A Deep Learning Framework with an Intermediate Layer Using the Swarm Intelligence Optimizer for Diagnosing Oral Squamous Cell Carcinoma
One of the most prevalent cancers is oral squamous cell carcinoma, and preventing mortality from this disease primarily depends on early detection. Clinicians will greatly benefit from automated diagnostic techniques that analyze a patient’s histopathology images to identify abnormal oral lesions. A...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/22/3461 |
| _version_ | 1797459599350038528 |
|---|---|
| author | Bharanidharan Nagarajan Sannasi Chakravarthy Vinoth Kumar Venkatesan Mahesh Thyluru Ramakrishna Surbhi Bhatia Khan Shakila Basheer Eid Albalawi |
| author_facet | Bharanidharan Nagarajan Sannasi Chakravarthy Vinoth Kumar Venkatesan Mahesh Thyluru Ramakrishna Surbhi Bhatia Khan Shakila Basheer Eid Albalawi |
| author_sort | Bharanidharan Nagarajan |
| collection | DOAJ |
| description | One of the most prevalent cancers is oral squamous cell carcinoma, and preventing mortality from this disease primarily depends on early detection. Clinicians will greatly benefit from automated diagnostic techniques that analyze a patient’s histopathology images to identify abnormal oral lesions. A deep learning framework was designed with an intermediate layer between feature extraction layers and classification layers for classifying the histopathological images into two categories, namely, normal and oral squamous cell carcinoma. The intermediate layer is constructed using the proposed swarm intelligence technique called the Modified Gorilla Troops Optimizer. While there are many optimization algorithms used in the literature for feature selection, weight updating, and optimal parameter identification in deep learning models, this work focuses on using optimization algorithms as an intermediate layer to convert extracted features into features that are better suited for classification. Three datasets comprising 2784 normal and 3632 oral squamous cell carcinoma subjects are considered in this work. Three popular CNN architectures, namely, InceptionV2, MobileNetV3, and EfficientNetB3, are investigated as feature extraction layers. Two fully connected Neural Network layers, batch normalization, and dropout are used as classification layers. With the best accuracy of 0.89 among the examined feature extraction models, MobileNetV3 exhibits good performance. This accuracy is increased to 0.95 when the suggested Modified Gorilla Troops Optimizer is used as an intermediary layer. |
| first_indexed | 2024-03-09T16:53:41Z |
| format | Article |
| id | doaj.art-53c716c55d594a3ea520916e92aaaf46 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T16:53:41Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-53c716c55d594a3ea520916e92aaaf462023-11-24T14:37:42ZengMDPI AGDiagnostics2075-44182023-11-011322346110.3390/diagnostics13223461A Deep Learning Framework with an Intermediate Layer Using the Swarm Intelligence Optimizer for Diagnosing Oral Squamous Cell CarcinomaBharanidharan Nagarajan0Sannasi Chakravarthy1Vinoth Kumar Venkatesan2Mahesh Thyluru Ramakrishna3Surbhi Bhatia Khan4Shakila Basheer5Eid Albalawi6School of Computer Science Engineering and Information Systems (SCORE), Vellore Institute of Technology, Vellore 632014, IndiaDepartment of ECE, Bannari Amman Institute of Technology, Sathyamangalam 638401, IndiaSchool of Computer Science Engineering and Information Systems (SCORE), Vellore Institute of Technology, Vellore 632014, IndiaDepartment of Computer Science and Engineering, Faculty of Engineering and Technology, JAIN (Deemed-to-Be University), Bangalore 562112, IndiaDepartment of Data Science, School of Science Engineering and Environment, University of Salford, Manchester M5 4WT, UKDepartment of Information Systems, College of Computer and Information Science, Princess Nourah bint Abdulrahman University, Riyadh 11671, Saudi ArabiaDepartment of Computer Science, School of Computer Science and Information Technology, King Faisal University, Al-Ahsa 31982, Saudi ArabiaOne of the most prevalent cancers is oral squamous cell carcinoma, and preventing mortality from this disease primarily depends on early detection. Clinicians will greatly benefit from automated diagnostic techniques that analyze a patient’s histopathology images to identify abnormal oral lesions. A deep learning framework was designed with an intermediate layer between feature extraction layers and classification layers for classifying the histopathological images into two categories, namely, normal and oral squamous cell carcinoma. The intermediate layer is constructed using the proposed swarm intelligence technique called the Modified Gorilla Troops Optimizer. While there are many optimization algorithms used in the literature for feature selection, weight updating, and optimal parameter identification in deep learning models, this work focuses on using optimization algorithms as an intermediate layer to convert extracted features into features that are better suited for classification. Three datasets comprising 2784 normal and 3632 oral squamous cell carcinoma subjects are considered in this work. Three popular CNN architectures, namely, InceptionV2, MobileNetV3, and EfficientNetB3, are investigated as feature extraction layers. Two fully connected Neural Network layers, batch normalization, and dropout are used as classification layers. With the best accuracy of 0.89 among the examined feature extraction models, MobileNetV3 exhibits good performance. This accuracy is increased to 0.95 when the suggested Modified Gorilla Troops Optimizer is used as an intermediary layer.https://www.mdpi.com/2075-4418/13/22/3461oral cancerhistopathologic imagesCNNdeep learning frameworkswarm intelligenceGorilla Troops Optimizer |
| spellingShingle | Bharanidharan Nagarajan Sannasi Chakravarthy Vinoth Kumar Venkatesan Mahesh Thyluru Ramakrishna Surbhi Bhatia Khan Shakila Basheer Eid Albalawi A Deep Learning Framework with an Intermediate Layer Using the Swarm Intelligence Optimizer for Diagnosing Oral Squamous Cell Carcinoma Diagnostics oral cancer histopathologic images CNN deep learning framework swarm intelligence Gorilla Troops Optimizer |
| title | A Deep Learning Framework with an Intermediate Layer Using the Swarm Intelligence Optimizer for Diagnosing Oral Squamous Cell Carcinoma |
| title_full | A Deep Learning Framework with an Intermediate Layer Using the Swarm Intelligence Optimizer for Diagnosing Oral Squamous Cell Carcinoma |
| title_fullStr | A Deep Learning Framework with an Intermediate Layer Using the Swarm Intelligence Optimizer for Diagnosing Oral Squamous Cell Carcinoma |
| title_full_unstemmed | A Deep Learning Framework with an Intermediate Layer Using the Swarm Intelligence Optimizer for Diagnosing Oral Squamous Cell Carcinoma |
| title_short | A Deep Learning Framework with an Intermediate Layer Using the Swarm Intelligence Optimizer for Diagnosing Oral Squamous Cell Carcinoma |
| title_sort | deep learning framework with an intermediate layer using the swarm intelligence optimizer for diagnosing oral squamous cell carcinoma |
| topic | oral cancer histopathologic images CNN deep learning framework swarm intelligence Gorilla Troops Optimizer |
| url | https://www.mdpi.com/2075-4418/13/22/3461 |
| work_keys_str_mv | AT bharanidharannagarajan adeeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT sannasichakravarthy adeeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT vinothkumarvenkatesan adeeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT maheshthylururamakrishna adeeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT surbhibhatiakhan adeeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT shakilabasheer adeeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT eidalbalawi adeeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT bharanidharannagarajan deeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT sannasichakravarthy deeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT vinothkumarvenkatesan deeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT maheshthylururamakrishna deeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT surbhibhatiakhan deeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT shakilabasheer deeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma AT eidalbalawi deeplearningframeworkwithanintermediatelayerusingtheswarmintelligenceoptimizerfordiagnosingoralsquamouscellcarcinoma |