Framing image registration as a landmark detection problem for label-noise-aware task representation (HitR)

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Waldmannstetter, Diana, Ezhov, Ivan, Wiestler, Benedikt, Campi, Francesco, Kukuljan, Ivan, Ehrlich, Stefan, Vinayahalingam, Shankeeth, Baheti, Bhakti, Chakrabarty, Satrajit, Baid, Ujjwal, Bakas, Spyridon, Schwarting, Julian, Metz, Marie, Kirschke, Jan S., Rueckert, Daniel, Heckemann, Rolf A., Piraud, Marie, Menze, Bjoern H., Kofler, Florian
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929404749283328
author Waldmannstetter, Diana
Ezhov, Ivan
Wiestler, Benedikt
Campi, Francesco
Kukuljan, Ivan
Ehrlich, Stefan
Vinayahalingam, Shankeeth
Baheti, Bhakti
Chakrabarty, Satrajit
Baid, Ujjwal
Bakas, Spyridon
Schwarting, Julian
Metz, Marie
Kirschke, Jan S.
Rueckert, Daniel
Heckemann, Rolf A.
Piraud, Marie
Menze, Bjoern H.
Kofler, Florian
author_facet Waldmannstetter, Diana
Ezhov, Ivan
Wiestler, Benedikt
Campi, Francesco
Kukuljan, Ivan
Ehrlich, Stefan
Vinayahalingam, Shankeeth
Baheti, Bhakti
Chakrabarty, Satrajit
Baid, Ujjwal
Bakas, Spyridon
Schwarting, Julian
Metz, Marie
Kirschke, Jan S.
Rueckert, Daniel
Heckemann, Rolf A.
Piraud, Marie
Menze, Bjoern H.
Kofler, Florian
contents Accurate image registration is pivotal in biomedical image analysis, where selecting suitable registration algorithms demands careful consideration. While numerous algorithms are available, the evaluation metrics to assess their performance have remained relatively static. This study addresses this challenge by introducing a novel evaluation metric termed Landmark Hit Rate (HitR), which focuses on the clinical relevance of image registration accuracy. Unlike traditional metrics such as Target Registration Error, which emphasize subresolution differences, HitR considers whether registration algorithms successfully position landmarks within defined confidence zones. This paradigm shift acknowledges the inherent annotation noise in medical images, allowing for more meaningful assessments. To equip HitR with label-noise-awareness, we propose defining these confidence zones based on an Inter-rater Variance analysis. Consequently, hit rate curves are computed for varying landmark zone sizes, enabling performance measurement for a task-specific level of accuracy. Our approach offers a more realistic and meaningful assessment of image registration algorithms, reflecting their suitability for clinical and biomedical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2308_01318
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Framing image registration as a landmark detection problem for label-noise-aware task representation (HitR)
Waldmannstetter, Diana
Ezhov, Ivan
Wiestler, Benedikt
Campi, Francesco
Kukuljan, Ivan
Ehrlich, Stefan
Vinayahalingam, Shankeeth
Baheti, Bhakti
Chakrabarty, Satrajit
Baid, Ujjwal
Bakas, Spyridon
Schwarting, Julian
Metz, Marie
Kirschke, Jan S.
Rueckert, Daniel
Heckemann, Rolf A.
Piraud, Marie
Menze, Bjoern H.
Kofler, Florian
Image and Video Processing
Computer Vision and Pattern Recognition
Medical Physics
Accurate image registration is pivotal in biomedical image analysis, where selecting suitable registration algorithms demands careful consideration. While numerous algorithms are available, the evaluation metrics to assess their performance have remained relatively static. This study addresses this challenge by introducing a novel evaluation metric termed Landmark Hit Rate (HitR), which focuses on the clinical relevance of image registration accuracy. Unlike traditional metrics such as Target Registration Error, which emphasize subresolution differences, HitR considers whether registration algorithms successfully position landmarks within defined confidence zones. This paradigm shift acknowledges the inherent annotation noise in medical images, allowing for more meaningful assessments. To equip HitR with label-noise-awareness, we propose defining these confidence zones based on an Inter-rater Variance analysis. Consequently, hit rate curves are computed for varying landmark zone sizes, enabling performance measurement for a task-specific level of accuracy. Our approach offers a more realistic and meaningful assessment of image registration algorithms, reflecting their suitability for clinical and biomedical applications.
title Framing image registration as a landmark detection problem for label-noise-aware task representation (HitR)
topic Image and Video Processing
Computer Vision and Pattern Recognition
Medical Physics
url https://arxiv.org/abs/2308.01318