Fine-tuning pre-trained neural networks for medical image classification in small clinical datasets

• Published in: Multimedia tools and applications Vol. 83; no. 9; pp. 27305 - 27329
• Main Authors: Spolaôr, Newton, Lee, Huei Diana, Mendes, Ana Isabel, Nogueira, Conceição Veloso, Parmezan, Antonio Rafael Sabino, Takaki, Weber Shoity Resende, Coy, Claudio Saddy Rodrigues, Wu, Feng Chung, Fonseca-Pinto, Rui
• Format: Journal Article
• Language: English
• Published: New York Springer US 01-03-2024; Springer Nature B.V
• Subjects: Artificial neural networks; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Datasets; Deep learning; Dermatology; Image acquisition; Image classification; Knowledge acquisition; Lesions; Machine learning; Medical imaging; Multimedia Information Systems; Neural networks; Special Purpose and Application-Based Systems; Track 2: Medical Applications of Multimedia; Feature learning; RMSprop; Statistical test; Few-shot learning; Shallow learning; VGG
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-16529-w

Convolutional neural networks have been effective in several applications, arising as a promising supporting tool in a relevant Dermatology problem: skin cancer diagnosis. However, generalizing well can be difficult when little training data is available. The fine-tuning transfer learning strategy has been employed to differentiate properly malignant from non-malignant lesions in dermoscopic images. Fine-tuning a pre-trained network allows one to classify data in the target domain, occasionally with few images, using knowledge acquired in another domain. This work proposes eight fine-tuning settings based on convolutional networks previously trained on ImageNet that can be employed mainly in limited data samples to reduce overfitting risk. They differ on the architecture, the learning rate and the number of unfrozen layer blocks. We evaluated the settings in two public datasets with 104 and 200 dermoscopic images. By finding competitive configurations in small datasets, this paper illustrates that deep learning can be effective if one has only a few dozen malignant and non-malignant lesion images to study and differentiate in Dermatology. The proposal is also flexible and potentially useful for other domains. In fact, it performed satisfactorily in an assessment conducted in a larger dataset with 746 computerized tomographic images associated with the coronavirus disease.