Skin Cancer Classification using Inception Network and Transfer Learning

Abstract

Medical data classification is typically a challenging task due to imbalance between classes. In this paper, we propose an approach to classify dermatoscopic images from HAM10000 (Human Against Machine with 10000 training images) dataset, consisting of seven imbalanced types of skin lesions, with good precision and low resources requirements. Classification is done by using a pretrained convolutional neural network. We evaluate the accuracy and performance of the proposal and illustrate possible extensions.

International Conference on Computational Science and Its Applications, ICCSA 2020

References in corpus (4)

• The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions
• The Marginal Value of Adaptive Gradient Methods in Machine Learning
• An Approach for Improving Automatic Mouth Emotion Recognition
• Towards a learning-based performance modeling for accelerating Deep Neural Networks

Cited by in corpus (4)

• Implementing a scalable and elastic computing environment based on Cloud Containers
• A new method for binary classification of proteins with Machine Learning
• An example of use of Variational Methods in Quantum Machine Learning
• IoT to monitor people flow in areas of public interest