Integrating spatial configuration into heatmap regression based CNNs for landmark localization

Horst Bischof, Darko Stern, Christian Payer, Martin Urschler

Research output: Contribution to journal › Article › Research › peer-review

Abstract

In many medical image analysis applications, only a limited amount of training data is available due to the costs of image acquisition and the large manual annotation effort required from experts. Training recent state-of-the-art machine learning methods like convolutional neural networks (CNNs) from small datasets is a challenging task. In this work on anatomical landmark localization, we propose a CNN architecture that learns to split the localization task into two simpler sub-problems, reducing the overall need for large training datasets. Our fully convolutional SpatialConfiguration-Net (SCN) learns this simplification due to multiplying the heatmap predictions of its two components and by training the network in an end-to-end manner. Thus, the SCN dedicates one component to locally accurate but ambiguous candidate predictions, while the other component improves robustness to ambiguities by incorporating the …
Original languageGerman
Pages (from-to)207-219
JournalMedical image analysis
Publication statusPublished - 2019

Cite this

Integrating spatial configuration into heatmap regression based CNNs for landmark localization. / Bischof, Horst; Stern, Darko; Payer, Christian; Urschler, Martin.

In: Medical image analysis, 2019, p. 207-219.

Research output: Contribution to journal › Article › Research › peer-review

Bischof, H, Stern, D, Payer, C & Urschler, M 2019, 'Integrating spatial configuration into heatmap regression based CNNs for landmark localization' Medical image analysis, pp. 207-219.
Bischof H, Stern D, Payer C, Urschler M. Integrating spatial configuration into heatmap regression based CNNs for landmark localization. Medical image analysis. 2019;207-219.
Bischof, Horst ; Stern, Darko ; Payer, Christian ; Urschler, Martin. / Integrating spatial configuration into heatmap regression based CNNs for landmark localization. In: Medical image analysis. 2019 ; pp. 207-219.
@article{afbe8409138a4c3791633ee3d0eb135f,
title = "Integrating spatial configuration into heatmap regression based CNNs for landmark localization",
abstract = "In many medical image analysis applications, only a limited amount of training data is available due to the costs of image acquisition and the large manual annotation effort required from experts. Training recent state-of-the-art machine learning methods like convolutional neural networks (CNNs) from small datasets is a challenging task. In this work on anatomical landmark localization, we propose a CNN architecture that learns to split the localization task into two simpler sub-problems, reducing the overall need for large training datasets. Our fully convolutional SpatialConfiguration-Net (SCN) learns this simplification due to multiplying the heatmap predictions of its two components and by training the network in an end-to-end manner. Thus, the SCN dedicates one component to locally accurate but ambiguous candidate predictions, while the other component improves robustness to ambiguities by incorporating the …",
author = "Horst Bischof and Darko Stern and Christian Payer and Martin Urschler",
year = "2019",
language = "deutsch",
pages = "207--219",
journal = "Medical image analysis",
issn = "1361-8415",
publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Integrating spatial configuration into heatmap regression based CNNs for landmark localization

AU - Bischof, Horst

AU - Stern, Darko

AU - Payer, Christian

AU - Urschler, Martin

PY - 2019

Y1 - 2019

N2 - In many medical image analysis applications, only a limited amount of training data is available due to the costs of image acquisition and the large manual annotation effort required from experts. Training recent state-of-the-art machine learning methods like convolutional neural networks (CNNs) from small datasets is a challenging task. In this work on anatomical landmark localization, we propose a CNN architecture that learns to split the localization task into two simpler sub-problems, reducing the overall need for large training datasets. Our fully convolutional SpatialConfiguration-Net (SCN) learns this simplification due to multiplying the heatmap predictions of its two components and by training the network in an end-to-end manner. Thus, the SCN dedicates one component to locally accurate but ambiguous candidate predictions, while the other component improves robustness to ambiguities by incorporating the …

AB - In many medical image analysis applications, only a limited amount of training data is available due to the costs of image acquisition and the large manual annotation effort required from experts. Training recent state-of-the-art machine learning methods like convolutional neural networks (CNNs) from small datasets is a challenging task. In this work on anatomical landmark localization, we propose a CNN architecture that learns to split the localization task into two simpler sub-problems, reducing the overall need for large training datasets. Our fully convolutional SpatialConfiguration-Net (SCN) learns this simplification due to multiplying the heatmap predictions of its two components and by training the network in an end-to-end manner. Thus, the SCN dedicates one component to locally accurate but ambiguous candidate predictions, while the other component improves robustness to ambiguities by incorporating the …

M3 - Artikel

SP - 207

EP - 219

JO - Medical image analysis

JF - Medical image analysis

SN - 1361-8415

ER -