Transfer Learning-Based Encoder-Decoder Model for Skin Lesion Segmentation

Justice Kwame Appati, Leonard Mensah Boante, Ebenezer Owusu, Silas Kwabla Gah

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Skin cancer is a highly dangerous form of cancer that affects numerous countries. Studies have shown that the timely detection of melanoma or skin cancer can lead to improved survival rates. Patients diagnosed with melanoma cancer at an early stage have a 90% chance of survival and tend to respond well to treatment. With this understanding, this study seeks to develop various architectures for the early detection of melanoma. Transfer learning, an approach that has garnered significant attention among researchers in solving computer vision problems, was employed in this project. In this study the U-Net architecture’s encoder was modified by replacine it with a pre-trained model to enhance its performance. The performance of the proposed segmentation model was evaluated using the ISIC-2018 dataset. The model recorded a dice coefficient score of 90.7% which is a 4.7% improvement on U-Net model (86%) for segmenting skin lesions. The model’s performance was further evaluated using other metrics such as recall (91.86%) and precision (91.13%). Subsequent analysis was conducted to determine the best hyper-parameters that provide the highest degree of performance when segmenting skin lesions. The results revealed that using the Efficient-Net pre-trained model as the encoder, PReLu activation function, and Tversky loss function yielded better performance in segmenting skin lesions.

Original languageEnglish
Title of host publicationInformation, Communication and Computing Technology - 8th International Conference, ICICCT 2023, Revised Selected Papers
EditorsJemal Abawajy, Joao Tavares, Latika Kharb, Deepak Chahal, Ali Bou Nassif
PublisherSpringer Science and Business Media Deutschland GmbH
Pages117-128
Number of pages12
ISBN (Print)9783031438370
DOIs
Publication statusPublished - 2023
Event8th International Conference on Information, Communication and Computing Technology, ICICCT 2023 - New Delhi
Duration: 27 May 202327 May 2023

Publication series

NameCommunications in Computer and Information Science
Volume1841 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference8th International Conference on Information, Communication and Computing Technology, ICICCT 2023
Country/TerritoryIndia
CityNew Delhi
Period27/05/2327/05/23

Keywords

  • Encoder
  • Segmentation
  • Transfer Learning
  • U-Net architecture

Fingerprint

Dive into the research topics of 'Transfer Learning-Based Encoder-Decoder Model for Skin Lesion Segmentation'. Together they form a unique fingerprint.

Cite this