Robust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images
Abstract Deep learning (DL) is a widely applied mathematical modeling technique. Classically, DL models utilize large volumes of training data, which are not available in many healthcare contexts. For patients with brain tumors, non-invasive diagnosis would represent a substantial clinical advance,...
Guardado en:
Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2020
|
Materias: | |
Acceso en línea: | https://doaj.org/article/48a196a679684d488c084efeeb434cda |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:48a196a679684d488c084efeeb434cda |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:48a196a679684d488c084efeeb434cda2021-12-02T18:36:14ZRobust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images10.1038/s41598-020-73278-82045-2322https://doaj.org/article/48a196a679684d488c084efeeb434cda2020-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-73278-8https://doaj.org/toc/2045-2322Abstract Deep learning (DL) is a widely applied mathematical modeling technique. Classically, DL models utilize large volumes of training data, which are not available in many healthcare contexts. For patients with brain tumors, non-invasive diagnosis would represent a substantial clinical advance, potentially sparing patients from the risks associated with surgical intervention on the brain. Such an approach will depend upon highly accurate models built using the limited datasets that are available. Herein, we present a novel genetic algorithm (GA) that identifies optimal architecture parameters using feature embeddings from state-of-the-art image classification networks to identify the pediatric brain tumor, adamantinomatous craniopharyngioma (ACP). We optimized classification models for preoperative Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and combined CT and MRI datasets with demonstrated test accuracies of 85.3%, 83.3%, and 87.8%, respectively. Notably, our GA improved baseline model performance by up to 38%. This work advances DL and its applications within healthcare by identifying optimized networks in small-scale data contexts. The proposed system is easily implementable and scalable for non-invasive computer-aided diagnosis, even for uncommon diseases.Eric W. PrinceRos WhelanDavid M. MirskyNicholas StenceSusan StaulcupPaul KlimoRichard C. E. AndersonToba N. NiaziGerald GrantMark SouweidaneJames M. JohnstonEric M. JacksonDavid D. LimbrickAmy SmithAnnie DrapeauJoshua J. ChernLindsay KilburnKevin GinnRobert NaftelRoy DudleyElizabeth Tyler-KabaraGeorge JalloMichael H. HandlerKenneth JonesAndrew M. DonsonNicholas K. ForemanTodd C. HankinsonNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-13 (2020) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Eric W. Prince Ros Whelan David M. Mirsky Nicholas Stence Susan Staulcup Paul Klimo Richard C. E. Anderson Toba N. Niazi Gerald Grant Mark Souweidane James M. Johnston Eric M. Jackson David D. Limbrick Amy Smith Annie Drapeau Joshua J. Chern Lindsay Kilburn Kevin Ginn Robert Naftel Roy Dudley Elizabeth Tyler-Kabara George Jallo Michael H. Handler Kenneth Jones Andrew M. Donson Nicholas K. Foreman Todd C. Hankinson Robust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images |
description |
Abstract Deep learning (DL) is a widely applied mathematical modeling technique. Classically, DL models utilize large volumes of training data, which are not available in many healthcare contexts. For patients with brain tumors, non-invasive diagnosis would represent a substantial clinical advance, potentially sparing patients from the risks associated with surgical intervention on the brain. Such an approach will depend upon highly accurate models built using the limited datasets that are available. Herein, we present a novel genetic algorithm (GA) that identifies optimal architecture parameters using feature embeddings from state-of-the-art image classification networks to identify the pediatric brain tumor, adamantinomatous craniopharyngioma (ACP). We optimized classification models for preoperative Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and combined CT and MRI datasets with demonstrated test accuracies of 85.3%, 83.3%, and 87.8%, respectively. Notably, our GA improved baseline model performance by up to 38%. This work advances DL and its applications within healthcare by identifying optimized networks in small-scale data contexts. The proposed system is easily implementable and scalable for non-invasive computer-aided diagnosis, even for uncommon diseases. |
format |
article |
author |
Eric W. Prince Ros Whelan David M. Mirsky Nicholas Stence Susan Staulcup Paul Klimo Richard C. E. Anderson Toba N. Niazi Gerald Grant Mark Souweidane James M. Johnston Eric M. Jackson David D. Limbrick Amy Smith Annie Drapeau Joshua J. Chern Lindsay Kilburn Kevin Ginn Robert Naftel Roy Dudley Elizabeth Tyler-Kabara George Jallo Michael H. Handler Kenneth Jones Andrew M. Donson Nicholas K. Foreman Todd C. Hankinson |
author_facet |
Eric W. Prince Ros Whelan David M. Mirsky Nicholas Stence Susan Staulcup Paul Klimo Richard C. E. Anderson Toba N. Niazi Gerald Grant Mark Souweidane James M. Johnston Eric M. Jackson David D. Limbrick Amy Smith Annie Drapeau Joshua J. Chern Lindsay Kilburn Kevin Ginn Robert Naftel Roy Dudley Elizabeth Tyler-Kabara George Jallo Michael H. Handler Kenneth Jones Andrew M. Donson Nicholas K. Foreman Todd C. Hankinson |
author_sort |
Eric W. Prince |
title |
Robust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images |
title_short |
Robust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images |
title_full |
Robust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images |
title_fullStr |
Robust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images |
title_full_unstemmed |
Robust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images |
title_sort |
robust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images |
publisher |
Nature Portfolio |
publishDate |
2020 |
url |
https://doaj.org/article/48a196a679684d488c084efeeb434cda |
work_keys_str_mv |
AT ericwprince robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT roswhelan robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT davidmmirsky robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT nicholasstence robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT susanstaulcup robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT paulklimo robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT richardceanderson robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT tobanniazi robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT geraldgrant robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT marksouweidane robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT jamesmjohnston robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT ericmjackson robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT daviddlimbrick robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT amysmith robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT anniedrapeau robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT joshuajchern robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT lindsaykilburn robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT kevinginn robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT robertnaftel robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT roydudley robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT elizabethtylerkabara robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT georgejallo robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT michaelhhandler robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT kennethjones robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT andrewmdonson robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT nicholaskforeman robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages AT toddchankinson robustdeeplearningclassificationofadamantinomatouscraniopharyngiomafromlimitedpreoperativeradiographicimages |
_version_ |
1718377857260978176 |