Congo red fluorescence enhances digital pathology workflow in cardiac amyloidosis

Abstract Despite advances in non-invasive methods, endomyocardial biopsy (EMB) remains essential for definitive diagnosis of amyloidosis in many cases. Traditionally, Congo red birefringence (CRB) has been crucial for identifying amyloid deposits but is challenging to capture digitally. Emerging flu...

Full description

Saved in:
Bibliographic Details
Main Authors: Giorgio Cazzaniga, Monica De Gaspari, Vincenzo L’Imperio, Carlo Beretta, Angela Greco, Stefania Rizzo, Cristina Basso, Fabio Pagni
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-07157-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333074626609152
author Giorgio Cazzaniga
Monica De Gaspari
Vincenzo L’Imperio
Carlo Beretta
Angela Greco
Stefania Rizzo
Cristina Basso
Fabio Pagni
author_facet Giorgio Cazzaniga
Monica De Gaspari
Vincenzo L’Imperio
Carlo Beretta
Angela Greco
Stefania Rizzo
Cristina Basso
Fabio Pagni
author_sort Giorgio Cazzaniga
collection DOAJ
description Abstract Despite advances in non-invasive methods, endomyocardial biopsy (EMB) remains essential for definitive diagnosis of amyloidosis in many cases. Traditionally, Congo red birefringence (CRB) has been crucial for identifying amyloid deposits but is challenging to capture digitally. Emerging fluorescent Congo red imaging (CRF) overcomes this problem and holds promise in image analysis and AI applications. The diagnostic performance of CRF on virtual slides was evaluated in a cohort of EMB and autopsy cases. The feasibility of developing AI algorithms applicable to centers lacking a fluorescence scanner was investigated leveraging a computational pipeline that enables fluorescence outcome visualization in brightfield. The study analyzed 43 digital myocardial slides stained with Congo Red, acquired using a fluorescent Texas Red filter. Among these, 28 (65%) were diagnosed with amyloidosis, with complete diagnostic agreement with original diagnosis. AI achieved an AUC-ROC of 0.87, 0.86 and 0.79 on the training, validation and test set, respectively, in tile-level classification for amyloidosis positivity and IoU and Dice scores indicating partial but reasonable overlap between predictions and ground truth in amyloid segmentation. The study underscores CRF’s transformative impact on virtual slides and AI integration for diagnosing cardiac amyloidosis, showcasing high reliability and diagnostic accuracy. These advancements promise a more quantitative and precise approach, facilitating the histological study of the disease in the digital transition era of pathology labs.
format Article
id doaj-art-7b254b5f214b48c09e2fde95e2a4b2d1
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-7b254b5f214b48c09e2fde95e2a4b2d12025-08-20T03:46:00ZengNature PortfolioScientific Reports2045-23222025-07-0115111210.1038/s41598-025-07157-5Congo red fluorescence enhances digital pathology workflow in cardiac amyloidosisGiorgio Cazzaniga0Monica De Gaspari1Vincenzo L’Imperio2Carlo Beretta3Angela Greco4Stefania Rizzo5Cristina Basso6Fabio Pagni7Pathology, IRCCS Fondazione San Gerardo dei TintoriCardiovascular Pathology Unit, Azienda Ospedaliera, Department of Cardiac, Thoracic, and Vascular Sciences and Public Health, University of PaduaPathology, IRCCS Fondazione San Gerardo dei TintoriDepartment of Medicine and Surgery, University of Milano-BicoccaPathology, IRCCS Fondazione San Gerardo dei TintoriCardiovascular Pathology Unit, Azienda Ospedaliera, Department of Cardiac, Thoracic, and Vascular Sciences and Public Health, University of PaduaCardiovascular Pathology Unit, Azienda Ospedaliera, Department of Cardiac, Thoracic, and Vascular Sciences and Public Health, University of PaduaPathology, IRCCS Fondazione San Gerardo dei TintoriAbstract Despite advances in non-invasive methods, endomyocardial biopsy (EMB) remains essential for definitive diagnosis of amyloidosis in many cases. Traditionally, Congo red birefringence (CRB) has been crucial for identifying amyloid deposits but is challenging to capture digitally. Emerging fluorescent Congo red imaging (CRF) overcomes this problem and holds promise in image analysis and AI applications. The diagnostic performance of CRF on virtual slides was evaluated in a cohort of EMB and autopsy cases. The feasibility of developing AI algorithms applicable to centers lacking a fluorescence scanner was investigated leveraging a computational pipeline that enables fluorescence outcome visualization in brightfield. The study analyzed 43 digital myocardial slides stained with Congo Red, acquired using a fluorescent Texas Red filter. Among these, 28 (65%) were diagnosed with amyloidosis, with complete diagnostic agreement with original diagnosis. AI achieved an AUC-ROC of 0.87, 0.86 and 0.79 on the training, validation and test set, respectively, in tile-level classification for amyloidosis positivity and IoU and Dice scores indicating partial but reasonable overlap between predictions and ground truth in amyloid segmentation. The study underscores CRF’s transformative impact on virtual slides and AI integration for diagnosing cardiac amyloidosis, showcasing high reliability and diagnostic accuracy. These advancements promise a more quantitative and precise approach, facilitating the histological study of the disease in the digital transition era of pathology labs.https://doi.org/10.1038/s41598-025-07157-5Digital pathologyCardiac amyloidosisArtificial intelligenceCongo redCardiovascular pathology
spellingShingle Giorgio Cazzaniga
Monica De Gaspari
Vincenzo L’Imperio
Carlo Beretta
Angela Greco
Stefania Rizzo
Cristina Basso
Fabio Pagni
Congo red fluorescence enhances digital pathology workflow in cardiac amyloidosis
Scientific Reports
Digital pathology
Cardiac amyloidosis
Artificial intelligence
Congo red
Cardiovascular pathology
title Congo red fluorescence enhances digital pathology workflow in cardiac amyloidosis
title_full Congo red fluorescence enhances digital pathology workflow in cardiac amyloidosis
title_fullStr Congo red fluorescence enhances digital pathology workflow in cardiac amyloidosis
title_full_unstemmed Congo red fluorescence enhances digital pathology workflow in cardiac amyloidosis
title_short Congo red fluorescence enhances digital pathology workflow in cardiac amyloidosis
title_sort congo red fluorescence enhances digital pathology workflow in cardiac amyloidosis
topic Digital pathology
Cardiac amyloidosis
Artificial intelligence
Congo red
Cardiovascular pathology
url https://doi.org/10.1038/s41598-025-07157-5
work_keys_str_mv AT giorgiocazzaniga congoredfluorescenceenhancesdigitalpathologyworkflowincardiacamyloidosis
AT monicadegaspari congoredfluorescenceenhancesdigitalpathologyworkflowincardiacamyloidosis
AT vincenzolimperio congoredfluorescenceenhancesdigitalpathologyworkflowincardiacamyloidosis
AT carloberetta congoredfluorescenceenhancesdigitalpathologyworkflowincardiacamyloidosis
AT angelagreco congoredfluorescenceenhancesdigitalpathologyworkflowincardiacamyloidosis
AT stefaniarizzo congoredfluorescenceenhancesdigitalpathologyworkflowincardiacamyloidosis
AT cristinabasso congoredfluorescenceenhancesdigitalpathologyworkflowincardiacamyloidosis
AT fabiopagni congoredfluorescenceenhancesdigitalpathologyworkflowincardiacamyloidosis