Cargando…

Radiologist-Trained and -Tested (R2.2.4) Deep Learning Models for Identifying Anatomical Landmarks in Chest CT

(1) Background: Optimal anatomic coverage is important for radiation-dose optimization. We trained and tested (R2.2.4) two (R3-2) deep learning (DL) algorithms on a machine vision tool library platform (Cognex Vision Pro Deep Learning software) to recognize anatomic landmarks and classify chest CT a...

Descripción completa

Detalles Bibliográficos
Autores principales: Kaviani, Parisa, Bizzo, Bernardo C., Digumarthy, Subba R., Dasegowda, Giridhar, Karout, Lina, Hillis, James, Neumark, Nir, Kalra, Mannudeep K., Dreyer, Keith J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9407000/
https://www.ncbi.nlm.nih.gov/pubmed/36010194
http://dx.doi.org/10.3390/diagnostics12081844
_version_ 1784774258979766272
author Kaviani, Parisa
Bizzo, Bernardo C.
Digumarthy, Subba R.
Dasegowda, Giridhar
Karout, Lina
Hillis, James
Neumark, Nir
Kalra, Mannudeep K.
Dreyer, Keith J.
author_facet Kaviani, Parisa
Bizzo, Bernardo C.
Digumarthy, Subba R.
Dasegowda, Giridhar
Karout, Lina
Hillis, James
Neumark, Nir
Kalra, Mannudeep K.
Dreyer, Keith J.
author_sort Kaviani, Parisa
collection PubMed
description (1) Background: Optimal anatomic coverage is important for radiation-dose optimization. We trained and tested (R2.2.4) two (R3-2) deep learning (DL) algorithms on a machine vision tool library platform (Cognex Vision Pro Deep Learning software) to recognize anatomic landmarks and classify chest CT as those with optimum, under-scanned, or over-scanned scan length. (2) Methods: To test our hypothesis, we performed a study with 428 consecutive chest CT examinations (mean age 70 ± 14 years; male:female 190:238) performed at one of the four hospitals. CT examinations from two hospitals were used to train the DL classification algorithms to identify lung apices and bases. The developed algorithms were then tested on the data from the remaining two hospitals. For each CT, we recorded the scan lengths above and below the lung apices and bases. Model performance was assessed with receiver operating characteristics (ROC) analysis. (3) Results: The two DL models for lung apex and bases had high sensitivity, specificity, accuracy, and areas under the curve (AUC) for identifying under-scanning (100%, 99%, 99%, and 0.999 (95% CI 0.996–1.000)) and over-scanning (99%, 99%, 99%, and 0.998 (95%CI 0.992–1.000)). (4) Conclusions: Our DL models can accurately identify markers for missing anatomic coverage and over-scanning in chest CTs.
format Online
Article
Text
id pubmed-9407000
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-94070002022-08-26 Radiologist-Trained and -Tested (R2.2.4) Deep Learning Models for Identifying Anatomical Landmarks in Chest CT Kaviani, Parisa Bizzo, Bernardo C. Digumarthy, Subba R. Dasegowda, Giridhar Karout, Lina Hillis, James Neumark, Nir Kalra, Mannudeep K. Dreyer, Keith J. Diagnostics (Basel) Article (1) Background: Optimal anatomic coverage is important for radiation-dose optimization. We trained and tested (R2.2.4) two (R3-2) deep learning (DL) algorithms on a machine vision tool library platform (Cognex Vision Pro Deep Learning software) to recognize anatomic landmarks and classify chest CT as those with optimum, under-scanned, or over-scanned scan length. (2) Methods: To test our hypothesis, we performed a study with 428 consecutive chest CT examinations (mean age 70 ± 14 years; male:female 190:238) performed at one of the four hospitals. CT examinations from two hospitals were used to train the DL classification algorithms to identify lung apices and bases. The developed algorithms were then tested on the data from the remaining two hospitals. For each CT, we recorded the scan lengths above and below the lung apices and bases. Model performance was assessed with receiver operating characteristics (ROC) analysis. (3) Results: The two DL models for lung apex and bases had high sensitivity, specificity, accuracy, and areas under the curve (AUC) for identifying under-scanning (100%, 99%, 99%, and 0.999 (95% CI 0.996–1.000)) and over-scanning (99%, 99%, 99%, and 0.998 (95%CI 0.992–1.000)). (4) Conclusions: Our DL models can accurately identify markers for missing anatomic coverage and over-scanning in chest CTs. MDPI 2022-07-30 /pmc/articles/PMC9407000/ /pubmed/36010194 http://dx.doi.org/10.3390/diagnostics12081844 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kaviani, Parisa
Bizzo, Bernardo C.
Digumarthy, Subba R.
Dasegowda, Giridhar
Karout, Lina
Hillis, James
Neumark, Nir
Kalra, Mannudeep K.
Dreyer, Keith J.
Radiologist-Trained and -Tested (R2.2.4) Deep Learning Models for Identifying Anatomical Landmarks in Chest CT
title Radiologist-Trained and -Tested (R2.2.4) Deep Learning Models for Identifying Anatomical Landmarks in Chest CT
title_full Radiologist-Trained and -Tested (R2.2.4) Deep Learning Models for Identifying Anatomical Landmarks in Chest CT
title_fullStr Radiologist-Trained and -Tested (R2.2.4) Deep Learning Models for Identifying Anatomical Landmarks in Chest CT
title_full_unstemmed Radiologist-Trained and -Tested (R2.2.4) Deep Learning Models for Identifying Anatomical Landmarks in Chest CT
title_short Radiologist-Trained and -Tested (R2.2.4) Deep Learning Models for Identifying Anatomical Landmarks in Chest CT
title_sort radiologist-trained and -tested (r2.2.4) deep learning models for identifying anatomical landmarks in chest ct
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9407000/
https://www.ncbi.nlm.nih.gov/pubmed/36010194
http://dx.doi.org/10.3390/diagnostics12081844
work_keys_str_mv AT kavianiparisa radiologisttrainedandtestedr224deeplearningmodelsforidentifyinganatomicallandmarksinchestct
AT bizzobernardoc radiologisttrainedandtestedr224deeplearningmodelsforidentifyinganatomicallandmarksinchestct
AT digumarthysubbar radiologisttrainedandtestedr224deeplearningmodelsforidentifyinganatomicallandmarksinchestct
AT dasegowdagiridhar radiologisttrainedandtestedr224deeplearningmodelsforidentifyinganatomicallandmarksinchestct
AT karoutlina radiologisttrainedandtestedr224deeplearningmodelsforidentifyinganatomicallandmarksinchestct
AT hillisjames radiologisttrainedandtestedr224deeplearningmodelsforidentifyinganatomicallandmarksinchestct
AT neumarknir radiologisttrainedandtestedr224deeplearningmodelsforidentifyinganatomicallandmarksinchestct
AT kalramannudeepk radiologisttrainedandtestedr224deeplearningmodelsforidentifyinganatomicallandmarksinchestct
AT dreyerkeithj radiologisttrainedandtestedr224deeplearningmodelsforidentifyinganatomicallandmarksinchestct