Modified LSTM based skin lesion segmentation and classification using optimization concept

Guardado en:
Detalles Bibliográficos
Publicado en:SN Applied Sciences vol. 7, no. 8 (Aug 2025), p. 880
Autor principal: Gomathi, S.
Otros Autores: Arunachalam, N.
Publicado:
Springer Nature B.V.
Materias:
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3236322436
003 UK-CbPIL
022 |a 2523-3963 
022 |a 2523-3971 
024 7 |a 10.1007/s42452-025-07511-2  |2 doi 
035 |a 3236322436 
045 2 |b d20250801  |b d20250831 
100 1 |a Gomathi, S.  |u SRM Institute of Science & Technology, Department of Computing Technologies, Kattankulathur, India (GRID:grid.412742.6) (ISNI:0000 0004 0635 5080) 
245 1 |a Modified LSTM based skin lesion segmentation and classification using optimization concept 
260 |b Springer Nature B.V.  |c Aug 2025 
513 |a Journal Article 
520 3 |a Skin cancer, one of the most serious types of cancer, affects a significant portion of the population. Image analysis has greatly enhanced automatic diagnostic accuracy compared to unaided visual assessment. Machine learning has emerged as a critical technique for automated skin lesion classification; however, its scalability is often constrained by the availability of high-quality annotated data for training. This research aims to perform segmentation and classification of skin lesions using novel deep learning techniques. Data samples were obtained from benchmark datasets, including HAM10000 and ISIC 2017, ensuring representativeness and diversity. Pre-processing involved hair removal followed by median filtering on the hair-removed images. Skin lesion segmentation was performed using the U-Net method, and features such as color, texture via GLCM, and RGB histogram features were extracted from the segmented images. The final classification phase utilized MLSTM with hidden neurons optimized using STBO, aiming to maximize accuracy and precision. The proposed model categorizes skin lesions as normal, benign, or malignant. The final classification phase utilized MLSTM with hidden neurons optimized using STBO, aiming to maximize accuracy and precision. The proposed model categorizes skin lesions as normal, benign, or malignant. Comparative analysis demonstrated that the MLSTM-STBO model achieves an accuracy of 97.20%, sensitivity of 97.14%, precision of 97.04%, specificity of 99.48%, F1-score of 97.08%, MCC of 98.12%, TPR of 96.17%, and FPR of 6.20%, outperforming traditional methods by margins up to 25.21%. 
653 |a Dermatology 
653 |a Neurons 
653 |a Tomography 
653 |a Accuracy 
653 |a Comparative analysis 
653 |a Datasets 
653 |a Deep learning 
653 |a Skin cancer 
653 |a Classification 
653 |a Visual discrimination learning 
653 |a Hair 
653 |a Optimization techniques 
653 |a Segmentation 
653 |a Medical imaging 
653 |a Lesions 
653 |a Image processing 
653 |a Skin diseases 
653 |a Registration 
653 |a Automation 
653 |a Machine learning 
653 |a Clinical outcomes 
653 |a Skin lesions 
653 |a Image analysis 
653 |a Image segmentation 
653 |a Cancer 
653 |a Decision making 
653 |a Microscopy 
653 |a Hair removal 
653 |a Digital photography 
653 |a Environmental 
700 1 |a Arunachalam, N.  |u SRM Institute of Science & Technology, Department of Computing Technologies, Kattankulathur, India (GRID:grid.412742.6) (ISNI:0000 0004 0635 5080) 
773 0 |t SN Applied Sciences  |g vol. 7, no. 8 (Aug 2025), p. 880 
786 0 |d ProQuest  |t Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3236322436/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3236322436/fulltext/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3236322436/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch