A neural network for glomerulus classification based on histological images of kidney biopsy

Abstract Background Computer-aided diagnosis (CAD) systems based on medical images could support physicians in the decision-making process. During the last decades, researchers have proposed CAD systems in several medical domains achieving promising results. CAD systems play an important role in dig...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Giacomo Donato Cascarano, Francesco Saverio Debitonto, Ruggero Lemma, Antonio Brunetti, Domenico Buongiorno, Irio De Feudis, Andrea Guerriero, Umberto Venere, Silvia Matino, Maria Teresa Rocchetti, Michele Rossini, Francesco Pesce, Loreto Gesualdo, Vitoantonio Bevilacqua
Formato: article
Lenguaje:EN
Publicado: BMC 2021
Materias:
CKD
ANN
Acceso en línea:https://doaj.org/article/db873284506541638164c996738de283
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:db873284506541638164c996738de283
record_format dspace
spelling oai:doaj.org-article:db873284506541638164c996738de2832021-11-08T10:59:21ZA neural network for glomerulus classification based on histological images of kidney biopsy10.1186/s12911-021-01650-31472-6947https://doaj.org/article/db873284506541638164c996738de2832021-11-01T00:00:00Zhttps://doi.org/10.1186/s12911-021-01650-3https://doaj.org/toc/1472-6947Abstract Background Computer-aided diagnosis (CAD) systems based on medical images could support physicians in the decision-making process. During the last decades, researchers have proposed CAD systems in several medical domains achieving promising results. CAD systems play an important role in digital pathology supporting pathologists in analyzing biopsy slides by means of standardized and objective workflows. In the proposed work, we designed and tested a novel CAD system module based on image processing techniques and machine learning, whose objective was to classify the condition affecting renal corpuscles (glomeruli) between sclerotic and non-sclerotic. Such discrimination is useful for the biopsy slides evaluation performed by pathologists. Results We collected 26 digital slides taken from the kidneys of 19 donors with Periodic Acid-Schiff staining. Expert pathologists have conducted the slides preparation, digital acquisition and glomeruli annotations. Before setting the classifiers, we evaluated several feature extraction techniques from the annotated regions. Then, a feature reduction procedure followed by a shallow artificial neural network allowed discriminating between the glomeruli classes. We evaluated the workflow considering an independent dataset (i.e., processing images not used in the training procedure). Ten independent runs of the training algorithm, and evaluation, allowed achieving MCC and Accuracy of 0.95 (± 0.01) and 0.99 (standard deviation < 0.00), respectively. We also obtained good precision (0.9844 ± 0.0111) and recall (0.9310 ± 0.0153). Conclusions Results on the test set confirm that the proposed workflow is consistent and reliable for the investigated domain, and it can support the clinical practice of discriminating the two classes of glomeruli. Analyses on misclassifications show that the involved images are usually affected by staining artefacts or present partial sections due to slice preparation and staining processes. In clinical practice, however, pathologists discard images showing such artefacts.Giacomo Donato CascaranoFrancesco Saverio DebitontoRuggero LemmaAntonio BrunettiDomenico BuongiornoIrio De FeudisAndrea GuerrieroUmberto VenereSilvia MatinoMaria Teresa RocchettiMichele RossiniFrancesco PesceLoreto GesualdoVitoantonio BevilacquaBMCarticleCKDKidneyGlomerulus classificationMorphological featuresTexture featuresANNComputer applications to medicine. Medical informaticsR858-859.7ENBMC Medical Informatics and Decision Making, Vol 21, Iss S1, Pp 1-14 (2021)
institution DOAJ
collection DOAJ
language EN
topic CKD
Kidney
Glomerulus classification
Morphological features
Texture features
ANN
Computer applications to medicine. Medical informatics
R858-859.7
spellingShingle CKD
Kidney
Glomerulus classification
Morphological features
Texture features
ANN
Computer applications to medicine. Medical informatics
R858-859.7
Giacomo Donato Cascarano
Francesco Saverio Debitonto
Ruggero Lemma
Antonio Brunetti
Domenico Buongiorno
Irio De Feudis
Andrea Guerriero
Umberto Venere
Silvia Matino
Maria Teresa Rocchetti
Michele Rossini
Francesco Pesce
Loreto Gesualdo
Vitoantonio Bevilacqua
A neural network for glomerulus classification based on histological images of kidney biopsy
description Abstract Background Computer-aided diagnosis (CAD) systems based on medical images could support physicians in the decision-making process. During the last decades, researchers have proposed CAD systems in several medical domains achieving promising results. CAD systems play an important role in digital pathology supporting pathologists in analyzing biopsy slides by means of standardized and objective workflows. In the proposed work, we designed and tested a novel CAD system module based on image processing techniques and machine learning, whose objective was to classify the condition affecting renal corpuscles (glomeruli) between sclerotic and non-sclerotic. Such discrimination is useful for the biopsy slides evaluation performed by pathologists. Results We collected 26 digital slides taken from the kidneys of 19 donors with Periodic Acid-Schiff staining. Expert pathologists have conducted the slides preparation, digital acquisition and glomeruli annotations. Before setting the classifiers, we evaluated several feature extraction techniques from the annotated regions. Then, a feature reduction procedure followed by a shallow artificial neural network allowed discriminating between the glomeruli classes. We evaluated the workflow considering an independent dataset (i.e., processing images not used in the training procedure). Ten independent runs of the training algorithm, and evaluation, allowed achieving MCC and Accuracy of 0.95 (± 0.01) and 0.99 (standard deviation < 0.00), respectively. We also obtained good precision (0.9844 ± 0.0111) and recall (0.9310 ± 0.0153). Conclusions Results on the test set confirm that the proposed workflow is consistent and reliable for the investigated domain, and it can support the clinical practice of discriminating the two classes of glomeruli. Analyses on misclassifications show that the involved images are usually affected by staining artefacts or present partial sections due to slice preparation and staining processes. In clinical practice, however, pathologists discard images showing such artefacts.
format article
author Giacomo Donato Cascarano
Francesco Saverio Debitonto
Ruggero Lemma
Antonio Brunetti
Domenico Buongiorno
Irio De Feudis
Andrea Guerriero
Umberto Venere
Silvia Matino
Maria Teresa Rocchetti
Michele Rossini
Francesco Pesce
Loreto Gesualdo
Vitoantonio Bevilacqua
author_facet Giacomo Donato Cascarano
Francesco Saverio Debitonto
Ruggero Lemma
Antonio Brunetti
Domenico Buongiorno
Irio De Feudis
Andrea Guerriero
Umberto Venere
Silvia Matino
Maria Teresa Rocchetti
Michele Rossini
Francesco Pesce
Loreto Gesualdo
Vitoantonio Bevilacqua
author_sort Giacomo Donato Cascarano
title A neural network for glomerulus classification based on histological images of kidney biopsy
title_short A neural network for glomerulus classification based on histological images of kidney biopsy
title_full A neural network for glomerulus classification based on histological images of kidney biopsy
title_fullStr A neural network for glomerulus classification based on histological images of kidney biopsy
title_full_unstemmed A neural network for glomerulus classification based on histological images of kidney biopsy
title_sort neural network for glomerulus classification based on histological images of kidney biopsy
publisher BMC
publishDate 2021
url https://doaj.org/article/db873284506541638164c996738de283
work_keys_str_mv AT giacomodonatocascarano aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT francescosaveriodebitonto aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT ruggerolemma aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT antoniobrunetti aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT domenicobuongiorno aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT iriodefeudis aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT andreaguerriero aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT umbertovenere aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT silviamatino aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT mariateresarocchetti aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT michelerossini aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT francescopesce aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT loretogesualdo aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT vitoantoniobevilacqua aneuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT giacomodonatocascarano neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT francescosaveriodebitonto neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT ruggerolemma neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT antoniobrunetti neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT domenicobuongiorno neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT iriodefeudis neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT andreaguerriero neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT umbertovenere neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT silviamatino neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT mariateresarocchetti neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT michelerossini neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT francescopesce neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT loretogesualdo neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
AT vitoantoniobevilacqua neuralnetworkforglomerulusclassificationbasedonhistologicalimagesofkidneybiopsy
_version_ 1718442476700696576