Fusion of Deep and Time–Frequency Local Features for Melanoma Skin Cancer Detection
Skin cancer spreads quickly as the skin is the most vulnerable organ, and melanoma (MEL) is a fatal type of skin cancer. Detecting MEL in the early stage can hugely increase the chance of a cure. There are several methods based on machine learning to detect MEL from dermoscopic images. However, incr...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Applied Computational Intelligence and Soft Computing |
| Online Access: | http://dx.doi.org/10.1155/acis/4767052 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849702284134449152 |
|---|---|
| author | Hamidreza Eghtesaddoust Morteza Valizadeh Mehdi Chehel Amirani |
| author_facet | Hamidreza Eghtesaddoust Morteza Valizadeh Mehdi Chehel Amirani |
| author_sort | Hamidreza Eghtesaddoust |
| collection | DOAJ |
| description | Skin cancer spreads quickly as the skin is the most vulnerable organ, and melanoma (MEL) is a fatal type of skin cancer. Detecting MEL in the early stage can hugely increase the chance of a cure. There are several methods based on machine learning to detect MEL from dermoscopic images. However, increasing the accuracy of detection is still challenging. This paper presents a new method for MEL detection that considers the combination of deep and handcrafted time–frequency local features. After short preprocessing, the convolutional neural networks (CNNs) extract the deep features. To this end, feature maps at the output of the flatten layer are considered as deep features. The scale-invariant feature transform (SIFT) descriptors are handcrafted local features computed from the four subbands of one-level two-dimensional discrete wavelet transform (2D DWT). After the fusion of the mentioned features, semisupervised discriminant analysis (SDA) reduces the highly correlated and redundant features. The Bayesian optimizer finds the optimum parameters of the SDA and Gaussian kernel of the support vector machine (SVM) classifier to maximize the classification accuracy. The HAM10000 dataset with data augmentation is considered to assess the performance of the proposed method. Simulation results show that the proposed method reaches the accuracy and sensitivity of 94.19% and 96.22%, respectively. The most challenging parts of the proposed method are extraction of deep features and tuning the parameters of SDA and Gaussian-SVM. |
| format | Article |
| id | doaj-art-0f4f22cc9f4c44ce8e0b153ce876ee00 |
| institution | DOAJ |
| issn | 1687-9732 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applied Computational Intelligence and Soft Computing |
| spelling | doaj-art-0f4f22cc9f4c44ce8e0b153ce876ee002025-08-20T03:17:43ZengWileyApplied Computational Intelligence and Soft Computing1687-97322025-01-01202510.1155/acis/4767052Fusion of Deep and Time–Frequency Local Features for Melanoma Skin Cancer DetectionHamidreza Eghtesaddoust0Morteza Valizadeh1Mehdi Chehel Amirani2Department of Electrical and Computer EngineeringDepartment of Electrical and Computer EngineeringDepartment of Electrical and Computer EngineeringSkin cancer spreads quickly as the skin is the most vulnerable organ, and melanoma (MEL) is a fatal type of skin cancer. Detecting MEL in the early stage can hugely increase the chance of a cure. There are several methods based on machine learning to detect MEL from dermoscopic images. However, increasing the accuracy of detection is still challenging. This paper presents a new method for MEL detection that considers the combination of deep and handcrafted time–frequency local features. After short preprocessing, the convolutional neural networks (CNNs) extract the deep features. To this end, feature maps at the output of the flatten layer are considered as deep features. The scale-invariant feature transform (SIFT) descriptors are handcrafted local features computed from the four subbands of one-level two-dimensional discrete wavelet transform (2D DWT). After the fusion of the mentioned features, semisupervised discriminant analysis (SDA) reduces the highly correlated and redundant features. The Bayesian optimizer finds the optimum parameters of the SDA and Gaussian kernel of the support vector machine (SVM) classifier to maximize the classification accuracy. The HAM10000 dataset with data augmentation is considered to assess the performance of the proposed method. Simulation results show that the proposed method reaches the accuracy and sensitivity of 94.19% and 96.22%, respectively. The most challenging parts of the proposed method are extraction of deep features and tuning the parameters of SDA and Gaussian-SVM.http://dx.doi.org/10.1155/acis/4767052 |
| spellingShingle | Hamidreza Eghtesaddoust Morteza Valizadeh Mehdi Chehel Amirani Fusion of Deep and Time–Frequency Local Features for Melanoma Skin Cancer Detection Applied Computational Intelligence and Soft Computing |
| title | Fusion of Deep and Time–Frequency Local Features for Melanoma Skin Cancer Detection |
| title_full | Fusion of Deep and Time–Frequency Local Features for Melanoma Skin Cancer Detection |
| title_fullStr | Fusion of Deep and Time–Frequency Local Features for Melanoma Skin Cancer Detection |
| title_full_unstemmed | Fusion of Deep and Time–Frequency Local Features for Melanoma Skin Cancer Detection |
| title_short | Fusion of Deep and Time–Frequency Local Features for Melanoma Skin Cancer Detection |
| title_sort | fusion of deep and time frequency local features for melanoma skin cancer detection |
| url | http://dx.doi.org/10.1155/acis/4767052 |
| work_keys_str_mv | AT hamidrezaeghtesaddoust fusionofdeepandtimefrequencylocalfeaturesformelanomaskincancerdetection AT mortezavalizadeh fusionofdeepandtimefrequencylocalfeaturesformelanomaskincancerdetection AT mehdichehelamirani fusionofdeepandtimefrequencylocalfeaturesformelanomaskincancerdetection |