Imagen de Portada

The Brain Tumor Sequence Registration (BraTS-Reg) Challenge: Establishing Correspondence Between Pre-Operative and Follow-up MRI Scans of Diffuse Glioma Patients

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Baheti, Bhakti, Chakrabarty, Satrajit, Akbari, Hamed, Bilello, Michel, Wiestler, Benedikt, Schwarting, Julian, Calabrese, Evan, Rudie, Jeffrey, Abidi, Syed, Mousa, Mina, Villanueva-Meyer, Javier, Fields, Brandon K. K., Kofler, Florian, Shinohara, Russell Takeshi, Iglesias, Juan Eugenio, Mok, Tony C. W., Chung, Albert C. S., Wodzinski, Marek, Jurgas, Artur, Marini, Niccolo, Atzori, Manfredo, Muller, Henning, Grobroehmer, Christoph, Siebert, Hanna, Hansen, Lasse, Heinrich, Mattias P., Canalini, Luca, Klein, Jan, Gerken, Annika, Heldmann, Stefan, Hering, Alessa, Hahn, Horst K., Meng, Mingyuan, Bi, Lei, Feng, Dagan, Kim, Jinman, Zeineldin, Ramy A., Karar, Mohamed E., Mathis-Ullrich, Franziska, Burgert, Oliver, Abderezaei, Javid, Pionteck, Aymeric, Chopra, Agamdeep, Kurt, Mehmet, Yan, Kewei, Yan, Yonghong, Tang, Zhe, Ma, Jianqiang, Nasser, Sahar Almahfouz, Kurian, Nikhil Cherian, Meena, Mohit, Shamsi, Saqib, Sethi, Amit, Tustison, Nicholas J., Avants, Brian B., Cook, Philip, Gee, James C., Tian, Lin, Greer, Hastings, Niethammer, Marc, Hoopes, Andrew, Hoffmann, Malte, Dalca, Adrian V., Christodoulidis, Stergios, Estiene, Theo, Vakalopoulou, Maria, Paragios, Nikos, Marcus, Daniel S., Davatzikos, Christos, Sotiras, Aristeidis, Menze, Bjoern, Bakas, Spyridon, Waldmannstetter, Diana
Formato:	Preprint
Publicado:	2021
Materias:	Image and Video Processing Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

_version_	1866914757616861184
author	Baheti, Bhakti Chakrabarty, Satrajit Akbari, Hamed Bilello, Michel Wiestler, Benedikt Schwarting, Julian Calabrese, Evan Rudie, Jeffrey Abidi, Syed Mousa, Mina Villanueva-Meyer, Javier Fields, Brandon K. K. Kofler, Florian Shinohara, Russell Takeshi Iglesias, Juan Eugenio Mok, Tony C. W. Chung, Albert C. S. Wodzinski, Marek Jurgas, Artur Marini, Niccolo Atzori, Manfredo Muller, Henning Grobroehmer, Christoph Siebert, Hanna Hansen, Lasse Heinrich, Mattias P. Canalini, Luca Klein, Jan Gerken, Annika Heldmann, Stefan Hering, Alessa Hahn, Horst K. Meng, Mingyuan Bi, Lei Feng, Dagan Kim, Jinman Zeineldin, Ramy A. Karar, Mohamed E. Mathis-Ullrich, Franziska Burgert, Oliver Abderezaei, Javid Pionteck, Aymeric Chopra, Agamdeep Kurt, Mehmet Yan, Kewei Yan, Yonghong Tang, Zhe Ma, Jianqiang Nasser, Sahar Almahfouz Kurian, Nikhil Cherian Meena, Mohit Shamsi, Saqib Sethi, Amit Tustison, Nicholas J. Avants, Brian B. Cook, Philip Gee, James C. Tian, Lin Greer, Hastings Niethammer, Marc Hoopes, Andrew Hoffmann, Malte Dalca, Adrian V. Christodoulidis, Stergios Estiene, Theo Vakalopoulou, Maria Paragios, Nikos Marcus, Daniel S. Davatzikos, Christos Sotiras, Aristeidis Menze, Bjoern Bakas, Spyridon Waldmannstetter, Diana
author_facet	Baheti, Bhakti Chakrabarty, Satrajit Akbari, Hamed Bilello, Michel Wiestler, Benedikt Schwarting, Julian Calabrese, Evan Rudie, Jeffrey Abidi, Syed Mousa, Mina Villanueva-Meyer, Javier Fields, Brandon K. K. Kofler, Florian Shinohara, Russell Takeshi Iglesias, Juan Eugenio Mok, Tony C. W. Chung, Albert C. S. Wodzinski, Marek Jurgas, Artur Marini, Niccolo Atzori, Manfredo Muller, Henning Grobroehmer, Christoph Siebert, Hanna Hansen, Lasse Heinrich, Mattias P. Canalini, Luca Klein, Jan Gerken, Annika Heldmann, Stefan Hering, Alessa Hahn, Horst K. Meng, Mingyuan Bi, Lei Feng, Dagan Kim, Jinman Zeineldin, Ramy A. Karar, Mohamed E. Mathis-Ullrich, Franziska Burgert, Oliver Abderezaei, Javid Pionteck, Aymeric Chopra, Agamdeep Kurt, Mehmet Yan, Kewei Yan, Yonghong Tang, Zhe Ma, Jianqiang Nasser, Sahar Almahfouz Kurian, Nikhil Cherian Meena, Mohit Shamsi, Saqib Sethi, Amit Tustison, Nicholas J. Avants, Brian B. Cook, Philip Gee, James C. Tian, Lin Greer, Hastings Niethammer, Marc Hoopes, Andrew Hoffmann, Malte Dalca, Adrian V. Christodoulidis, Stergios Estiene, Theo Vakalopoulou, Maria Paragios, Nikos Marcus, Daniel S. Davatzikos, Christos Sotiras, Aristeidis Menze, Bjoern Bakas, Spyridon Waldmannstetter, Diana
contents	Registration of longitudinal brain MRI scans containing pathologies is challenging due to dramatic changes in tissue appearance. Although there has been progress in developing general-purpose medical image registration techniques, they have not yet attained the requisite precision and reliability for this task, highlighting its inherent complexity. Here we describe the Brain Tumor Sequence Registration (BraTS-Reg) challenge, as the first public benchmark environment for deformable registration algorithms focusing on estimating correspondences between pre-operative and follow-up scans of the same patient diagnosed with a diffuse brain glioma. The BraTS-Reg data comprise de-identified multi-institutional multi-parametric MRI (mpMRI) scans, curated for size and resolution according to a canonical anatomical template, and divided into training, validation, and testing sets. Clinical experts annotated ground truth (GT) landmark points of anatomical locations distinct across the temporal domain. Quantitative evaluation and ranking were based on the Median Euclidean Error (MEE), Robustness, and the determinant of the Jacobian of the displacement field. The top-ranked methodologies yielded similar performance across all evaluation metrics and shared several methodological commonalities, including pre-alignment, deep neural networks, inverse consistency analysis, and test-time instance optimization per-case basis as a post-processing step. The top-ranked method attained the MEE at or below that of the inter-rater variability for approximately 60% of the evaluated landmarks, underscoring the scope for further accuracy and robustness improvements, especially relative to human experts. The aim of BraTS-Reg is to continue to serve as an active resource for research, with the data and online evaluation tools accessible at https://bratsreg.github.io/.
format	Preprint
id	arxiv_https___arxiv_org_abs_2112_06979
institution	arXiv
publishDate	2021
record_format	arxiv
spellingShingle	The Brain Tumor Sequence Registration (BraTS-Reg) Challenge: Establishing Correspondence Between Pre-Operative and Follow-up MRI Scans of Diffuse Glioma Patients Baheti, Bhakti Chakrabarty, Satrajit Akbari, Hamed Bilello, Michel Wiestler, Benedikt Schwarting, Julian Calabrese, Evan Rudie, Jeffrey Abidi, Syed Mousa, Mina Villanueva-Meyer, Javier Fields, Brandon K. K. Kofler, Florian Shinohara, Russell Takeshi Iglesias, Juan Eugenio Mok, Tony C. W. Chung, Albert C. S. Wodzinski, Marek Jurgas, Artur Marini, Niccolo Atzori, Manfredo Muller, Henning Grobroehmer, Christoph Siebert, Hanna Hansen, Lasse Heinrich, Mattias P. Canalini, Luca Klein, Jan Gerken, Annika Heldmann, Stefan Hering, Alessa Hahn, Horst K. Meng, Mingyuan Bi, Lei Feng, Dagan Kim, Jinman Zeineldin, Ramy A. Karar, Mohamed E. Mathis-Ullrich, Franziska Burgert, Oliver Abderezaei, Javid Pionteck, Aymeric Chopra, Agamdeep Kurt, Mehmet Yan, Kewei Yan, Yonghong Tang, Zhe Ma, Jianqiang Nasser, Sahar Almahfouz Kurian, Nikhil Cherian Meena, Mohit Shamsi, Saqib Sethi, Amit Tustison, Nicholas J. Avants, Brian B. Cook, Philip Gee, James C. Tian, Lin Greer, Hastings Niethammer, Marc Hoopes, Andrew Hoffmann, Malte Dalca, Adrian V. Christodoulidis, Stergios Estiene, Theo Vakalopoulou, Maria Paragios, Nikos Marcus, Daniel S. Davatzikos, Christos Sotiras, Aristeidis Menze, Bjoern Bakas, Spyridon Waldmannstetter, Diana Image and Video Processing Computer Vision and Pattern Recognition Registration of longitudinal brain MRI scans containing pathologies is challenging due to dramatic changes in tissue appearance. Although there has been progress in developing general-purpose medical image registration techniques, they have not yet attained the requisite precision and reliability for this task, highlighting its inherent complexity. Here we describe the Brain Tumor Sequence Registration (BraTS-Reg) challenge, as the first public benchmark environment for deformable registration algorithms focusing on estimating correspondences between pre-operative and follow-up scans of the same patient diagnosed with a diffuse brain glioma. The BraTS-Reg data comprise de-identified multi-institutional multi-parametric MRI (mpMRI) scans, curated for size and resolution according to a canonical anatomical template, and divided into training, validation, and testing sets. Clinical experts annotated ground truth (GT) landmark points of anatomical locations distinct across the temporal domain. Quantitative evaluation and ranking were based on the Median Euclidean Error (MEE), Robustness, and the determinant of the Jacobian of the displacement field. The top-ranked methodologies yielded similar performance across all evaluation metrics and shared several methodological commonalities, including pre-alignment, deep neural networks, inverse consistency analysis, and test-time instance optimization per-case basis as a post-processing step. The top-ranked method attained the MEE at or below that of the inter-rater variability for approximately 60% of the evaluated landmarks, underscoring the scope for further accuracy and robustness improvements, especially relative to human experts. The aim of BraTS-Reg is to continue to serve as an active resource for research, with the data and online evaluation tools accessible at https://bratsreg.github.io/.
title	The Brain Tumor Sequence Registration (BraTS-Reg) Challenge: Establishing Correspondence Between Pre-Operative and Follow-up MRI Scans of Diffuse Glioma Patients
topic	Image and Video Processing Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2112.06979