Convolutional neural networks are used to classify dermoscopic skin lesion images. The high accuracy of deep learning models is well documented; however, those models do not perform very well on testing (unseen data) sets due to imbalanced classes of images. To tackle this problem, over-sampling and under-sampling methods are explored in this study. Part 1 of the study focuses on the details of these sampling techniques, while Part 2 highlights the architecture of the deep learning model and its performance when using both sampling approaches. The results of Part 1 show that through the use of unsupervised learning techniques, namely, Hierarchical Clustering, Self-Organizing Maps, and K-Means, similar images are clustered, based on the skin lesions’ shape and color. Using augmentation for oversampling, 32,731 images are included for the training task in total. For undersampling, unsupervised learning techniques suggested 3 or 4 sub-groups of melanocytic nevi. Going through those clusters, the image background color also affects the way unsupervised learning techniques group similar images together.
Sampling Methods to Balance Classes in Dermoscopic Skin Lesion Images
Lect. Notes Electrical Eng.
International Conference on Robotics, Vision, Signal Processing and Power Applications ; 2021 April 05, 2021 - April 06, 2021
Proceedings of the 12th International Conference on Robotics, Vision, Signal Processing and Power Applications ; Chapter : 51 ; 407-413
2024-03-31
7 pages
Article/Chapter (Book)
Electronic Resource
English
Measuring Lesion Growth from 3D Medical Images
British Library Conference Proceedings | 1997
|Measuring lesion growth from 3D medical images
IEEE | 1997
|