Self-Supervised Learning to Increase the Performance of Skin Lesion Classification

To successfully train a deep neural network, a large amount of human-labeled data is required. Unfortunately, in many areas, collecting and labeling data is a difficult and tedious task. Several ways have been developed to mitigate the problem associated with the shortage of data, the most common of which is transfer learning. However, in many cases, the use of transfer learning as the only remedy is insufficient. In this study, we improve deep neural models training and increase the classification accuracy under a scarcity of data by the use of the self-supervised learning technique. Self-supervised learning allows an unlabeled dataset to be used for pretraining the network, as opposed to transfer learning that requires labeled datasets. The pretrained network can be then fine-tuned using the annotated data. Moreover, we investigated the effect of combining the self-supervised learning approach with transfer learning. It is shown that this strategy outperforms network training from scratch or with transfer learning. The tests were conducted on a very important and sensitive application (skin lesion classification), but the presented approach can be applied to a broader family of applications, especially in the medical domain where the scarcity of data is a real problem.

[1]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Michał Grochowski,et al.  Selected technical issues of deep neural networks for image classification purposes , 2023, Bulletin of the Polish Academy of Sciences Technical Sciences.

[3]  Chao Yang,et al.  A Survey on Deep Transfer Learning , 2018, ICANN.

[4]  Mark J. van der Laan,et al.  The relative performance of ensemble methods with deep convolutional neural networks for image classification , 2017, Journal of applied statistics.

[5]  Balázs Harangi,et al.  Skin lesion detection based on an ensemble of deep convolutional neural network , 2017, J. Biomed. Informatics.

[6]  Arkadiusz Kwasigroch,et al.  Intelligent system supporting diagnosis of malignant melanoma , 2017, KKA.

[7]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[8]  Arkadiusz Kwasigroch,et al.  Neural Architecture Search for Skin Lesion Classification , 2020, IEEE Access.

[9]  Jorge S. Marques,et al.  Explainable skin lesion diagnosis using taxonomies , 2021, Pattern Recognit..

[10]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Yong Xia,et al.  Attention Residual Learning for Skin Lesion Classification , 2019, IEEE Transactions on Medical Imaging.

[12]  Jorge S. Marques,et al.  A Survey of Feature Extraction in Dermoscopy Image Analysis of Skin Cancer , 2019, IEEE Journal of Biomedical and Health Informatics.

[13]  Fan Zhang,et al.  OTL-Classifier: Towards Imaging Processing for Future Unmanned Overhead Transmission Line Maintenance , 2019, Electronics.

[14]  Michał Grochowski,et al.  Data augmentation for improving deep learning in image classification problem , 2018, 2018 International Interdisciplinary PhD Workshop (IIPhDW).

[15]  Heung-Il Suk,et al.  Deep Learning in Medical Image Analysis. , 2017, Annual review of biomedical engineering.

[16]  Farzin Aghdasi,et al.  A Strong and Efficient Baseline for Vehicle Re-Identification Using Deep Triplet Embedding , 2020, J. Artif. Intell. Soft Comput. Res..

[17]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).