Inverse Gini indexed averaging: A multi-leveled ensemble approach for skin lesion classification using attention-integrated customized ResNet variants
Objective To improve the accuracy and explainability of skin lesion detection and classification, particularly for several types of skin cancers, through a novel approach based on the convolutional neural networks with attention-integrated customized ResNet variants (CRVs) and an optimized ensemble...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2025-01-01
|
| Series: | Digital Health |
| Online Access: | https://doi.org/10.1177/20552076241312936 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841525297939218432 |
|---|---|
| author | Anwar Hossain Efat SM Mahedy Hasan Md Palash Uddin Faysal Hossain Emon |
| author_facet | Anwar Hossain Efat SM Mahedy Hasan Md Palash Uddin Faysal Hossain Emon |
| author_sort | Anwar Hossain Efat |
| collection | DOAJ |
| description | Objective To improve the accuracy and explainability of skin lesion detection and classification, particularly for several types of skin cancers, through a novel approach based on the convolutional neural networks with attention-integrated customized ResNet variants (CRVs) and an optimized ensemble learning (EL) strategy. Methods Our approach utilizes all ResNet variants combined with three attention mechanisms: channel attention, soft attention, and squeeze-excitation attention. These attention-integrated ResNet variants are aggregated through a unique multi-level EL strategy. We propose an innovative weight optimization method, inverse Gini indexed averaging (IGIA), which is further extended to multi-leveled IGIA (ML-IGIA) to determine the optimal weights for each model within multiple ensemble levels. For interpretability, we employ gradient class activation map to highlight the regions responsible for classification dominance, enhancing the model’s transparency. Results Our method was evaluated on the Human Against Machines 10000 dataset, achieving a superior accuracy of 94.52% with the ML-IGIA approach, outperforming existing methods. Conclusions The proposed CRV-based ensemble model with ML-IGIA demonstrates robust performance in skin lesion classification, offering both high accuracy and enhanced interpretability. This approach addresses the current research gap in effective weight optimization in EL and supports timely, automated skin disease detection. |
| format | Article |
| id | doaj-art-68d568921d3e443ebe62db3fa109344b |
| institution | Kabale University |
| issn | 2055-2076 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Digital Health |
| spelling | doaj-art-68d568921d3e443ebe62db3fa109344b2025-01-17T17:03:45ZengSAGE PublishingDigital Health2055-20762025-01-011110.1177/20552076241312936Inverse Gini indexed averaging: A multi-leveled ensemble approach for skin lesion classification using attention-integrated customized ResNet variantsAnwar Hossain Efat0SM Mahedy Hasan1Md Palash Uddin2Faysal Hossain Emon3 Computer Science and Engineering Department, , Dhaka, Bangladesh Computer Science and Engineering Department, , Kazla, Rajshahi, Bangladesh Computer Science and Engineering Department, , Dinajpur, Rangpur, Bangladesh , Dhaka, BangladeshObjective To improve the accuracy and explainability of skin lesion detection and classification, particularly for several types of skin cancers, through a novel approach based on the convolutional neural networks with attention-integrated customized ResNet variants (CRVs) and an optimized ensemble learning (EL) strategy. Methods Our approach utilizes all ResNet variants combined with three attention mechanisms: channel attention, soft attention, and squeeze-excitation attention. These attention-integrated ResNet variants are aggregated through a unique multi-level EL strategy. We propose an innovative weight optimization method, inverse Gini indexed averaging (IGIA), which is further extended to multi-leveled IGIA (ML-IGIA) to determine the optimal weights for each model within multiple ensemble levels. For interpretability, we employ gradient class activation map to highlight the regions responsible for classification dominance, enhancing the model’s transparency. Results Our method was evaluated on the Human Against Machines 10000 dataset, achieving a superior accuracy of 94.52% with the ML-IGIA approach, outperforming existing methods. Conclusions The proposed CRV-based ensemble model with ML-IGIA demonstrates robust performance in skin lesion classification, offering both high accuracy and enhanced interpretability. This approach addresses the current research gap in effective weight optimization in EL and supports timely, automated skin disease detection.https://doi.org/10.1177/20552076241312936 |
| spellingShingle | Anwar Hossain Efat SM Mahedy Hasan Md Palash Uddin Faysal Hossain Emon Inverse Gini indexed averaging: A multi-leveled ensemble approach for skin lesion classification using attention-integrated customized ResNet variants Digital Health |
| title | Inverse Gini indexed averaging: A multi-leveled ensemble approach for skin lesion classification using attention-integrated customized ResNet variants |
| title_full | Inverse Gini indexed averaging: A multi-leveled ensemble approach for skin lesion classification using attention-integrated customized ResNet variants |
| title_fullStr | Inverse Gini indexed averaging: A multi-leveled ensemble approach for skin lesion classification using attention-integrated customized ResNet variants |
| title_full_unstemmed | Inverse Gini indexed averaging: A multi-leveled ensemble approach for skin lesion classification using attention-integrated customized ResNet variants |
| title_short | Inverse Gini indexed averaging: A multi-leveled ensemble approach for skin lesion classification using attention-integrated customized ResNet variants |
| title_sort | inverse gini indexed averaging a multi leveled ensemble approach for skin lesion classification using attention integrated customized resnet variants |
| url | https://doi.org/10.1177/20552076241312936 |
| work_keys_str_mv | AT anwarhossainefat inverseginiindexedaveragingamultileveledensembleapproachforskinlesionclassificationusingattentionintegratedcustomizedresnetvariants AT smmahedyhasan inverseginiindexedaveragingamultileveledensembleapproachforskinlesionclassificationusingattentionintegratedcustomizedresnetvariants AT mdpalashuddin inverseginiindexedaveragingamultileveledensembleapproachforskinlesionclassificationusingattentionintegratedcustomizedresnetvariants AT faysalhossainemon inverseginiindexedaveragingamultileveledensembleapproachforskinlesionclassificationusingattentionintegratedcustomizedresnetvariants |