Hyperspectral Imaging for Enhanced Skin Cancer Classification Using Machine Learning

<b>Objective:</b> The classification of skin cancer is very helpful in its early diagnosis and treatment, considering the complexity involved in differentiating AK from BCC and SK. These conditions are generally not easily detectable due to their comparable clinical presentations. <b&...

Full description

Saved in:
Bibliographic Details
Main Authors: Teng-Li Lin, Arvind Mukundan, Riya Karmakar, Praveen Avala, Wen-Yen Chang, Hsiang-Chen Wang
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/12/7/755
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850078254300397568
author Teng-Li Lin
Arvind Mukundan
Riya Karmakar
Praveen Avala
Wen-Yen Chang
Hsiang-Chen Wang
author_facet Teng-Li Lin
Arvind Mukundan
Riya Karmakar
Praveen Avala
Wen-Yen Chang
Hsiang-Chen Wang
author_sort Teng-Li Lin
collection DOAJ
description <b>Objective:</b> The classification of skin cancer is very helpful in its early diagnosis and treatment, considering the complexity involved in differentiating AK from BCC and SK. These conditions are generally not easily detectable due to their comparable clinical presentations. <b>Method:</b> This paper presents a new approach to hyperspectral imaging for enhancing the visualization of skin lesions called the Spectrum-Aided Vision Enhancer (SAVE), which has the ability to convert any RGB image into a narrow-band image (NBI) by combining hyperspectral imaging (HSI) to increase the contrast of the area of the cancerous lesions when compared with the normal tissue, thereby increasing the accuracy of classification. The current study investigates the use of ten different machine learning algorithms for the purpose of classification of AK, BCC, and SK, including convolutional neural network (CNN), random forest (RF), you only look once (YOLO) version 8, support vector machine (SVM), ResNet50, MobileNetV2, Logistic Regression, SVM with stochastic gradient descent (SGD) Classifier, SVM with logarithmic (LOG) Classifier and SVM- Polynomial Classifier, in assessing the capability of the system to differentiate AK from BCC and SK with heightened accuracy. <b>Results:</b> The results demonstrated that SAVE enhanced classification performance and increased its accuracy, sensitivity, and specificity compared to a traditional RGB imaging approach. <b>Conclusions:</b> This advanced method offers dermatologists a tool for early and accurate diagnosis, reducing the likelihood of misclassification and improving patient outcomes.
format Article
id doaj-art-4056bfd743da4493a42aae6438527fd8
institution DOAJ
issn 2306-5354
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-4056bfd743da4493a42aae6438527fd82025-08-20T02:45:37ZengMDPI AGBioengineering2306-53542025-07-0112775510.3390/bioengineering12070755Hyperspectral Imaging for Enhanced Skin Cancer Classification Using Machine LearningTeng-Li Lin0Arvind Mukundan1Riya Karmakar2Praveen Avala3Wen-Yen Chang4Hsiang-Chen Wang5Department of Dermatology, Dalin Tzu Chi Hospital, No. 2, Min-Sheng Rd., Dalin Town, Chiayi 62247, TaiwanDepartment of Mechanical Engineering, National Chung Cheng University, 168, University Rd., Min Hsiung, Chiayi 62102, TaiwanDepartment of Mechanical Engineering, National Chung Cheng University, 168, University Rd., Min Hsiung, Chiayi 62102, TaiwanDepartment of Computer Science Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, No. 42, Avadi-Vel Tech Road Vel Nagar, Avadi, Chennai 600062, Tamil Nadu, IndiaDepartment of General Surgery, Kaohsiung Armed Forces General Hospital, 2, Zhongzheng 1st. Rd., Kaohsiung City 80284, TaiwanDepartment of Mechanical Engineering, National Chung Cheng University, 168, University Rd., Min Hsiung, Chiayi 62102, Taiwan<b>Objective:</b> The classification of skin cancer is very helpful in its early diagnosis and treatment, considering the complexity involved in differentiating AK from BCC and SK. These conditions are generally not easily detectable due to their comparable clinical presentations. <b>Method:</b> This paper presents a new approach to hyperspectral imaging for enhancing the visualization of skin lesions called the Spectrum-Aided Vision Enhancer (SAVE), which has the ability to convert any RGB image into a narrow-band image (NBI) by combining hyperspectral imaging (HSI) to increase the contrast of the area of the cancerous lesions when compared with the normal tissue, thereby increasing the accuracy of classification. The current study investigates the use of ten different machine learning algorithms for the purpose of classification of AK, BCC, and SK, including convolutional neural network (CNN), random forest (RF), you only look once (YOLO) version 8, support vector machine (SVM), ResNet50, MobileNetV2, Logistic Regression, SVM with stochastic gradient descent (SGD) Classifier, SVM with logarithmic (LOG) Classifier and SVM- Polynomial Classifier, in assessing the capability of the system to differentiate AK from BCC and SK with heightened accuracy. <b>Results:</b> The results demonstrated that SAVE enhanced classification performance and increased its accuracy, sensitivity, and specificity compared to a traditional RGB imaging approach. <b>Conclusions:</b> This advanced method offers dermatologists a tool for early and accurate diagnosis, reducing the likelihood of misclassification and improving patient outcomes.https://www.mdpi.com/2306-5354/12/7/755skin cancerhyperspectral imagingspectrum-aided vision enhancerconvolutional neural networkyolorandom forest
spellingShingle Teng-Li Lin
Arvind Mukundan
Riya Karmakar
Praveen Avala
Wen-Yen Chang
Hsiang-Chen Wang
Hyperspectral Imaging for Enhanced Skin Cancer Classification Using Machine Learning
Bioengineering
skin cancer
hyperspectral imaging
spectrum-aided vision enhancer
convolutional neural network
yolo
random forest
title Hyperspectral Imaging for Enhanced Skin Cancer Classification Using Machine Learning
title_full Hyperspectral Imaging for Enhanced Skin Cancer Classification Using Machine Learning
title_fullStr Hyperspectral Imaging for Enhanced Skin Cancer Classification Using Machine Learning
title_full_unstemmed Hyperspectral Imaging for Enhanced Skin Cancer Classification Using Machine Learning
title_short Hyperspectral Imaging for Enhanced Skin Cancer Classification Using Machine Learning
title_sort hyperspectral imaging for enhanced skin cancer classification using machine learning
topic skin cancer
hyperspectral imaging
spectrum-aided vision enhancer
convolutional neural network
yolo
random forest
url https://www.mdpi.com/2306-5354/12/7/755
work_keys_str_mv AT tenglilin hyperspectralimagingforenhancedskincancerclassificationusingmachinelearning
AT arvindmukundan hyperspectralimagingforenhancedskincancerclassificationusingmachinelearning
AT riyakarmakar hyperspectralimagingforenhancedskincancerclassificationusingmachinelearning
AT praveenavala hyperspectralimagingforenhancedskincancerclassificationusingmachinelearning
AT wenyenchang hyperspectralimagingforenhancedskincancerclassificationusingmachinelearning
AT hsiangchenwang hyperspectralimagingforenhancedskincancerclassificationusingmachinelearning