Development and validation of a framework for registration of whole-mount radical prostatectomy histopathology with three-dimensional transrectal ultrasound

Abstract Purpose Artificial intelligence (AI) has the potential to improve diagnostic imaging on multiple levels. To develop and validate these AI-assisted modalities a reliable dataset is of utmost importance. The registration of imaging to pathology is an essential step in creating such a dataset....

Full description

Saved in:
Bibliographic Details
Main Authors: Auke Jager, Marije J. Zwart, Arnoud W. Postema, Daniel L. van den Kroonenberg, Wim Zwart, Harrie P. Beerlage, J. R. Oddens, Massimo Mischi
Format: Article
Language:English
Published: BMC 2025-04-01
Series:BMC Urology
Online Access:https://doi.org/10.1186/s12894-025-01736-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850153516096552960
author Auke Jager
Marije J. Zwart
Arnoud W. Postema
Daniel L. van den Kroonenberg
Wim Zwart
Harrie P. Beerlage
J. R. Oddens
Massimo Mischi
author_facet Auke Jager
Marije J. Zwart
Arnoud W. Postema
Daniel L. van den Kroonenberg
Wim Zwart
Harrie P. Beerlage
J. R. Oddens
Massimo Mischi
author_sort Auke Jager
collection DOAJ
description Abstract Purpose Artificial intelligence (AI) has the potential to improve diagnostic imaging on multiple levels. To develop and validate these AI-assisted modalities a reliable dataset is of utmost importance. The registration of imaging to pathology is an essential step in creating such a dataset. This study presents a comprehensive framework for the registration of 3D transrectal ultrasound (TRUS) to radical prostatectomy specimen (RPS) pathology. Methods The study enrolled patients who underwent 3D TRUS and were scheduled for radical prostatectomy. A four-step process for registering RPS to TRUS was used: image segmentation, 3D reconstruction of RPS pathology, registration and ground truth calculation. Accuracy was assessed using a target-registration error (TRE) based on landmarks visible on both TRUS and pathology. Results 20 Sets of 3D TRUS and RPS pathology were included for analyses. The mean TRE was 3.5 mm, (range: 0.4 to 5.4 mm), with TRE values in the apex-base, left-right and posterior-anterior directions of 2.5 mm, 1.1 mm, and 1.4 mm, respectively. Conclusion The framework proposed in this study accomplishes precise registration between prostate pathology and imaging. The methodologies employed hold the potential for broader application across diverse imaging modalities and other target organs. However, limitations such a small sample size and the need for manual segmentation should be considered when interpreting te results. Future efforts should focus on automating key steps to enhance reproducibility and scalability.
format Article
id doaj-art-b327ef42dfc44fe291852aea8cec19ac
institution OA Journals
issn 1471-2490
language English
publishDate 2025-04-01
publisher BMC
record_format Article
series BMC Urology
spelling doaj-art-b327ef42dfc44fe291852aea8cec19ac2025-08-20T02:25:41ZengBMCBMC Urology1471-24902025-04-0125111010.1186/s12894-025-01736-4Development and validation of a framework for registration of whole-mount radical prostatectomy histopathology with three-dimensional transrectal ultrasoundAuke Jager0Marije J. Zwart1Arnoud W. Postema2Daniel L. van den Kroonenberg3Wim Zwart4Harrie P. Beerlage5J. R. Oddens6Massimo Mischi7Department of Urology, Amsterdam UMC location Vrije Universiteit AmsterdamDepartment of Electrical Engineering, Eindhoven University of TechnologyDepartment of Urology, Leiden University Medical CenterDepartment of Urology, Amsterdam UMC location Vrije Universiteit AmsterdamAngiogenesis AnalyticsDepartment of Urology, Amsterdam UMC location Vrije Universiteit AmsterdamDepartment of Urology, Amsterdam UMC location Vrije Universiteit AmsterdamDepartment of Electrical Engineering, Eindhoven University of TechnologyAbstract Purpose Artificial intelligence (AI) has the potential to improve diagnostic imaging on multiple levels. To develop and validate these AI-assisted modalities a reliable dataset is of utmost importance. The registration of imaging to pathology is an essential step in creating such a dataset. This study presents a comprehensive framework for the registration of 3D transrectal ultrasound (TRUS) to radical prostatectomy specimen (RPS) pathology. Methods The study enrolled patients who underwent 3D TRUS and were scheduled for radical prostatectomy. A four-step process for registering RPS to TRUS was used: image segmentation, 3D reconstruction of RPS pathology, registration and ground truth calculation. Accuracy was assessed using a target-registration error (TRE) based on landmarks visible on both TRUS and pathology. Results 20 Sets of 3D TRUS and RPS pathology were included for analyses. The mean TRE was 3.5 mm, (range: 0.4 to 5.4 mm), with TRE values in the apex-base, left-right and posterior-anterior directions of 2.5 mm, 1.1 mm, and 1.4 mm, respectively. Conclusion The framework proposed in this study accomplishes precise registration between prostate pathology and imaging. The methodologies employed hold the potential for broader application across diverse imaging modalities and other target organs. However, limitations such a small sample size and the need for manual segmentation should be considered when interpreting te results. Future efforts should focus on automating key steps to enhance reproducibility and scalability.https://doi.org/10.1186/s12894-025-01736-4
spellingShingle Auke Jager
Marije J. Zwart
Arnoud W. Postema
Daniel L. van den Kroonenberg
Wim Zwart
Harrie P. Beerlage
J. R. Oddens
Massimo Mischi
Development and validation of a framework for registration of whole-mount radical prostatectomy histopathology with three-dimensional transrectal ultrasound
BMC Urology
title Development and validation of a framework for registration of whole-mount radical prostatectomy histopathology with three-dimensional transrectal ultrasound
title_full Development and validation of a framework for registration of whole-mount radical prostatectomy histopathology with three-dimensional transrectal ultrasound
title_fullStr Development and validation of a framework for registration of whole-mount radical prostatectomy histopathology with three-dimensional transrectal ultrasound
title_full_unstemmed Development and validation of a framework for registration of whole-mount radical prostatectomy histopathology with three-dimensional transrectal ultrasound
title_short Development and validation of a framework for registration of whole-mount radical prostatectomy histopathology with three-dimensional transrectal ultrasound
title_sort development and validation of a framework for registration of whole mount radical prostatectomy histopathology with three dimensional transrectal ultrasound
url https://doi.org/10.1186/s12894-025-01736-4
work_keys_str_mv AT aukejager developmentandvalidationofaframeworkforregistrationofwholemountradicalprostatectomyhistopathologywiththreedimensionaltransrectalultrasound
AT marijejzwart developmentandvalidationofaframeworkforregistrationofwholemountradicalprostatectomyhistopathologywiththreedimensionaltransrectalultrasound
AT arnoudwpostema developmentandvalidationofaframeworkforregistrationofwholemountradicalprostatectomyhistopathologywiththreedimensionaltransrectalultrasound
AT daniellvandenkroonenberg developmentandvalidationofaframeworkforregistrationofwholemountradicalprostatectomyhistopathologywiththreedimensionaltransrectalultrasound
AT wimzwart developmentandvalidationofaframeworkforregistrationofwholemountradicalprostatectomyhistopathologywiththreedimensionaltransrectalultrasound
AT harriepbeerlage developmentandvalidationofaframeworkforregistrationofwholemountradicalprostatectomyhistopathologywiththreedimensionaltransrectalultrasound
AT jroddens developmentandvalidationofaframeworkforregistrationofwholemountradicalprostatectomyhistopathologywiththreedimensionaltransrectalultrasound
AT massimomischi developmentandvalidationofaframeworkforregistrationofwholemountradicalprostatectomyhistopathologywiththreedimensionaltransrectalultrasound