists, as well as the consistency across different network architectures, further supports the reliability and accuracy of the DL models. The top-performing models have been made publicly available to facilitate further research and potential clinical implementation. This study highlights the promising role of DL in enhancing cSCC diagnosis and, ultimately, improving patient care.
format Article
id doaj-art-a9b1fec44c174a429f9d2f0cf82f0bbe
institution DOAJ
issn 2067-7855
language English
publishDate 2025-05-01
publisher Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca
record_format Article
series Applied Medical Informatics
spelling doaj-art-a9b1fec44c174a429f9d2f0cf82f0bbe2025-08-20T02:39:54ZengIuliu Hatieganu University of Medicine and Pharmacy, Cluj-NapocaApplied Medical Informatics2067-78552025-05-0147Suppl. 1Deep Learning Model for Automated Cutaneous Squamous Cell Carcinoma GradingAlexandra BURUIANĂ0Mircea-Sebastian ŞERBĂNESCU1Bogdan-Alexandru GHEBAN2Department of Pathology, Faculty of Medicine, “Iuliu Hatieganu” University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania.Department of Medical Informatics and Biostatistics, University of Medicine and Pharmacy of Craiova, Petru Rareş Str., no. 2, 200349 Craiova, RomaniaDepartment 1, Faculty of Medical Assistance and Health Sciences, “Iuliu Haţieganu” University of Medicine and Pharmacy, Victor Babeş Str., no. 8, 400012 Cluj-Napoca, Romania Accurate and efficient grading of cutaneous squamous cell carcinoma (cSCC) is critical for effective treatment and prognosis, but traditional manual grading methods are subjective and time-consuming. This study aimed to develop and validate a deep learning (DL) model for automated cSCC grading, potentially improving diagnostic accuracy and efficiency. Three different deep neural network (DNN) architectures (AlexNet, GoogLeNet, and ResNet-18) were trained using transfer learning on a dataset of 300 histopathological images of cSCC. The performance of the models was evaluated based on accuracy, sensitivity, specificity, and area under the curve (AUC). A clinical validation was conducted on 60 images, comparing the DNNs' predictions with those made by a panel of pathologists. The DL models achieved high performance metrics (accuracy >85%, sensitivity >85%, specificity >92%, AUC >97%), demonstrating their potential for objective and efficient cSCC grading. The strong agreement observed between the DNNs and the panel of pathologists, as well as the consistency across different network architectures, further supports the reliability and accuracy of the DL models. The top-performing models have been made publicly available to facilitate further research and potential clinical implementation. This study highlights the promising role of DL in enhancing cSCC diagnosis and, ultimately, improving patient care. https://ami.info.umfcluj.ro/index.php/AMI/article/view/1180Cutaneous Squamous Cell CarcinomaDeep LearningHistological GradingTransfer Learning; Artificial Intelligence
spellingShingle Alexandra BURUIANĂ
Mircea-Sebastian ŞERBĂNESCU
Bogdan-Alexandru GHEBAN
Deep Learning Model for Automated Cutaneous Squamous Cell Carcinoma Grading
Applied Medical Informatics
Cutaneous Squamous Cell Carcinoma
Deep Learning
Histological Grading
Transfer Learning; Artificial Intelligence
title Deep Learning Model for Automated Cutaneous Squamous Cell Carcinoma Grading
title_full Deep Learning Model for Automated Cutaneous Squamous Cell Carcinoma Grading
title_fullStr Deep Learning Model for Automated Cutaneous Squamous Cell Carcinoma Grading
title_full_unstemmed Deep Learning Model for Automated Cutaneous Squamous Cell Carcinoma Grading
title_short Deep Learning Model for Automated Cutaneous Squamous Cell Carcinoma Grading
title_sort deep learning model for automated cutaneous squamous cell carcinoma grading
topic Cutaneous Squamous Cell Carcinoma
Deep Learning
Histological Grading
Transfer Learning; Artificial Intelligence
url https://ami.info.umfcluj.ro/index.php/AMI/article/view/1180
work_keys_str_mv AT alexandraburuiana deeplearningmodelforautomatedcutaneoussquamouscellcarcinomagrading
AT mirceasebastianserbanescu deeplearningmodelforautomatedcutaneoussquamouscellcarcinomagrading
AT bogdanalexandrugheban deeplearningmodelforautomatedcutaneoussquamouscellcarcinomagrading