Classification of Skin Lesion Images Using Artificial Intelligence Methodologies through Radial Fourier–Mellin and Hilbert Transform Signatures
This manuscript proposes the possibility of concatenated signatures (instead of images) obtained from different integral transforms, such as Fourier, Mellin, and Hilbert, to classify skin lesions. Eight lesions were analyzed using some algorithms of artificial intelligence: basal cell carcinoma (BCC...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/20/11425 |
| _version_ | 1797574875666186240 |
|---|---|
| author | Esperanza Guerra-Rosas Luis Felipe López-Ávila Esbanyely Garza-Flores Claudia Andrea Vidales-Basurto Josué Álvarez-Borrego |
| author_facet | Esperanza Guerra-Rosas Luis Felipe López-Ávila Esbanyely Garza-Flores Claudia Andrea Vidales-Basurto Josué Álvarez-Borrego |
| author_sort | Esperanza Guerra-Rosas |
| collection | DOAJ |
| description | This manuscript proposes the possibility of concatenated signatures (instead of images) obtained from different integral transforms, such as Fourier, Mellin, and Hilbert, to classify skin lesions. Eight lesions were analyzed using some algorithms of artificial intelligence: basal cell carcinoma (BCC), squamous cell carcinoma (SCC), melanoma (MEL), actinic keratosis (AK), benign keratosis (BKL), dermatofibromas (DF), melanocytic nevi (NV), and vascular lesions (VASCs). Eleven artificial intelligence models were applied so that eight skin lesions could be classified by analyzing the signatures of each lesion. The database was randomly divided into 80% and 20% for the training and test dataset images, respectively. The metrics that are reported are accuracy, sensitivity, specificity, and precision. Each process was repeated 30 times to avoid bias, according to the central limit theorem in this work, and the averages and ± standard deviations were reported for each metric. Although all the results were very satisfactory, the highest average score for the eight lesions analyzed was obtained using the subspace k-NN model, where the test metrics were 99.98% accuracy, 99.96% sensitivity, 99.99% specificity, and 99.95% precision. |
| first_indexed | 2024-03-10T21:28:18Z |
| format | Article |
| id | doaj.art-50884f7836e14fe49046c504072ebb7e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T21:28:18Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-50884f7836e14fe49046c504072ebb7e2023-11-19T15:32:01ZengMDPI AGApplied Sciences2076-34172023-10-0113201142510.3390/app132011425Classification of Skin Lesion Images Using Artificial Intelligence Methodologies through Radial Fourier–Mellin and Hilbert Transform SignaturesEsperanza Guerra-Rosas0Luis Felipe López-Ávila1Esbanyely Garza-Flores2Claudia Andrea Vidales-Basurto3Josué Álvarez-Borrego4Facultad de Ingeniería, Arquitectura y Diseño, Universidad Autónoma de Baja California, Km. 103 Carretera Tijuana-Ensenada, Ensenada 22860, Baja California, MexicoCentro de Investigación Científica y de Educación Superior de Ensenada (CICESE), Baja California, Carretera Ensenada-Tijuana No. 3918, Zona Playitas, Ensenada 22860, Baja California, MexicoSolexVintel, Santa Margarita 117, Colonia Insurgentes San Borja, Alcaldía Benito Juárez, Cd. De Mexico C. P. 03100, MexicoCentro de Investigación Científica y de Educación Superior de Ensenada (CICESE), Baja California, Carretera Ensenada-Tijuana No. 3918, Zona Playitas, Ensenada 22860, Baja California, MexicoCentro de Investigación Científica y de Educación Superior de Ensenada (CICESE), Baja California, Carretera Ensenada-Tijuana No. 3918, Zona Playitas, Ensenada 22860, Baja California, MexicoThis manuscript proposes the possibility of concatenated signatures (instead of images) obtained from different integral transforms, such as Fourier, Mellin, and Hilbert, to classify skin lesions. Eight lesions were analyzed using some algorithms of artificial intelligence: basal cell carcinoma (BCC), squamous cell carcinoma (SCC), melanoma (MEL), actinic keratosis (AK), benign keratosis (BKL), dermatofibromas (DF), melanocytic nevi (NV), and vascular lesions (VASCs). Eleven artificial intelligence models were applied so that eight skin lesions could be classified by analyzing the signatures of each lesion. The database was randomly divided into 80% and 20% for the training and test dataset images, respectively. The metrics that are reported are accuracy, sensitivity, specificity, and precision. Each process was repeated 30 times to avoid bias, according to the central limit theorem in this work, and the averages and ± standard deviations were reported for each metric. Although all the results were very satisfactory, the highest average score for the eight lesions analyzed was obtained using the subspace k-NN model, where the test metrics were 99.98% accuracy, 99.96% sensitivity, 99.99% specificity, and 99.95% precision.https://www.mdpi.com/2076-3417/13/20/11425radial Fourier signaturesSVMmachine learningskin lesionstexture descriptorsimage processing |
| spellingShingle | Esperanza Guerra-Rosas Luis Felipe López-Ávila Esbanyely Garza-Flores Claudia Andrea Vidales-Basurto Josué Álvarez-Borrego Classification of Skin Lesion Images Using Artificial Intelligence Methodologies through Radial Fourier–Mellin and Hilbert Transform Signatures Applied Sciences radial Fourier signatures SVM machine learning skin lesions texture descriptors image processing |
| title | Classification of Skin Lesion Images Using Artificial Intelligence Methodologies through Radial Fourier–Mellin and Hilbert Transform Signatures |
| title_full | Classification of Skin Lesion Images Using Artificial Intelligence Methodologies through Radial Fourier–Mellin and Hilbert Transform Signatures |
| title_fullStr | Classification of Skin Lesion Images Using Artificial Intelligence Methodologies through Radial Fourier–Mellin and Hilbert Transform Signatures |
| title_full_unstemmed | Classification of Skin Lesion Images Using Artificial Intelligence Methodologies through Radial Fourier–Mellin and Hilbert Transform Signatures |
| title_short | Classification of Skin Lesion Images Using Artificial Intelligence Methodologies through Radial Fourier–Mellin and Hilbert Transform Signatures |
| title_sort | classification of skin lesion images using artificial intelligence methodologies through radial fourier mellin and hilbert transform signatures |
| topic | radial Fourier signatures SVM machine learning skin lesions texture descriptors image processing |
| url | https://www.mdpi.com/2076-3417/13/20/11425 |
| work_keys_str_mv | AT esperanzaguerrarosas classificationofskinlesionimagesusingartificialintelligencemethodologiesthroughradialfouriermellinandhilberttransformsignatures AT luisfelipelopezavila classificationofskinlesionimagesusingartificialintelligencemethodologiesthroughradialfouriermellinandhilberttransformsignatures AT esbanyelygarzaflores classificationofskinlesionimagesusingartificialintelligencemethodologiesthroughradialfouriermellinandhilberttransformsignatures AT claudiaandreavidalesbasurto classificationofskinlesionimagesusingartificialintelligencemethodologiesthroughradialfouriermellinandhilberttransformsignatures AT josuealvarezborrego classificationofskinlesionimagesusingartificialintelligencemethodologiesthroughradialfouriermellinandhilberttransformsignatures |