FFTL-Net: a network for the classification of skin diseases based on feature fusion and transfer learning
The objective is to address the issues of data imbalance, overfitting, and inadequate generalization ability in skin disease datasets and recognition models. The proposed model for the classification of skin diseases is based on the fusion of features and the utilization of transfer learning. The mo...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ade4f0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839650898191581184 |
|---|---|
| author | Xiaowei Song Yurong Mei Zhilei Zhao Hao Chang Lina Han Hui Wang Xinyi Zhang Guoqiang Wang |
| author_facet | Xiaowei Song Yurong Mei Zhilei Zhao Hao Chang Lina Han Hui Wang Xinyi Zhang Guoqiang Wang |
| author_sort | Xiaowei Song |
| collection | DOAJ |
| description | The objective is to address the issues of data imbalance, overfitting, and inadequate generalization ability in skin disease datasets and recognition models. The proposed model for the classification of skin diseases is based on the fusion of features and the utilization of transfer learning. The model’s architecture is predicated on a dense connection network that serves as its fundamental framework, with LBP and HOG features incorporated as supplementary inputs. Subsequently, a feature fusion module integrated with an attention mechanism is employed to extract and combine features. Finally, the Softmax-loss function of category equilibrium and the domain adaptive strategy based on the maximum mean difference are established. The integration of prior knowledge into the deep network is a critical step in addressing the challenges of overfitting and data imbalance in skin disease classification. The FFTL-Net achieved AUC value of 98.16% on the International skin imaging collaboration (ISIC) 2018 dataset and 98.31% on the ISIC 2019 dataset. This represents an improvement of 1.25% and 0.33% compared to the second-ranked algorithm, respectively. The experimental results demonstrate the efficacy of the model in addressing the data imbalance issue in skin disease datasets, with prediction accuracies of at least 93% being achieved for BCC and other rare samples. The model demonstrates superior recognition accuracy, augmented generalization capability, and an absence of indications of overfitting. |
| format | Article |
| id | doaj-art-b58e3fa0597447ce8fbb0e1ce58c2ccd |
| institution | Matheson Library |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-b58e3fa0597447ce8fbb0e1ce58c2ccd2025-06-26T15:08:40ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016202507210.1088/2632-2153/ade4f0FFTL-Net: a network for the classification of skin diseases based on feature fusion and transfer learningXiaowei Song0https://orcid.org/0000-0001-8247-5859Yurong Mei1Zhilei Zhao2https://orcid.org/0009-0000-8767-1787Hao Chang3Lina Han4Hui Wang5https://orcid.org/0000-0002-8051-3695Xinyi Zhang6Guoqiang Wang7College of Mechatronic Engineering, North University of China , Taiyuan 030000, People’s Republic of ChinaThe Eighth Medical Center, Chinese PLA General Hospital , Beijing 100000, People’s Republic of ChinaSchool of Automation, Beijing Institute of Technology University , Beijing 100081, People’s Republic of ChinaCollege of Mechatronic Engineering, North University of China , Taiyuan 030000, People’s Republic of ChinaDepartment of Cardiology, The Second Medical Center, National Clinical Research Center for Geriatric Diseases, Chinese PLA General Hospital , Beijing 100000, People’s Republic of ChinaSchool of Automation, Beijing Institute of Technology University , Beijing 100081, People’s Republic of ChinaCollege of Mechatronic Engineering, North University of China , Taiyuan 030000, People’s Republic of ChinaCollege of Mechatronic Engineering, North University of China , Taiyuan 030000, People’s Republic of ChinaThe objective is to address the issues of data imbalance, overfitting, and inadequate generalization ability in skin disease datasets and recognition models. The proposed model for the classification of skin diseases is based on the fusion of features and the utilization of transfer learning. The model’s architecture is predicated on a dense connection network that serves as its fundamental framework, with LBP and HOG features incorporated as supplementary inputs. Subsequently, a feature fusion module integrated with an attention mechanism is employed to extract and combine features. Finally, the Softmax-loss function of category equilibrium and the domain adaptive strategy based on the maximum mean difference are established. The integration of prior knowledge into the deep network is a critical step in addressing the challenges of overfitting and data imbalance in skin disease classification. The FFTL-Net achieved AUC value of 98.16% on the International skin imaging collaboration (ISIC) 2018 dataset and 98.31% on the ISIC 2019 dataset. This represents an improvement of 1.25% and 0.33% compared to the second-ranked algorithm, respectively. The experimental results demonstrate the efficacy of the model in addressing the data imbalance issue in skin disease datasets, with prediction accuracies of at least 93% being achieved for BCC and other rare samples. The model demonstrates superior recognition accuracy, augmented generalization capability, and an absence of indications of overfitting.https://doi.org/10.1088/2632-2153/ade4f0skin diseasedensenetdeep learningtransfer learning |
| spellingShingle | Xiaowei Song Yurong Mei Zhilei Zhao Hao Chang Lina Han Hui Wang Xinyi Zhang Guoqiang Wang FFTL-Net: a network for the classification of skin diseases based on feature fusion and transfer learning Machine Learning: Science and Technology skin disease densenet deep learning transfer learning |
| title | FFTL-Net: a network for the classification of skin diseases based on feature fusion and transfer learning |
| title_full | FFTL-Net: a network for the classification of skin diseases based on feature fusion and transfer learning |
| title_fullStr | FFTL-Net: a network for the classification of skin diseases based on feature fusion and transfer learning |
| title_full_unstemmed | FFTL-Net: a network for the classification of skin diseases based on feature fusion and transfer learning |
| title_short | FFTL-Net: a network for the classification of skin diseases based on feature fusion and transfer learning |
| title_sort | fftl net a network for the classification of skin diseases based on feature fusion and transfer learning |
| topic | skin disease densenet deep learning transfer learning |
| url | https://doi.org/10.1088/2632-2153/ade4f0 |
| work_keys_str_mv | AT xiaoweisong fftlnetanetworkfortheclassificationofskindiseasesbasedonfeaturefusionandtransferlearning AT yurongmei fftlnetanetworkfortheclassificationofskindiseasesbasedonfeaturefusionandtransferlearning AT zhileizhao fftlnetanetworkfortheclassificationofskindiseasesbasedonfeaturefusionandtransferlearning AT haochang fftlnetanetworkfortheclassificationofskindiseasesbasedonfeaturefusionandtransferlearning AT linahan fftlnetanetworkfortheclassificationofskindiseasesbasedonfeaturefusionandtransferlearning AT huiwang fftlnetanetworkfortheclassificationofskindiseasesbasedonfeaturefusionandtransferlearning AT xinyizhang fftlnetanetworkfortheclassificationofskindiseasesbasedonfeaturefusionandtransferlearning AT guoqiangwang fftlnetanetworkfortheclassificationofskindiseasesbasedonfeaturefusionandtransferlearning |