Design of inception architecture for skin melanoma classification

Abstract

The number of people diagnosed with skin cancer is increasing sharply. Both invasive and non-invasive methods of examination may be used to investigate it. However, the invasive method is more difficult for the patient because samples must be taken from the lesion itself, or the whole lesion must be cut out. It also requires more time and cost. To avoid invasive procedures, computer-based analysis and diagnosis have the potential to increase diagnostic accuracy and turnaround time. This study develops a unique discriminative deep learning architecture (DDLA) for dermoscopic image classification (DIC), called DDLA-DIC, which uses the concept of inception. Using this concept, the proposed DDLA-DIC system is designed wider and deeper and the network learns from various spatial patterns. The proposed DDLA-DIC system can extract image characteristics from dermoscopic images for skin cancer diagnosis in an effective and efficient way. The proposed DDLA-DIC system is evaluated by utilizing the dermoscopic images from the PH2 database, and the obtained classification results are based on a random split approach. The simulation results indicate that the framework has a great deal of potential with 99.79% accuracy.