Exploring the efficacy of various CNN architectures in diagnosing oral cancer from squamous cell carcinoma

Oral cancer can result from mutations in cells located in the lips or mouth. Diagnosing oral cavity squamous cell carcinoma (OCSCC) is particularly challenging, often occurring at advanced stages. To address this, computer-aided diagnosis methods are increasingly being used. In this work, a deep lea...

Full description

Saved in:
Bibliographic Details
Main Authors: Prerna Kulkarni, Nidhi Sarwe, Abhishek Pingale, Yash Sarolkar, Rutuja Rajendra Patil, Gitanjali Shinde, Gagandeep Kaur
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:MethodsX
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2215016124004850
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846169447976402944
author Prerna Kulkarni
Nidhi Sarwe
Abhishek Pingale
Yash Sarolkar
Rutuja Rajendra Patil
Gitanjali Shinde
Gagandeep Kaur
author_facet Prerna Kulkarni
Nidhi Sarwe
Abhishek Pingale
Yash Sarolkar
Rutuja Rajendra Patil
Gitanjali Shinde
Gagandeep Kaur
author_sort Prerna Kulkarni
collection DOAJ
description Oral cancer can result from mutations in cells located in the lips or mouth. Diagnosing oral cavity squamous cell carcinoma (OCSCC) is particularly challenging, often occurring at advanced stages. To address this, computer-aided diagnosis methods are increasingly being used. In this work, a deep learning-based approach utilizing models such as VGG16, ResNet50, LeNet-5, MobileNetV2, and Inception V3 is presented. NEOR and OCSCC datasets were used for feature extraction, with virtual slide images divided into tiles and classified as normal or squamous cell cancer. Performance metrics like accuracy, F1-score, AUC, precision, and recall were analyzed to determine the prerequisites for optimal CNN performance. The proposed CNN approaches were effective for classifying OCSCC and oral dysplasia, with the highest accuracy of 95.41 % achieved using MobileNetV2. Key findings: Deep learning models, particularly MobileNetV2, achieved high classification accuracy (95.41 %) for OCSCC.CNN-based methods show promise for early-stage OCSCC and oral dysplasia diagnosis. Performance parameters like precision, recall, and F1-score help optimize CNN model selection for this task.
format Article
id doaj-art-e1820ece0e1f484ebcd41bd426fbcc4f
institution Kabale University
issn 2215-0161
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series MethodsX
spelling doaj-art-e1820ece0e1f484ebcd41bd426fbcc4f2024-11-13T04:29:47ZengElsevierMethodsX2215-01612024-12-0113103034Exploring the efficacy of various CNN architectures in diagnosing oral cancer from squamous cell carcinomaPrerna Kulkarni0Nidhi Sarwe1Abhishek Pingale2Yash Sarolkar3Rutuja Rajendra Patil4Gitanjali Shinde5Gagandeep Kaur6Department of CSE (AIML), Vishwakarma Institute of Information Technology, Kondhwa (Budruk) Pune, Maharashtra 411048, IndiaDepartment of CSE (AIML), Vishwakarma Institute of Information Technology, Kondhwa (Budruk) Pune, Maharashtra 411048, IndiaDepartment of CSE (AIML), Vishwakarma Institute of Information Technology, Kondhwa (Budruk) Pune, Maharashtra 411048, IndiaDepartment of CSE (AIML), Vishwakarma Institute of Information Technology, Kondhwa (Budruk) Pune, Maharashtra 411048, IndiaDepartment of CSE (AIML), Vishwakarma Institute of Information Technology, Kondhwa (Budruk) Pune, Maharashtra 411048, IndiaDepartment of CSE (AIML), Vishwakarma Institute of Information Technology, Kondhwa (Budruk) Pune, Maharashtra 411048, IndiaCSE Department, Symbiosis Institute of Technology, Nagpur Campus, Symbiosis International (Deemed University), Pune, India; Corresponding author.Oral cancer can result from mutations in cells located in the lips or mouth. Diagnosing oral cavity squamous cell carcinoma (OCSCC) is particularly challenging, often occurring at advanced stages. To address this, computer-aided diagnosis methods are increasingly being used. In this work, a deep learning-based approach utilizing models such as VGG16, ResNet50, LeNet-5, MobileNetV2, and Inception V3 is presented. NEOR and OCSCC datasets were used for feature extraction, with virtual slide images divided into tiles and classified as normal or squamous cell cancer. Performance metrics like accuracy, F1-score, AUC, precision, and recall were analyzed to determine the prerequisites for optimal CNN performance. The proposed CNN approaches were effective for classifying OCSCC and oral dysplasia, with the highest accuracy of 95.41 % achieved using MobileNetV2. Key findings: Deep learning models, particularly MobileNetV2, achieved high classification accuracy (95.41 %) for OCSCC.CNN-based methods show promise for early-stage OCSCC and oral dysplasia diagnosis. Performance parameters like precision, recall, and F1-score help optimize CNN model selection for this task.http://www.sciencedirect.com/science/article/pii/S2215016124004850Convolutional Neural Networks
spellingShingle Prerna Kulkarni
Nidhi Sarwe
Abhishek Pingale
Yash Sarolkar
Rutuja Rajendra Patil
Gitanjali Shinde
Gagandeep Kaur
Exploring the efficacy of various CNN architectures in diagnosing oral cancer from squamous cell carcinoma
MethodsX
Convolutional Neural Networks
title Exploring the efficacy of various CNN architectures in diagnosing oral cancer from squamous cell carcinoma
title_full Exploring the efficacy of various CNN architectures in diagnosing oral cancer from squamous cell carcinoma
title_fullStr Exploring the efficacy of various CNN architectures in diagnosing oral cancer from squamous cell carcinoma
title_full_unstemmed Exploring the efficacy of various CNN architectures in diagnosing oral cancer from squamous cell carcinoma
title_short Exploring the efficacy of various CNN architectures in diagnosing oral cancer from squamous cell carcinoma
title_sort exploring the efficacy of various cnn architectures in diagnosing oral cancer from squamous cell carcinoma
topic Convolutional Neural Networks
url http://www.sciencedirect.com/science/article/pii/S2215016124004850
work_keys_str_mv AT prernakulkarni exploringtheefficacyofvariouscnnarchitecturesindiagnosingoralcancerfromsquamouscellcarcinoma
AT nidhisarwe exploringtheefficacyofvariouscnnarchitecturesindiagnosingoralcancerfromsquamouscellcarcinoma
AT abhishekpingale exploringtheefficacyofvariouscnnarchitecturesindiagnosingoralcancerfromsquamouscellcarcinoma
AT yashsarolkar exploringtheefficacyofvariouscnnarchitecturesindiagnosingoralcancerfromsquamouscellcarcinoma
AT rutujarajendrapatil exploringtheefficacyofvariouscnnarchitecturesindiagnosingoralcancerfromsquamouscellcarcinoma
AT gitanjalishinde exploringtheefficacyofvariouscnnarchitecturesindiagnosingoralcancerfromsquamouscellcarcinoma
AT gagandeepkaur exploringtheefficacyofvariouscnnarchitecturesindiagnosingoralcancerfromsquamouscellcarcinoma