Cargando…

Improved Repeatability of Mouse Tibia Volume Segmentation in Murine Myelofibrosis Model Using Deep Learning

A murine model of myelofibrosis in tibia was used in a co-clinical trial to evaluate segmentation methods for application of image-based biomarkers to assess disease status. The dataset (32 mice with 157 3D MRI scans including 49 test–retest pairs scanned on consecutive days) was split into approxim...

Descripción completa

Detalles Bibliográficos
Autores principales: Kushwaha, Aman, Mourad, Rami F., Heist, Kevin, Tariq, Humera, Chan, Heang-Ping, Ross, Brian D., Chenevert, Thomas L., Malyarenko, Dariya, Hadjiiski, Lubomir M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10037585/
https://www.ncbi.nlm.nih.gov/pubmed/36961007
http://dx.doi.org/10.3390/tomography9020048
_version_ 1784911912622882816
author Kushwaha, Aman
Mourad, Rami F.
Heist, Kevin
Tariq, Humera
Chan, Heang-Ping
Ross, Brian D.
Chenevert, Thomas L.
Malyarenko, Dariya
Hadjiiski, Lubomir M.
author_facet Kushwaha, Aman
Mourad, Rami F.
Heist, Kevin
Tariq, Humera
Chan, Heang-Ping
Ross, Brian D.
Chenevert, Thomas L.
Malyarenko, Dariya
Hadjiiski, Lubomir M.
author_sort Kushwaha, Aman
collection PubMed
description A murine model of myelofibrosis in tibia was used in a co-clinical trial to evaluate segmentation methods for application of image-based biomarkers to assess disease status. The dataset (32 mice with 157 3D MRI scans including 49 test–retest pairs scanned on consecutive days) was split into approximately 70% training, 10% validation, and 20% test subsets. Two expert annotators (EA1 and EA2) performed manual segmentations of the mouse tibia (EA1: all data; EA2: test and validation). Attention U-net (A-U-net) model performance was assessed for accuracy with respect to EA1 reference using the average Jaccard index (AJI), volume intersection ratio (AVI), volume error (AVE), and Hausdorff distance (AHD) for four training scenarios: full training, two half-splits, and a single-mouse subsets. The repeatability of computer versus expert segmentations for tibia volume of test–retest pairs was assessed by within-subject coefficient of variance (%wCV). A-U-net models trained on full and half-split training sets achieved similar average accuracy (with respect to EA1 annotations) for test set: AJI = 83–84%, AVI = 89–90%, AVE = 2–3%, and AHD = 0.5 mm–0.7 mm, exceeding EA2 accuracy: AJ = 81%, AVI = 83%, AVE = 14%, and AHD = 0.3 mm. The A-U-net model repeatability wCV [95% CI]: 3 [2, 5]% was notably better than that of expert annotators EA1: 5 [4, 9]% and EA2: 8 [6, 13]%. The developed deep learning model effectively automates murine bone marrow segmentation with accuracy comparable to human annotators and substantially improved repeatability.
format Online
Article
Text
id pubmed-10037585
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100375852023-03-25 Improved Repeatability of Mouse Tibia Volume Segmentation in Murine Myelofibrosis Model Using Deep Learning Kushwaha, Aman Mourad, Rami F. Heist, Kevin Tariq, Humera Chan, Heang-Ping Ross, Brian D. Chenevert, Thomas L. Malyarenko, Dariya Hadjiiski, Lubomir M. Tomography Article A murine model of myelofibrosis in tibia was used in a co-clinical trial to evaluate segmentation methods for application of image-based biomarkers to assess disease status. The dataset (32 mice with 157 3D MRI scans including 49 test–retest pairs scanned on consecutive days) was split into approximately 70% training, 10% validation, and 20% test subsets. Two expert annotators (EA1 and EA2) performed manual segmentations of the mouse tibia (EA1: all data; EA2: test and validation). Attention U-net (A-U-net) model performance was assessed for accuracy with respect to EA1 reference using the average Jaccard index (AJI), volume intersection ratio (AVI), volume error (AVE), and Hausdorff distance (AHD) for four training scenarios: full training, two half-splits, and a single-mouse subsets. The repeatability of computer versus expert segmentations for tibia volume of test–retest pairs was assessed by within-subject coefficient of variance (%wCV). A-U-net models trained on full and half-split training sets achieved similar average accuracy (with respect to EA1 annotations) for test set: AJI = 83–84%, AVI = 89–90%, AVE = 2–3%, and AHD = 0.5 mm–0.7 mm, exceeding EA2 accuracy: AJ = 81%, AVI = 83%, AVE = 14%, and AHD = 0.3 mm. The A-U-net model repeatability wCV [95% CI]: 3 [2, 5]% was notably better than that of expert annotators EA1: 5 [4, 9]% and EA2: 8 [6, 13]%. The developed deep learning model effectively automates murine bone marrow segmentation with accuracy comparable to human annotators and substantially improved repeatability. MDPI 2023-03-07 /pmc/articles/PMC10037585/ /pubmed/36961007 http://dx.doi.org/10.3390/tomography9020048 Text en © 2023 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
Kushwaha, Aman
Mourad, Rami F.
Heist, Kevin
Tariq, Humera
Chan, Heang-Ping
Ross, Brian D.
Chenevert, Thomas L.
Malyarenko, Dariya
Hadjiiski, Lubomir M.
Improved Repeatability of Mouse Tibia Volume Segmentation in Murine Myelofibrosis Model Using Deep Learning
title Improved Repeatability of Mouse Tibia Volume Segmentation in Murine Myelofibrosis Model Using Deep Learning
title_full Improved Repeatability of Mouse Tibia Volume Segmentation in Murine Myelofibrosis Model Using Deep Learning
title_fullStr Improved Repeatability of Mouse Tibia Volume Segmentation in Murine Myelofibrosis Model Using Deep Learning
title_full_unstemmed Improved Repeatability of Mouse Tibia Volume Segmentation in Murine Myelofibrosis Model Using Deep Learning
title_short Improved Repeatability of Mouse Tibia Volume Segmentation in Murine Myelofibrosis Model Using Deep Learning
title_sort improved repeatability of mouse tibia volume segmentation in murine myelofibrosis model using deep learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10037585/
https://www.ncbi.nlm.nih.gov/pubmed/36961007
http://dx.doi.org/10.3390/tomography9020048
work_keys_str_mv AT kushwahaaman improvedrepeatabilityofmousetibiavolumesegmentationinmurinemyelofibrosismodelusingdeeplearning
AT mouradramif improvedrepeatabilityofmousetibiavolumesegmentationinmurinemyelofibrosismodelusingdeeplearning
AT heistkevin improvedrepeatabilityofmousetibiavolumesegmentationinmurinemyelofibrosismodelusingdeeplearning
AT tariqhumera improvedrepeatabilityofmousetibiavolumesegmentationinmurinemyelofibrosismodelusingdeeplearning
AT chanheangping improvedrepeatabilityofmousetibiavolumesegmentationinmurinemyelofibrosismodelusingdeeplearning
AT rossbriand improvedrepeatabilityofmousetibiavolumesegmentationinmurinemyelofibrosismodelusingdeeplearning
AT chenevertthomasl improvedrepeatabilityofmousetibiavolumesegmentationinmurinemyelofibrosismodelusingdeeplearning
AT malyarenkodariya improvedrepeatabilityofmousetibiavolumesegmentationinmurinemyelofibrosismodelusingdeeplearning
AT hadjiiskilubomirm improvedrepeatabilityofmousetibiavolumesegmentationinmurinemyelofibrosismodelusingdeeplearning