Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting
Skin lesions are caused due to multiple factors, like allergies, infections, exposition to the sun, etc. These skin diseases have become a challenge in medical diagnosis due to visual similarities, where image classification is an essential task to achieve an adequate diagnostic of different lesions...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2021 |
| País: | España |
| Institución: | Instituto de Salud Carlos III (ISCIII) |
| Repositorio: | Repisalud |
| Idioma: | español |
| OAI Identifier: | oai:repisalud.isciii.es:20.500.12105/18430 |
| Acceso en línea: | http://hdl.handle.net/20.500.12105/18430 |
| Access Level: | acceso abierto |
| Palabra clave: | Image processing Deep learning Classification Skin lesion Melanoma Convolutional neural networks Skin cancer Procesamiento de imagen asistido por computador Aprendizaje profundo Clasificación Lesiones por desenguantamiento Red nerviosa Neoplasias cutáneas Skin Neoplasms Neural Networks (Computer) Skin Diseases Hypersensitivity Humans Melanocytes Probability Epidermis Image Processing, Computer-Assisted |
| Sumario: | Skin lesions are caused due to multiple factors, like allergies, infections, exposition to the sun, etc. These skin diseases have become a challenge in medical diagnosis due to visual similarities, where image classification is an essential task to achieve an adequate diagnostic of different lesions. Melanoma is one of the best-known types of skin lesions due to the vast majority of skin cancer deaths. In this work, we propose an ensemble of improved convolutional neural networks combined with a test-time regularly spaced shifting technique for skin lesion classification. The shifting technique builds several versions of the test input image, which are shifted by displacement vectors that lie on a regular lattice in the plane of possible shifts. These shifted versions of the test image are subsequently passed on to each of the classifiers of an ensemble. Finally, all the outputs from the classifiers are combined to yield the final result. Experiment results show a significant improvement on the well-known HAM10000 dataset in terms of accuracy and F-score. In particular, it is demonstrated that our combination of ensembles with test-time regularly spaced shifting yields better performance than any of the two methods when applied alone. |
|---|