An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model
This research addresses the challenge of automating skin disease diagnosis using dermatoscopic images. The primary issue lies in accurately classifying pigmented skin lesions, which traditionally rely on manual assessment by dermatologists and are prone to subjectivity and time consumption. By integ...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2024-02-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1884.pdf |
| _version_ | 1797292451199713280 |
|---|---|
| author | Anubhav De Nilamadhab Mishra Hsien-Tsung Chang |
| author_facet | Anubhav De Nilamadhab Mishra Hsien-Tsung Chang |
| author_sort | Anubhav De |
| collection | DOAJ |
| description | This research addresses the challenge of automating skin disease diagnosis using dermatoscopic images. The primary issue lies in accurately classifying pigmented skin lesions, which traditionally rely on manual assessment by dermatologists and are prone to subjectivity and time consumption. By integrating a hybrid CNN-DenseNet model, this study aimed to overcome the complexities of differentiating various skin diseases and automating the diagnostic process effectively. Our methodology involved rigorous data preprocessing, exploratory data analysis, normalization, and label encoding. Techniques such as model hybridization, batch normalization and data fitting were employed to optimize the model architecture and data fitting. Initial iterations of our convolutional neural network (CNN) model achieved an accuracy of 76.22% on the test data and 75.69% on the validation data. Recognizing the need for improvement, the model was hybridized with DenseNet architecture and ResNet architecture was implemented for feature extraction and then further trained on the HAM10000 and PAD-UFES-20 datasets. Overall, our efforts resulted in a hybrid model that demonstrated an impressive accuracy of 95.7% on the HAM10000 dataset and 91.07% on the PAD-UFES-20 dataset. In comparison to recently published works, our model stands out because of its potential to effectively diagnose skin diseases such as melanocytic nevi, melanoma, benign keratosis-like lesions, basal cell carcinoma, actinic keratoses, vascular lesions, and dermatofibroma, all of which rival the diagnostic accuracy of real-world clinical specialists but also offer customization potential for more nuanced clinical uses. |
| first_indexed | 2024-03-07T19:52:45Z |
| format | Article |
| id | doaj.art-f928462abf64422981ebd1d13e789b8f |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-03-07T19:52:45Z |
| publishDate | 2024-02-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-f928462abf64422981ebd1d13e789b8f2024-02-28T15:05:28ZengPeerJ Inc.PeerJ Computer Science2376-59922024-02-0110e188410.7717/peerj-cs.1884An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet modelAnubhav De0Nilamadhab Mishra1Hsien-Tsung Chang2School of Computing Science & Engineering, VIT Bhopal University, Madhya Pradesh, IndiaSchool of Computing Science & Engineering, VIT Bhopal University, Madhya Pradesh, IndiaDepartment of Computer Science and Information Engineering, Chang Gung University, Taoyuan, TaiwanThis research addresses the challenge of automating skin disease diagnosis using dermatoscopic images. The primary issue lies in accurately classifying pigmented skin lesions, which traditionally rely on manual assessment by dermatologists and are prone to subjectivity and time consumption. By integrating a hybrid CNN-DenseNet model, this study aimed to overcome the complexities of differentiating various skin diseases and automating the diagnostic process effectively. Our methodology involved rigorous data preprocessing, exploratory data analysis, normalization, and label encoding. Techniques such as model hybridization, batch normalization and data fitting were employed to optimize the model architecture and data fitting. Initial iterations of our convolutional neural network (CNN) model achieved an accuracy of 76.22% on the test data and 75.69% on the validation data. Recognizing the need for improvement, the model was hybridized with DenseNet architecture and ResNet architecture was implemented for feature extraction and then further trained on the HAM10000 and PAD-UFES-20 datasets. Overall, our efforts resulted in a hybrid model that demonstrated an impressive accuracy of 95.7% on the HAM10000 dataset and 91.07% on the PAD-UFES-20 dataset. In comparison to recently published works, our model stands out because of its potential to effectively diagnose skin diseases such as melanocytic nevi, melanoma, benign keratosis-like lesions, basal cell carcinoma, actinic keratoses, vascular lesions, and dermatofibroma, all of which rival the diagnostic accuracy of real-world clinical specialists but also offer customization potential for more nuanced clinical uses.https://peerj.com/articles/cs-1884.pdfConvolutional neural networksHybridized densenet modelMulticlass classificationConfocal microscopy analysisSkin histopathological image analysisSkin disease classification |
| spellingShingle | Anubhav De Nilamadhab Mishra Hsien-Tsung Chang An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model PeerJ Computer Science Convolutional neural networks Hybridized densenet model Multiclass classification Confocal microscopy analysis Skin histopathological image analysis Skin disease classification |
| title | An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model |
| title_full | An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model |
| title_fullStr | An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model |
| title_full_unstemmed | An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model |
| title_short | An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model |
| title_sort | approach to the dermatological classification of histopathological skin images using a hybridized cnn densenet model |
| topic | Convolutional neural networks Hybridized densenet model Multiclass classification Confocal microscopy analysis Skin histopathological image analysis Skin disease classification |
| url | https://peerj.com/articles/cs-1884.pdf |
| work_keys_str_mv | AT anubhavde anapproachtothedermatologicalclassificationofhistopathologicalskinimagesusingahybridizedcnndensenetmodel AT nilamadhabmishra anapproachtothedermatologicalclassificationofhistopathologicalskinimagesusingahybridizedcnndensenetmodel AT hsientsungchang anapproachtothedermatologicalclassificationofhistopathologicalskinimagesusingahybridizedcnndensenetmodel AT anubhavde approachtothedermatologicalclassificationofhistopathologicalskinimagesusingahybridizedcnndensenetmodel AT nilamadhabmishra approachtothedermatologicalclassificationofhistopathologicalskinimagesusingahybridizedcnndensenetmodel AT hsientsungchang approachtothedermatologicalclassificationofhistopathologicalskinimagesusingahybridizedcnndensenetmodel |