Melanoma Detection with Uncertainty Quantification

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kim, SangHyuk, Gaibor, Edward, Matejek, Brian, Haehn, Daniel
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913578861199360
author Kim, SangHyuk
Gaibor, Edward
Matejek, Brian
Haehn, Daniel
author_facet Kim, SangHyuk
Gaibor, Edward
Matejek, Brian
Haehn, Daniel
contents Early detection of melanoma is crucial for improving survival rates. Current detection tools often utilize data-driven machine learning methods but often overlook the full integration of multiple datasets. We combine publicly available datasets to enhance data diversity, allowing numerous experiments to train and evaluate various classifiers. We then calibrate them to minimize misdiagnoses by incorporating uncertainty quantification. Our experiments on benchmark datasets show accuracies of up to 93.2% before and 97.8% after applying uncertainty-based rejection, leading to a reduction in misdiagnoses by over 40.5%. Our code and data are publicly available, and a web-based interface for quick melanoma detection of user-supplied images is also provided.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10322
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Melanoma Detection with Uncertainty Quantification
Kim, SangHyuk
Gaibor, Edward
Matejek, Brian
Haehn, Daniel
Computer Vision and Pattern Recognition
Early detection of melanoma is crucial for improving survival rates. Current detection tools often utilize data-driven machine learning methods but often overlook the full integration of multiple datasets. We combine publicly available datasets to enhance data diversity, allowing numerous experiments to train and evaluate various classifiers. We then calibrate them to minimize misdiagnoses by incorporating uncertainty quantification. Our experiments on benchmark datasets show accuracies of up to 93.2% before and 97.8% after applying uncertainty-based rejection, leading to a reduction in misdiagnoses by over 40.5%. Our code and data are publicly available, and a web-based interface for quick melanoma detection of user-supplied images is also provided.
title Melanoma Detection with Uncertainty Quantification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.10322