Automated Skin Lesion Classification Using Ensemble of Deep Neural Networks in ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection Challenge

TL;DR

This paper explores the use of ensemble deep neural networks for skin lesion classification, achieving high validation scores on the ISIC 2018 dataset to aid melanoma detection.

Contribution

It introduces a deep learning approach using multiple neural network architectures and demonstrates its effectiveness on the ISIC 2018 challenge dataset.

Findings

PNASNet-5-Large achieved a validation score of 0.76

Deep learning models improved skin lesion classification accuracy

Potential for further performance gains with larger datasets and hyper-parameter tuning

Abstract

In this paper, we studied extensively on different deep learning based methods to detect melanoma and skin lesion cancers. Melanoma, a form of malignant skin cancer is very threatening to health. Proper diagnosis of melanoma at an earlier stage is crucial for the success rate of complete cure. Dermoscopic images with Benign and malignant forms of skin cancer can be analyzed by computer vision system to streamline the process of skin cancer detection. In this study, we experimented with various neural networks which employ recent deep learning based models like PNASNet-5-Large, InceptionResNetV2, SENet154, InceptionV4. Dermoscopic images are properly processed and augmented before feeding them into the network. We tested our methods on International Skin Imaging Collaboration (ISIC) 2018 challenge dataset. Our system has achieved best validation score of 0.76 for PNASNet-5-Large model. Further improvement and optimization of the proposed methods with a bigger training dataset and carefully chosen hyper-parameter could improve the performances. The code available for download at https://github.com/miltonbd/ISIC_2018_classification