RT Conference Proceedings
T1 Enhanced transfer learning model by image shifting on a square lattice for skin lesion malignancy assessment
A1 Thurnhofer Hemsi, Karl
A1 Maza Quiroga, Rosa María
A1 Domínguez-Merino, Enrique
A1 Molina-Cabello, Miguel Ángel
A1 López-Rubio, Ezequiel
K1 Ciencias de la computación
K1 Lenguaje de computación
K1 Programación
K1 Cáncer de piel
K1 Diagnóstico médico
AB Skin cancer is one of the most prevalent diseases among people. Physicians have a challenge every time they haveto determine whether a diseased skin is benign or malign. There exist clinical diagnosis methods (such as the ABCDE rule), butthey depend mainly on the physician’s experience and might be imprecise. Deep learning models are very extended in medicalimage analysis, and several deep models have been proposed for moles classification. In this work, a convolutional neural network is proposed to support the diagnosis procedure. The proposed MobileNetV2-based model is improved by a shifting technique, providing better performance than raw transfer learning models for moles classification. Experiments show that this technique could be applied to the state-of-the-art deep models to improve their results and outperform the training phase.
YR 2021
FD 2021
LK https://hdl.handle.net/10630/22717
UL https://hdl.handle.net/10630/22717
LA eng
NO Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 4 mar 2026