A deep learning approach for successful big-bubble formation prediction in deep anterior lamellar keratoplasty

Abstract The efficacy of deep learning in predicting successful big-bubble (SBB) formation during deep anterior lamellar keratoplasty (DALK) was evaluated. Medical records of patients undergoing DALK at the University of Cologne, Germany between March 2013 and July 2019 were retrospectively analyzed...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Takahiko Hayashi, Hiroki Masumoto, Hitoshi Tabuchi, Naofumi Ishitobi, Mao Tanabe, Michael Grün, Björn Bachmann, Claus Cursiefen, Sebastian Siebelmann
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/b919681a42f845cd992eb3f80e6cb74e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:b919681a42f845cd992eb3f80e6cb74e
record_format dspace
spelling oai:doaj.org-article:b919681a42f845cd992eb3f80e6cb74e2021-12-02T15:15:35ZA deep learning approach for successful big-bubble formation prediction in deep anterior lamellar keratoplasty10.1038/s41598-021-98157-82045-2322https://doaj.org/article/b919681a42f845cd992eb3f80e6cb74e2021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-98157-8https://doaj.org/toc/2045-2322Abstract The efficacy of deep learning in predicting successful big-bubble (SBB) formation during deep anterior lamellar keratoplasty (DALK) was evaluated. Medical records of patients undergoing DALK at the University of Cologne, Germany between March 2013 and July 2019 were retrospectively analyzed. Patients were divided into two groups: (1) SBB or (2) failed big-bubble (FBB). Preoperative images of anterior segment optical coherence tomography and corneal biometric values (corneal thickness, corneal curvature, and densitometry) were evaluated. A deep neural network model, Visual Geometry Group-16, was selected to test the validation data, evaluate the model, create a heat map image, and calculate the area under the curve (AUC). This pilot study included 46 patients overall (11 women, 35 men). SBBs were more common in keratoconus eyes (KC eyes) than in corneal opacifications of other etiologies (non KC eyes) (p = 0.006). The AUC was 0.746 (95% confidence interval [CI] 0.603–0.889). The determination success rate was 78.3% (18/23 eyes) (95% CI 56.3–92.5%) for SBB and 69.6% (16/23 eyes) (95% CI 47.1–86.8%) for FBB. This automated system demonstrates the potential of SBB prediction in DALK. Although KC eyes had a higher SBB rate, no other specific findings were found in the corneal biometric data.Takahiko HayashiHiroki MasumotoHitoshi TabuchiNaofumi IshitobiMao TanabeMichael GrünBjörn BachmannClaus CursiefenSebastian SiebelmannNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-6 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Takahiko Hayashi
Hiroki Masumoto
Hitoshi Tabuchi
Naofumi Ishitobi
Mao Tanabe
Michael Grün
Björn Bachmann
Claus Cursiefen
Sebastian Siebelmann
A deep learning approach for successful big-bubble formation prediction in deep anterior lamellar keratoplasty
description Abstract The efficacy of deep learning in predicting successful big-bubble (SBB) formation during deep anterior lamellar keratoplasty (DALK) was evaluated. Medical records of patients undergoing DALK at the University of Cologne, Germany between March 2013 and July 2019 were retrospectively analyzed. Patients were divided into two groups: (1) SBB or (2) failed big-bubble (FBB). Preoperative images of anterior segment optical coherence tomography and corneal biometric values (corneal thickness, corneal curvature, and densitometry) were evaluated. A deep neural network model, Visual Geometry Group-16, was selected to test the validation data, evaluate the model, create a heat map image, and calculate the area under the curve (AUC). This pilot study included 46 patients overall (11 women, 35 men). SBBs were more common in keratoconus eyes (KC eyes) than in corneal opacifications of other etiologies (non KC eyes) (p = 0.006). The AUC was 0.746 (95% confidence interval [CI] 0.603–0.889). The determination success rate was 78.3% (18/23 eyes) (95% CI 56.3–92.5%) for SBB and 69.6% (16/23 eyes) (95% CI 47.1–86.8%) for FBB. This automated system demonstrates the potential of SBB prediction in DALK. Although KC eyes had a higher SBB rate, no other specific findings were found in the corneal biometric data.
format article
author Takahiko Hayashi
Hiroki Masumoto
Hitoshi Tabuchi
Naofumi Ishitobi
Mao Tanabe
Michael Grün
Björn Bachmann
Claus Cursiefen
Sebastian Siebelmann
author_facet Takahiko Hayashi
Hiroki Masumoto
Hitoshi Tabuchi
Naofumi Ishitobi
Mao Tanabe
Michael Grün
Björn Bachmann
Claus Cursiefen
Sebastian Siebelmann
author_sort Takahiko Hayashi
title A deep learning approach for successful big-bubble formation prediction in deep anterior lamellar keratoplasty
title_short A deep learning approach for successful big-bubble formation prediction in deep anterior lamellar keratoplasty
title_full A deep learning approach for successful big-bubble formation prediction in deep anterior lamellar keratoplasty
title_fullStr A deep learning approach for successful big-bubble formation prediction in deep anterior lamellar keratoplasty
title_full_unstemmed A deep learning approach for successful big-bubble formation prediction in deep anterior lamellar keratoplasty
title_sort deep learning approach for successful big-bubble formation prediction in deep anterior lamellar keratoplasty
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/b919681a42f845cd992eb3f80e6cb74e
work_keys_str_mv AT takahikohayashi adeeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT hirokimasumoto adeeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT hitoshitabuchi adeeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT naofumiishitobi adeeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT maotanabe adeeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT michaelgrun adeeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT bjornbachmann adeeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT clauscursiefen adeeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT sebastiansiebelmann adeeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT takahikohayashi deeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT hirokimasumoto deeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT hitoshitabuchi deeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT naofumiishitobi deeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT maotanabe deeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT michaelgrun deeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT bjornbachmann deeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT clauscursiefen deeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
AT sebastiansiebelmann deeplearningapproachforsuccessfulbigbubbleformationpredictionindeepanteriorlamellarkeratoplasty
_version_ 1718387532626919424