Convolutional Neural Network for Skin Lesion Classification: Understanding the Fundamentals Through Hands-On Learning
Deep learning architectures for the classification of images have shown outstanding results in a variety of disciplines, including dermatology. The expectations generated by deep learning for, e.g., image-based diagnosis have created the need for non-experts to become familiar with the working princ...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-03-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2021.644327/full |
| _version_ | 1818576976090234880 |
|---|---|
| author | Marta Cullell-Dalmau Sergio Noé Marta Otero-Viñas Ivan Meić Ivan Meić Carlo Manzo |
| author_facet | Marta Cullell-Dalmau Sergio Noé Marta Otero-Viñas Ivan Meić Ivan Meić Carlo Manzo |
| author_sort | Marta Cullell-Dalmau |
| collection | DOAJ |
| description | Deep learning architectures for the classification of images have shown outstanding results in a variety of disciplines, including dermatology. The expectations generated by deep learning for, e.g., image-based diagnosis have created the need for non-experts to become familiar with the working principles of these algorithms. In our opinion, getting hands-on experience with these tools through a simplified but accurate model can facilitate their understanding in an intuitive way. The visualization of the results of the operations performed by deep learning algorithms on dermatological images can help students to grasp concepts like convolution, even without an advanced mathematical background. In addition, the possibility to tune hyperparameters and even to tweak computer code further empower the reach of an intuitive comprehension of these processes, without requiring advanced computational and theoretical skills. This is nowadays possible thanks to recent advances that have helped to lower technical and technological barriers associated with the use of these tools, making them accessible to a broader community. Therefore, we propose a hands-on pedagogical activity that dissects the procedures to train a convolutional neural network on a dataset containing images of skin lesions associated with different skin cancer categories. The activity is available open-source and its execution does not require the installation of software. We further provide a step-by-step description of the algorithm and of its functions, following the development of the building blocks of the computer code, guiding the reader through the execution of a realistic example, including the visualization and the evaluation of the results. |
| first_indexed | 2024-12-16T06:22:34Z |
| format | Article |
| id | doaj.art-f3a5af6b515f417482129e71bd84d0ba |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-12-16T06:22:34Z |
| publishDate | 2021-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-f3a5af6b515f417482129e71bd84d0ba2022-12-21T22:41:05ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2021-03-01810.3389/fmed.2021.644327644327Convolutional Neural Network for Skin Lesion Classification: Understanding the Fundamentals Through Hands-On LearningMarta Cullell-Dalmau0Sergio Noé1Marta Otero-Viñas2Ivan Meić3Ivan Meić4Carlo Manzo5The QuBI Lab, Facultat de Ciències i Tecnologia, Universitat de Vic – Universitat Central de Catalunya, Vic, SpainThe QuBI Lab, Facultat de Ciències i Tecnologia, Universitat de Vic – Universitat Central de Catalunya, Vic, SpainTissue Repair and Regeneration Laboratory, Facultat de Ciències i Tecnologia, Universitat de Vic – Universitat Central de Catalunya, Vic, SpainThe QuBI Lab, Facultat de Ciències i Tecnologia, Universitat de Vic – Universitat Central de Catalunya, Vic, SpainUniversity of Zagreb, Zagreb, CroatiaThe QuBI Lab, Facultat de Ciències i Tecnologia, Universitat de Vic – Universitat Central de Catalunya, Vic, SpainDeep learning architectures for the classification of images have shown outstanding results in a variety of disciplines, including dermatology. The expectations generated by deep learning for, e.g., image-based diagnosis have created the need for non-experts to become familiar with the working principles of these algorithms. In our opinion, getting hands-on experience with these tools through a simplified but accurate model can facilitate their understanding in an intuitive way. The visualization of the results of the operations performed by deep learning algorithms on dermatological images can help students to grasp concepts like convolution, even without an advanced mathematical background. In addition, the possibility to tune hyperparameters and even to tweak computer code further empower the reach of an intuitive comprehension of these processes, without requiring advanced computational and theoretical skills. This is nowadays possible thanks to recent advances that have helped to lower technical and technological barriers associated with the use of these tools, making them accessible to a broader community. Therefore, we propose a hands-on pedagogical activity that dissects the procedures to train a convolutional neural network on a dataset containing images of skin lesions associated with different skin cancer categories. The activity is available open-source and its execution does not require the installation of software. We further provide a step-by-step description of the algorithm and of its functions, following the development of the building blocks of the computer code, guiding the reader through the execution of a realistic example, including the visualization and the evaluation of the results.https://www.frontiersin.org/articles/10.3389/fmed.2021.644327/fullconvolutional neural networksskin lesion analysisclassificationmelanomadeep learning |
| spellingShingle | Marta Cullell-Dalmau Sergio Noé Marta Otero-Viñas Ivan Meić Ivan Meić Carlo Manzo Convolutional Neural Network for Skin Lesion Classification: Understanding the Fundamentals Through Hands-On Learning Frontiers in Medicine convolutional neural networks skin lesion analysis classification melanoma deep learning |
| title | Convolutional Neural Network for Skin Lesion Classification: Understanding the Fundamentals Through Hands-On Learning |
| title_full | Convolutional Neural Network for Skin Lesion Classification: Understanding the Fundamentals Through Hands-On Learning |
| title_fullStr | Convolutional Neural Network for Skin Lesion Classification: Understanding the Fundamentals Through Hands-On Learning |
| title_full_unstemmed | Convolutional Neural Network for Skin Lesion Classification: Understanding the Fundamentals Through Hands-On Learning |
| title_short | Convolutional Neural Network for Skin Lesion Classification: Understanding the Fundamentals Through Hands-On Learning |
| title_sort | convolutional neural network for skin lesion classification understanding the fundamentals through hands on learning |
| topic | convolutional neural networks skin lesion analysis classification melanoma deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2021.644327/full |
| work_keys_str_mv | AT martacullelldalmau convolutionalneuralnetworkforskinlesionclassificationunderstandingthefundamentalsthroughhandsonlearning AT sergionoe convolutionalneuralnetworkforskinlesionclassificationunderstandingthefundamentalsthroughhandsonlearning AT martaoterovinas convolutionalneuralnetworkforskinlesionclassificationunderstandingthefundamentalsthroughhandsonlearning AT ivanmeic convolutionalneuralnetworkforskinlesionclassificationunderstandingthefundamentalsthroughhandsonlearning AT ivanmeic convolutionalneuralnetworkforskinlesionclassificationunderstandingthefundamentalsthroughhandsonlearning AT carlomanzo convolutionalneuralnetworkforskinlesionclassificationunderstandingthefundamentalsthroughhandsonlearning |