Multiscale Softmax Cross Entropy for Fovea Localization on Color Fundus Photography

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wu, Yuli, Walter, Peter, Merhof, Dorit
Natura: Preprint
Pubblicazione: 2021
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911457460879360
author Wu, Yuli
Walter, Peter
Merhof, Dorit
author_facet Wu, Yuli
Walter, Peter
Merhof, Dorit
contents Fovea localization is one of the most popular tasks in ophthalmic medical image analysis, where the coordinates of the center point of the macula lutea, i.e. fovea centralis, should be calculated based on color fundus images. In this work, we treat the localization problem as a classification task, where the coordinates of the x- and y-axis are considered as the target classes. Moreover, the combination of the softmax activation function and the cross entropy loss function is modified to its multiscale variation to encourage the predicted coordinates to be located closely to the ground-truths. Based on color fundus photography images, we empirically show that the proposed multiscale softmax cross entropy yields better performance than the vanilla version and than the mean squared error loss with sigmoid activation, which provides a novel approach for coordinate regression.
format Preprint
id arxiv_https___arxiv_org_abs_2112_04499
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Multiscale Softmax Cross Entropy for Fovea Localization on Color Fundus Photography
Wu, Yuli
Walter, Peter
Merhof, Dorit
Image and Video Processing
Computer Vision and Pattern Recognition
Fovea localization is one of the most popular tasks in ophthalmic medical image analysis, where the coordinates of the center point of the macula lutea, i.e. fovea centralis, should be calculated based on color fundus images. In this work, we treat the localization problem as a classification task, where the coordinates of the x- and y-axis are considered as the target classes. Moreover, the combination of the softmax activation function and the cross entropy loss function is modified to its multiscale variation to encourage the predicted coordinates to be located closely to the ground-truths. Based on color fundus photography images, we empirically show that the proposed multiscale softmax cross entropy yields better performance than the vanilla version and than the mean squared error loss with sigmoid activation, which provides a novel approach for coordinate regression.
title Multiscale Softmax Cross Entropy for Fovea Localization on Color Fundus Photography
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2112.04499