Temporal integration of ResNet features with LSTM for enhanced skin lesion classification
The precise classification of skin lesions is essential for the early identification and efficient treatment of skin cancer. This research combines ResNet-50 for spatial feature extraction with Long Short-Term Memory (LSTM) networks for temporal analysis and introduces an innovative hybrid deep lear...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025002877 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540391106150400 |
|---|---|
| author | Sasmita Padhy Sachikanta Dash Naween Kumar Shailendra Pratap Singh Gyanendra Kumar Poonam Moral |
| author_facet | Sasmita Padhy Sachikanta Dash Naween Kumar Shailendra Pratap Singh Gyanendra Kumar Poonam Moral |
| author_sort | Sasmita Padhy |
| collection | DOAJ |
| description | The precise classification of skin lesions is essential for the early identification and efficient treatment of skin cancer. This research combines ResNet-50 for spatial feature extraction with Long Short-Term Memory (LSTM) networks for temporal analysis and introduces an innovative hybrid deep learning model, Residual network-Long Short-Term Memory (R-LSTM50). The approach tackles issues including class imbalance and the necessity for enhanced sensitivity in identifying malignant tumors. The ISIC2020 and HAM10000 benchmark datasets were employed for evaluation, utilizing sophisticated data augmentation methods and weighted loss functions to improve performance. Evaluation measures such as accuracy, sensitivity, specificity, and F1-score were employed to verify the model. Experimental findings indicate that R-LSTM50 attains state-of-the-art performance, achieving accuracies of 95.72% and 94.23%, F1-scores of 92.78% and 93.46%, sensitivities of 95.24% and 92.41%, and specificities of 92.08% and 90.33% on ISIC2020 and HAM10000, respectively. The results demonstrate the robustness and clinical significance of R-LSTM50, confirming its reliability as a tool for automated skin lesion classification. The hybrid design and sophisticated preprocessing techniques enhance the management of class imbalance and intricate feature interactions, establishing the proposed model as a notable improvement over current methodologies. |
| format | Article |
| id | doaj-art-5949682d65dc452d956429a9aec67330 |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-5949682d65dc452d956429a9aec673302025-02-05T04:32:36ZengElsevierResults in Engineering2590-12302025-03-0125104201Temporal integration of ResNet features with LSTM for enhanced skin lesion classificationSasmita Padhy0Sachikanta Dash1Naween Kumar2Shailendra Pratap Singh3Gyanendra Kumar4Poonam Moral5School of Computing Science and Engineering, VIT Bhopal University, Kothrikalan, Sehore, Madhya Pradesh 466114, IndiaComputer Science and Engineering, GIET University, Gunupur, Odisha, IndiaSCSET, Bennett University, Greater Noida, Uttar Pradesh, IndiaDepartment of Computer Science and Engineering, Madan Mohan Malaviya University of Technology, Gorakhpur, Uttar Pradesh, IndiaDepartment of IoT and Intelligent Systems, Manipal University Jaipur, Jaipur, India; Corresponding author.Department of Computer Science and Engineering, Birla Institute of Technology, Mesra, Ranchi 835215, IndiaThe precise classification of skin lesions is essential for the early identification and efficient treatment of skin cancer. This research combines ResNet-50 for spatial feature extraction with Long Short-Term Memory (LSTM) networks for temporal analysis and introduces an innovative hybrid deep learning model, Residual network-Long Short-Term Memory (R-LSTM50). The approach tackles issues including class imbalance and the necessity for enhanced sensitivity in identifying malignant tumors. The ISIC2020 and HAM10000 benchmark datasets were employed for evaluation, utilizing sophisticated data augmentation methods and weighted loss functions to improve performance. Evaluation measures such as accuracy, sensitivity, specificity, and F1-score were employed to verify the model. Experimental findings indicate that R-LSTM50 attains state-of-the-art performance, achieving accuracies of 95.72% and 94.23%, F1-scores of 92.78% and 93.46%, sensitivities of 95.24% and 92.41%, and specificities of 92.08% and 90.33% on ISIC2020 and HAM10000, respectively. The results demonstrate the robustness and clinical significance of R-LSTM50, confirming its reliability as a tool for automated skin lesion classification. The hybrid design and sophisticated preprocessing techniques enhance the management of class imbalance and intricate feature interactions, establishing the proposed model as a notable improvement over current methodologies.http://www.sciencedirect.com/science/article/pii/S2590123025002877Image classificationSkin lesionHAM10000Transfer learningISIC dataset |
| spellingShingle | Sasmita Padhy Sachikanta Dash Naween Kumar Shailendra Pratap Singh Gyanendra Kumar Poonam Moral Temporal integration of ResNet features with LSTM for enhanced skin lesion classification Results in Engineering Image classification Skin lesion HAM10000 Transfer learning ISIC dataset |
| title | Temporal integration of ResNet features with LSTM for enhanced skin lesion classification |
| title_full | Temporal integration of ResNet features with LSTM for enhanced skin lesion classification |
| title_fullStr | Temporal integration of ResNet features with LSTM for enhanced skin lesion classification |
| title_full_unstemmed | Temporal integration of ResNet features with LSTM for enhanced skin lesion classification |
| title_short | Temporal integration of ResNet features with LSTM for enhanced skin lesion classification |
| title_sort | temporal integration of resnet features with lstm for enhanced skin lesion classification |
| topic | Image classification Skin lesion HAM10000 Transfer learning ISIC dataset |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025002877 |
| work_keys_str_mv | AT sasmitapadhy temporalintegrationofresnetfeatureswithlstmforenhancedskinlesionclassification AT sachikantadash temporalintegrationofresnetfeatureswithlstmforenhancedskinlesionclassification AT naweenkumar temporalintegrationofresnetfeatureswithlstmforenhancedskinlesionclassification AT shailendrapratapsingh temporalintegrationofresnetfeatureswithlstmforenhancedskinlesionclassification AT gyanendrakumar temporalintegrationofresnetfeatureswithlstmforenhancedskinlesionclassification AT poonammoral temporalintegrationofresnetfeatureswithlstmforenhancedskinlesionclassification |