Search

Your search keyword '"Diagnòstic per la imatge"' showing total 2 results
Start Over Descriptor "Diagnòstic per la imatge" Publisher acta press
2 results on '"Diagnòstic per la imatge"'

1. Skin lesion classification from dermoscopic images using deep learning techniques

Author

Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions, Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo, Romero-Lopez, Adrià, Giró Nieto, Xavier, Burdick, Jack, Marques, Oge, Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions, Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo, Romero-Lopez, Adrià, Giró Nieto, Xavier, Burdick, Jack, and Marques, Oge

Abstract

The recent emergence of deep learning methods for medical image analysis has enabled the development of intelligent medical imaging-based diagnosis systems that can assist the human expert in making better decisions about a patient’s health. In this paper we focus on the problem of skin lesion classification, particularly early melanoma detection, and present a deep-learning based approach to solve the problem of classifying a dermoscopic image containing a skin lesion as malignant or benign. The proposed solution is built around the VGGNet convolutional neural network architecture and uses the transfer learning paradigm. Experimental results are encouraging: on the ISIC Archive dataset, the proposed method achieves a sensitivity value of 78.66%, which is significantly higher than the current state of the art on that dataset., Postprint (author's final draft)

Published
2017

2. Skin lesion classification from dermoscopic images using deep learning techniques

Author

Xavier Giro-i-Nieto, Jack Burdick, Oge Marques, Adria Romero Lopez, Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions, and Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo

Subjects
Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Dermatology, Machine learning, computer.software_genre, Convolutional neural network, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, Imatges -- Processament -- Tècniques digitals, 0302 clinical medicine, 0202 electrical engineering, electronic engineering, information engineering, Medical imaging, Image processing--Digital techniques, business.industry, Deep learning, Enginyeria de la telecomunicació::Processament del senyal::Reconeixement de formes [Àrees temàtiques de la UPC], deep learning, Dermatologia, Melanoma detection, Diagnòstic per la imatge, Ciències de la salut::Medicina::Dermatologia [Àrees temàtiques de la UPC], machine learning, Imatges mèdiques, Diagnostic imaging, 020201 artificial intelligence & image processing, Artificial intelligence, Skin lesion, Focus (optics), Transfer of learning, business, computer, medical image analysis
Abstract

The recent emergence of deep learning methods for medical image analysis has enabled the development of intelligent medical imaging-based diagnosis systems that can assist the human expert in making better decisions about a patient’s health. In this paper we focus on the problem of skin lesion classification, particularly early melanoma detection, and present a deep-learning based approach to solve the problem of classifying a dermoscopic image containing a skin lesion as malignant or benign. The proposed solution is built around the VGGNet convolutional neural network architecture and uses the transfer learning paradigm. Experimental results are encouraging: on the ISIC Archive dataset, the proposed method achieves a sensitivity value of 78.66%, which is significantly higher than the current state of the art on that dataset.

Catalog

Books, media, physical & digital resources
See catalog results