Deep learning for actinic keratosis classification
Classification of biological images plays a crucial role in many biological problems, e.g. recognition of cell phenotypes and maturation levels, localization of cell organelles and histopathological classification, and holds the potential to support early diagnosis, which is critical in disease prev...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2020-05-01
|
| Series: | AIMS Electronics and Electrical Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/10.3934/ElectrEng.2020.1.47/fulltext.html |
| _version_ | 1818213218295742464 |
|---|---|
| author | Loris Nanni Michelangelo Paci Gianluca Maguolo Stefano Ghidoni |
| author_facet | Loris Nanni Michelangelo Paci Gianluca Maguolo Stefano Ghidoni |
| author_sort | Loris Nanni |
| collection | DOAJ |
| description | Classification of biological images plays a crucial role in many biological problems, e.g. recognition of cell phenotypes and maturation levels, localization of cell organelles and histopathological classification, and holds the potential to support early diagnosis, which is critical in disease prevention. In this paper, we tested different ensemble of canonical and deep classifiers to provide accurate identification of actinic keratosis (AK), one of the most common skin lesions that could degenerate into lethal squamous cell carcinomas.<br />
We used a clinical image dataset to build and test different ensembles of support vector machines trained by handcrafted descriptors and convolutional neural networks (CNNs) for which we experimented different learning rates, augmentation techniques (e.g. warping) and topologies.<br />
Our results show that the proposed ensemble obtains performance comparable to the state of the art. To reproduce the experiments reported in this paper, the MATLAB code of all the descriptors is available at https://github.com/LorisNanni. |
| first_indexed | 2024-12-12T06:00:48Z |
| format | Article |
| id | doaj.art-5e72ce9b2e5a49339cf5147513b7de30 |
| institution | Directory Open Access Journal |
| issn | 2578-1588 |
| language | English |
| last_indexed | 2024-12-12T06:00:48Z |
| publishDate | 2020-05-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | AIMS Electronics and Electrical Engineering |
| spelling | doaj.art-5e72ce9b2e5a49339cf5147513b7de302022-12-22T00:35:24ZengAIMS PressAIMS Electronics and Electrical Engineering2578-15882020-05-0141475610.3934/ElectrEng.2020.1.47Deep learning for actinic keratosis classificationLoris Nanni0Michelangelo Paci1Gianluca Maguolo2Stefano Ghidoni3Stefano Ghidoni2 Faculty of Medicine and Health Technology, Tampere UniversityStefano GhidoniStefano GhidoniClassification of biological images plays a crucial role in many biological problems, e.g. recognition of cell phenotypes and maturation levels, localization of cell organelles and histopathological classification, and holds the potential to support early diagnosis, which is critical in disease prevention. In this paper, we tested different ensemble of canonical and deep classifiers to provide accurate identification of actinic keratosis (AK), one of the most common skin lesions that could degenerate into lethal squamous cell carcinomas.<br /> We used a clinical image dataset to build and test different ensembles of support vector machines trained by handcrafted descriptors and convolutional neural networks (CNNs) for which we experimented different learning rates, augmentation techniques (e.g. warping) and topologies.<br /> Our results show that the proposed ensemble obtains performance comparable to the state of the art. To reproduce the experiments reported in this paper, the MATLAB code of all the descriptors is available at https://github.com/LorisNanni.https://www.aimspress.com/article/10.3934/ElectrEng.2020.1.47/fulltext.htmlmicroscopy imaging classificationdeep learningconvolutional neural networksbioimage classificationsactinic keratosis |
| spellingShingle | Loris Nanni Michelangelo Paci Gianluca Maguolo Stefano Ghidoni Deep learning for actinic keratosis classification AIMS Electronics and Electrical Engineering microscopy imaging classification deep learning convolutional neural networks bioimage classifications actinic keratosis |
| title | Deep learning for actinic keratosis classification |
| title_full | Deep learning for actinic keratosis classification |
| title_fullStr | Deep learning for actinic keratosis classification |
| title_full_unstemmed | Deep learning for actinic keratosis classification |
| title_short | Deep learning for actinic keratosis classification |
| title_sort | deep learning for actinic keratosis classification |
| topic | microscopy imaging classification deep learning convolutional neural networks bioimage classifications actinic keratosis |
| url | https://www.aimspress.com/article/10.3934/ElectrEng.2020.1.47/fulltext.html |
| work_keys_str_mv | AT lorisnanni deeplearningforactinickeratosisclassification AT michelangelopaci deeplearningforactinickeratosisclassification AT gianlucamaguolo deeplearningforactinickeratosisclassification AT stefanoghidoni deeplearningforactinickeratosisclassification |