Cargando…

Medical decision support system using weakly-labeled lung CT scans

PURPOSE: Determination and development of an effective set of models leveraging Artificial Intelligence techniques to generate a system able to support clinical practitioners working with COVID-19 patients. It involves a pipeline including classification, lung and lesion segmentation, as well as les...

Descripción completa

Detalles Bibliográficos
Autores principales: Murillo-González, Alejandro, González, David, Jaramillo, Laura, Galeano, Carlos, Tavera, Fabby, Mejía, Marcia, Hernández, Alejandro, Rivera, David Restrepo, Paniagua, J. G., Ariza-Jiménez, Leandro, Garcés Echeverri, José Julián, Diaz León, Christian Andrés, Serna-Higuita, Diana Lucia, Barrios, Wayner, Arrázola, Wiston, Mejía, Miguel Ángel, Arango, Sebastián, Marín Ramírez, Daniela, Salinas-Miranda, Emmanuel, Quintero, O. L.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9554434/
https://www.ncbi.nlm.nih.gov/pubmed/36248019
http://dx.doi.org/10.3389/fmedt.2022.980735
_version_ 1784806695067713536
author Murillo-González, Alejandro
González, David
Jaramillo, Laura
Galeano, Carlos
Tavera, Fabby
Mejía, Marcia
Hernández, Alejandro
Rivera, David Restrepo
Paniagua, J. G.
Ariza-Jiménez, Leandro
Garcés Echeverri, José Julián
Diaz León, Christian Andrés
Serna-Higuita, Diana Lucia
Barrios, Wayner
Arrázola, Wiston
Mejía, Miguel Ángel
Arango, Sebastián
Marín Ramírez, Daniela
Salinas-Miranda, Emmanuel
Quintero, O. L.
author_facet Murillo-González, Alejandro
González, David
Jaramillo, Laura
Galeano, Carlos
Tavera, Fabby
Mejía, Marcia
Hernández, Alejandro
Rivera, David Restrepo
Paniagua, J. G.
Ariza-Jiménez, Leandro
Garcés Echeverri, José Julián
Diaz León, Christian Andrés
Serna-Higuita, Diana Lucia
Barrios, Wayner
Arrázola, Wiston
Mejía, Miguel Ángel
Arango, Sebastián
Marín Ramírez, Daniela
Salinas-Miranda, Emmanuel
Quintero, O. L.
author_sort Murillo-González, Alejandro
collection PubMed
description PURPOSE: Determination and development of an effective set of models leveraging Artificial Intelligence techniques to generate a system able to support clinical practitioners working with COVID-19 patients. It involves a pipeline including classification, lung and lesion segmentation, as well as lesion quantification of axial lung CT studies. APPROACH: A deep neural network architecture based on DenseNet is introduced for the classification of weakly-labeled, variable-sized (and possibly sparse) axial lung CT scans. The models are trained and tested on aggregated, publicly available data sets with over 10 categories. To further assess the models, a data set was collected from multiple medical institutions in Colombia, which includes healthy, COVID-19 and patients with other diseases. It is composed of 1,322 CT studies from a diverse set of CT machines and institutions that make over 550,000 slices. Each CT study was labeled based on a clinical test, and no per-slice annotation took place. This enabled a classification into Normal vs. Abnormal patients, and for those that were considered abnormal, an extra classification step into Abnormal (other diseases) vs. COVID-19. Additionally, the pipeline features a methodology to segment and quantify lesions of COVID-19 patients on the complete CT study, enabling easier localization and progress tracking. Moreover, multiple ablation studies were performed to appropriately assess the elements composing the classification pipeline. RESULTS: The best performing lung CT study classification models achieved 0.83 accuracy, 0.79 sensitivity, 0.87 specificity, 0.82 F1 score and 0.85 precision for the Normal vs. Abnormal task. For the Abnormal vs COVID-19 task, the model obtained 0.86 accuracy, 0.81 sensitivity, 0.91 specificity, 0.84 F1 score and 0.88 precision. The ablation studies showed that using the complete CT study in the pipeline resulted in greater classification performance, restating that relevant COVID-19 patterns cannot be ignored towards the top and bottom of the lung volume. DISCUSSION: The lung CT classification architecture introduced has shown that it can handle weakly-labeled, variable-sized and possibly sparse axial lung studies, reducing the need for expert annotations at a per-slice level. CONCLUSIONS: This work presents a working methodology that can guide the development of decision support systems for clinical reasoning in future interventionist or prospective studies.
format Online
Article
Text
id pubmed-9554434
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-95544342022-10-13 Medical decision support system using weakly-labeled lung CT scans Murillo-González, Alejandro González, David Jaramillo, Laura Galeano, Carlos Tavera, Fabby Mejía, Marcia Hernández, Alejandro Rivera, David Restrepo Paniagua, J. G. Ariza-Jiménez, Leandro Garcés Echeverri, José Julián Diaz León, Christian Andrés Serna-Higuita, Diana Lucia Barrios, Wayner Arrázola, Wiston Mejía, Miguel Ángel Arango, Sebastián Marín Ramírez, Daniela Salinas-Miranda, Emmanuel Quintero, O. L. Front Med Technol Medical Technology PURPOSE: Determination and development of an effective set of models leveraging Artificial Intelligence techniques to generate a system able to support clinical practitioners working with COVID-19 patients. It involves a pipeline including classification, lung and lesion segmentation, as well as lesion quantification of axial lung CT studies. APPROACH: A deep neural network architecture based on DenseNet is introduced for the classification of weakly-labeled, variable-sized (and possibly sparse) axial lung CT scans. The models are trained and tested on aggregated, publicly available data sets with over 10 categories. To further assess the models, a data set was collected from multiple medical institutions in Colombia, which includes healthy, COVID-19 and patients with other diseases. It is composed of 1,322 CT studies from a diverse set of CT machines and institutions that make over 550,000 slices. Each CT study was labeled based on a clinical test, and no per-slice annotation took place. This enabled a classification into Normal vs. Abnormal patients, and for those that were considered abnormal, an extra classification step into Abnormal (other diseases) vs. COVID-19. Additionally, the pipeline features a methodology to segment and quantify lesions of COVID-19 patients on the complete CT study, enabling easier localization and progress tracking. Moreover, multiple ablation studies were performed to appropriately assess the elements composing the classification pipeline. RESULTS: The best performing lung CT study classification models achieved 0.83 accuracy, 0.79 sensitivity, 0.87 specificity, 0.82 F1 score and 0.85 precision for the Normal vs. Abnormal task. For the Abnormal vs COVID-19 task, the model obtained 0.86 accuracy, 0.81 sensitivity, 0.91 specificity, 0.84 F1 score and 0.88 precision. The ablation studies showed that using the complete CT study in the pipeline resulted in greater classification performance, restating that relevant COVID-19 patterns cannot be ignored towards the top and bottom of the lung volume. DISCUSSION: The lung CT classification architecture introduced has shown that it can handle weakly-labeled, variable-sized and possibly sparse axial lung studies, reducing the need for expert annotations at a per-slice level. CONCLUSIONS: This work presents a working methodology that can guide the development of decision support systems for clinical reasoning in future interventionist or prospective studies. Frontiers Media S.A. 2022-09-28 /pmc/articles/PMC9554434/ /pubmed/36248019 http://dx.doi.org/10.3389/fmedt.2022.980735 Text en © 2022 Murillo-González, González, Jaramillo, Galeano, Tavera, Mejía, Hernández, Rivera, Paniagua, Ariza-Jiménez, Garcés Echeverri, Diaz León, Serna-Higuita, Barrios, Arrázola, Mejía, Arango, Marín Ramírez, Salinas-Miranda and Quintero. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (https://creativecommons.org/licenses/by/4.0/) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Medical Technology
Murillo-González, Alejandro
González, David
Jaramillo, Laura
Galeano, Carlos
Tavera, Fabby
Mejía, Marcia
Hernández, Alejandro
Rivera, David Restrepo
Paniagua, J. G.
Ariza-Jiménez, Leandro
Garcés Echeverri, José Julián
Diaz León, Christian Andrés
Serna-Higuita, Diana Lucia
Barrios, Wayner
Arrázola, Wiston
Mejía, Miguel Ángel
Arango, Sebastián
Marín Ramírez, Daniela
Salinas-Miranda, Emmanuel
Quintero, O. L.
Medical decision support system using weakly-labeled lung CT scans
title Medical decision support system using weakly-labeled lung CT scans
title_full Medical decision support system using weakly-labeled lung CT scans
title_fullStr Medical decision support system using weakly-labeled lung CT scans
title_full_unstemmed Medical decision support system using weakly-labeled lung CT scans
title_short Medical decision support system using weakly-labeled lung CT scans
title_sort medical decision support system using weakly-labeled lung ct scans
topic Medical Technology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9554434/
https://www.ncbi.nlm.nih.gov/pubmed/36248019
http://dx.doi.org/10.3389/fmedt.2022.980735
work_keys_str_mv AT murillogonzalezalejandro medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT gonzalezdavid medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT jaramillolaura medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT galeanocarlos medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT taverafabby medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT mejiamarcia medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT hernandezalejandro medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT riveradavidrestrepo medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT paniaguajg medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT arizajimenezleandro medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT garcesecheverrijosejulian medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT diazleonchristianandres medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT sernahiguitadianalucia medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT barrioswayner medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT arrazolawiston medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT mejiamiguelangel medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT arangosebastian medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT marinramirezdaniela medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT salinasmirandaemmanuel medicaldecisionsupportsystemusingweaklylabeledlungctscans
AT quinterool medicaldecisionsupportsystemusingweaklylabeledlungctscans