CLASEG: advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learning

Abstract Oral cancer has a high mortality rate primarily due to delayed diagnoses, highlighting the need for early detection of oral lesions. This study presents a novel deep learning framework for multi-class classification-based segmentation, enabling accurate differential diagnosis of 14 common o...

Full description

Saved in:
Bibliographic Details
Main Authors: Afnan Al-Ali, Ali Hamdi, Mohamed Elshrif, Keivin Isufaj, Khaled Shaban, Peter Chauvin, Sreenath Madathil, Ammar Daer, Faleh Tamimi, Raidan Ba-Hattab
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-03268-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769151176900608
author Afnan Al-Ali
Ali Hamdi
Mohamed Elshrif
Keivin Isufaj
Khaled Shaban
Peter Chauvin
Sreenath Madathil
Ammar Daer
Faleh Tamimi
Raidan Ba-Hattab
author_facet Afnan Al-Ali
Ali Hamdi
Mohamed Elshrif
Keivin Isufaj
Khaled Shaban
Peter Chauvin
Sreenath Madathil
Ammar Daer
Faleh Tamimi
Raidan Ba-Hattab
author_sort Afnan Al-Ali
collection DOAJ
description Abstract Oral cancer has a high mortality rate primarily due to delayed diagnoses, highlighting the need for early detection of oral lesions. This study presents a novel deep learning framework for multi-class classification-based segmentation, enabling accurate differential diagnosis of 14 common oral lesions—benign, pre-malignant, and malignant—across various mouth locations using photographic images. A dataset of 2,072 clinical images was used to train and validate the model. The proposed framework integrates EfficientNet-B3 for classification and ResNet-101-based Mask R-CNN for segmentation, achieving a classification accuracy of 74.49% and segmentation performance with an average precision (AP50) of 72.18. The gradient-weighted class activation map technique was applied to the model outputs to enable visualization of the specific areas that were most influential for predictive decisions made by the model. This significantly improves upon the state-of-the-art, where previous models achieved lower segmentation accuracy (AP50 < 50%). The framework not only classifies the lesion type but also delineates the lesion boundaries with high precision, which is critical for early detection and differential diagnosis in clinical practice.
format Article
id doaj-art-60f61bc92e4e498b9a8a0eb0145cde0e
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-60f61bc92e4e498b9a8a0eb0145cde0e2025-08-20T03:03:33ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-03268-1CLASEG: advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learningAfnan Al-Ali0Ali Hamdi1Mohamed Elshrif2Keivin Isufaj3Khaled Shaban4Peter Chauvin5Sreenath Madathil6Ammar Daer7Faleh Tamimi8Raidan Ba-Hattab9Computer Science and Engineering Department, Qatar UniversityMSA UniversityQatar Computing Research Institute, HBKUQatar Computing Research Institute, HBKUComputer Science and Engineering Department, Qatar UniversityFaculty of Dental Medicine and Oral Health Sciences, McGill UniversityFaculty of Dental Medicine and Oral Health Sciences, McGill UniversityFaculty of Dental Medicine and Oral Health Sciences, McGill UniversityPre-Clinical Oral Health Sciences Department, College of Dental Medicine, QU Health, Qatar UniversityPre-Clinical Oral Health Sciences Department, College of Dental Medicine, QU Health, Qatar UniversityAbstract Oral cancer has a high mortality rate primarily due to delayed diagnoses, highlighting the need for early detection of oral lesions. This study presents a novel deep learning framework for multi-class classification-based segmentation, enabling accurate differential diagnosis of 14 common oral lesions—benign, pre-malignant, and malignant—across various mouth locations using photographic images. A dataset of 2,072 clinical images was used to train and validate the model. The proposed framework integrates EfficientNet-B3 for classification and ResNet-101-based Mask R-CNN for segmentation, achieving a classification accuracy of 74.49% and segmentation performance with an average precision (AP50) of 72.18. The gradient-weighted class activation map technique was applied to the model outputs to enable visualization of the specific areas that were most influential for predictive decisions made by the model. This significantly improves upon the state-of-the-art, where previous models achieved lower segmentation accuracy (AP50 < 50%). The framework not only classifies the lesion type but also delineates the lesion boundaries with high precision, which is critical for early detection and differential diagnosis in clinical practice.https://doi.org/10.1038/s41598-025-03268-1Oral lesionOral cancerClassificationSegmentationDeep learningEarly detection
spellingShingle Afnan Al-Ali
Ali Hamdi
Mohamed Elshrif
Keivin Isufaj
Khaled Shaban
Peter Chauvin
Sreenath Madathil
Ammar Daer
Faleh Tamimi
Raidan Ba-Hattab
CLASEG: advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learning
Scientific Reports
Oral lesion
Oral cancer
Classification
Segmentation
Deep learning
Early detection
title CLASEG: advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learning
title_full CLASEG: advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learning
title_fullStr CLASEG: advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learning
title_full_unstemmed CLASEG: advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learning
title_short CLASEG: advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learning
title_sort claseg advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learning
topic Oral lesion
Oral cancer
Classification
Segmentation
Deep learning
Early detection
url https://doi.org/10.1038/s41598-025-03268-1
work_keys_str_mv AT afnanalali clasegadvancedmulticlassificationandsegmentationfordifferentialdiagnosisoforallesionsusingdeeplearning
AT alihamdi clasegadvancedmulticlassificationandsegmentationfordifferentialdiagnosisoforallesionsusingdeeplearning
AT mohamedelshrif clasegadvancedmulticlassificationandsegmentationfordifferentialdiagnosisoforallesionsusingdeeplearning
AT keivinisufaj clasegadvancedmulticlassificationandsegmentationfordifferentialdiagnosisoforallesionsusingdeeplearning
AT khaledshaban clasegadvancedmulticlassificationandsegmentationfordifferentialdiagnosisoforallesionsusingdeeplearning
AT peterchauvin clasegadvancedmulticlassificationandsegmentationfordifferentialdiagnosisoforallesionsusingdeeplearning
AT sreenathmadathil clasegadvancedmulticlassificationandsegmentationfordifferentialdiagnosisoforallesionsusingdeeplearning
AT ammardaer clasegadvancedmulticlassificationandsegmentationfordifferentialdiagnosisoforallesionsusingdeeplearning
AT falehtamimi clasegadvancedmulticlassificationandsegmentationfordifferentialdiagnosisoforallesionsusingdeeplearning
AT raidanbahattab clasegadvancedmulticlassificationandsegmentationfordifferentialdiagnosisoforallesionsusingdeeplearning