Evaluating Registrations of Serial Sections With Distortions of the Ground Truths

Registration of histological serial sections is a challenging task. Serial sections exhibit distortions and damage from sectioning. Missing information on how the tissue looked before cutting makes a realistic validation of 2D registrations extremely difficult. This work proposes methods for ground-...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Oleg Lobachev, Takuya Funatomi, Alexander Pfaffenroth, Reinhold Forster, Lars Knudsen, Christoph Wrede, Michael Guthe, David Haberthur, Ruslan Hlushchuk, Thomas Salaets, Jaan Toelen, Simone Gaffling, Christian Muhlfeld, Roman Grothausmann
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Registration ground truth histological sections evaluation image processing Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/17af14e0f67645568dde969f9043d622
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:17af14e0f67645568dde969f9043d622
record_format	dspace
spelling	oai:doaj.org-article:17af14e0f67645568dde969f9043d6222021-11-20T00:01:43ZEvaluating Registrations of Serial Sections With Distortions of the Ground Truths2169-353610.1109/ACCESS.2021.3124341https://doaj.org/article/17af14e0f67645568dde969f9043d6222021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9594850/https://doaj.org/toc/2169-3536Registration of histological serial sections is a challenging task. Serial sections exhibit distortions and damage from sectioning. Missing information on how the tissue looked before cutting makes a realistic validation of 2D registrations extremely difficult. This work proposes methods for ground-truth-based evaluation of registrations. Firstly, we present a methodology to generate test data for registrations. We distort an innately registered image stack in the manner similar to the cutting distortion of serial sections. Test cases are generated from existing 3D data sets, thus the ground truth is known. Secondly, our test case generation premises evaluation of the registrations with known ground truths. Our methodology for such an evaluation technique distinguishes this work from other approaches. Both under- and over-registration become evident in our evaluations. We also survey existing validation efforts. We present a full-series evaluation across six different registration methods applied to our distorted 3D data sets of animal lungs. Our distorted and ground truth data sets are made publicly available.Oleg LobachevTakuya FunatomiAlexander PfaffenrothReinhold ForsterLars KnudsenChristoph WredeMichael GutheDavid HaberthurRuslan HlushchukThomas SalaetsJaan ToelenSimone GafflingChristian MuhlfeldRoman GrothausmannIEEEarticleRegistrationground truthhistological sectionsevaluationimage processingElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 152514-152535 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Registration ground truth histological sections evaluation image processing Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Registration ground truth histological sections evaluation image processing Electrical engineering. Electronics. Nuclear engineering TK1-9971 Oleg Lobachev Takuya Funatomi Alexander Pfaffenroth Reinhold Forster Lars Knudsen Christoph Wrede Michael Guthe David Haberthur Ruslan Hlushchuk Thomas Salaets Jaan Toelen Simone Gaffling Christian Muhlfeld Roman Grothausmann Evaluating Registrations of Serial Sections With Distortions of the Ground Truths
description	Registration of histological serial sections is a challenging task. Serial sections exhibit distortions and damage from sectioning. Missing information on how the tissue looked before cutting makes a realistic validation of 2D registrations extremely difficult. This work proposes methods for ground-truth-based evaluation of registrations. Firstly, we present a methodology to generate test data for registrations. We distort an innately registered image stack in the manner similar to the cutting distortion of serial sections. Test cases are generated from existing 3D data sets, thus the ground truth is known. Secondly, our test case generation premises evaluation of the registrations with known ground truths. Our methodology for such an evaluation technique distinguishes this work from other approaches. Both under- and over-registration become evident in our evaluations. We also survey existing validation efforts. We present a full-series evaluation across six different registration methods applied to our distorted 3D data sets of animal lungs. Our distorted and ground truth data sets are made publicly available.
format	article
author	Oleg Lobachev Takuya Funatomi Alexander Pfaffenroth Reinhold Forster Lars Knudsen Christoph Wrede Michael Guthe David Haberthur Ruslan Hlushchuk Thomas Salaets Jaan Toelen Simone Gaffling Christian Muhlfeld Roman Grothausmann
author_facet	Oleg Lobachev Takuya Funatomi Alexander Pfaffenroth Reinhold Forster Lars Knudsen Christoph Wrede Michael Guthe David Haberthur Ruslan Hlushchuk Thomas Salaets Jaan Toelen Simone Gaffling Christian Muhlfeld Roman Grothausmann
author_sort	Oleg Lobachev
title	Evaluating Registrations of Serial Sections With Distortions of the Ground Truths
title_short	Evaluating Registrations of Serial Sections With Distortions of the Ground Truths
title_full	Evaluating Registrations of Serial Sections With Distortions of the Ground Truths
title_fullStr	Evaluating Registrations of Serial Sections With Distortions of the Ground Truths
title_full_unstemmed	Evaluating Registrations of Serial Sections With Distortions of the Ground Truths
title_sort	evaluating registrations of serial sections with distortions of the ground truths
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/17af14e0f67645568dde969f9043d622
work_keys_str_mv	AT oleglobachev evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT takuyafunatomi evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT alexanderpfaffenroth evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT reinholdforster evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT larsknudsen evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT christophwrede evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT michaelguthe evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT davidhaberthur evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT ruslanhlushchuk evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT thomassalaets evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT jaantoelen evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT simonegaffling evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT christianmuhlfeld evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths AT romangrothausmann evaluatingregistrationsofserialsectionswithdistortionsofthegroundtruths
_version_	1718419821201195008

Evaluating Registrations of Serial Sections With Distortions of the Ground Truths

Ejemplares similares