Vol.35, No.1, 2023, pp.675-687, doi:10.32604/iasc.2023.025930
OPEN ACCESS
ARTICLE
Automated Skin Lesion Diagnosis and Classification Using Learning Algorithms
  • A. Soujanya1,*, N. Nandhagopal2
1 Department of Information and Communication Engineering, Anna University, Chennai, 600025, Tamil Nadu, India
2 Department of Electronics and Communication Engineering, Excel Engineering College, Namakkal, 638052, Tamil Nadu, India
* Corresponding Author: A. Soujanya. Email:
Received 09 December 2021; Accepted 10 January 2022; Issue published 06 June 2022
Abstract
Due to the rising occurrence of skin cancer and inadequate clinical expertise, it is needed to design Artificial Intelligence (AI) based tools to diagnose skin cancer at an earlier stage. Since massive skin lesion datasets have existed in the literature, the AI-based Deep Learning (DL) models find useful to differentiate benign and malignant skin lesions using dermoscopic images. This study develops an Automated Seeded Growing Segmentation with Optimal EfficientNet (ARGS-OEN) technique for skin lesion segmentation and classification. The proposed ASRGS-OEN technique involves the design of an optimal EfficientNet model in which the hyper-parameter tuning process takes place using the Flower Pollination Algorithm (FPA). In addition, Multiwheel Attention Memory Network Encoder (MWAMNE) based classification technique is employed for identifying the appropriate class labels of the dermoscopic images. A comprehensive simulation analysis of the ASRGS-OEN technique takes place and the results are inspected under several dimensions. The simulation results highlighted the supremacy of the ASRGS-OEN technique on the applied dermoscopic images compared to the recently developed approaches.
Keywords
Computer aided diagnosis; deep learning; image segmentation; skin lesion diagnosis; dermoscopic images; medical image processing
Cite This Article
A. Soujanya and N. Nandhagopal, "Automated skin lesion diagnosis and classification using learning algorithms," Intelligent Automation & Soft Computing, vol. 35, no.1, pp. 675–687, 2023.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.