This work presents a novel fully automated method for retinal analysis in images acquired with a flood illuminated adaptive optics retinal camera (AO-FIO). The proposed processing pipeline consists of several steps: First, we register single AO-FIO images in a montage image capturing a larger retinal area. The registration is performed by combination of phase correlation and the scale-invariant feature transform method. A set of 200 AO-FIO images from 10 healthy subjects (10 images from left eye and 10 images from right eye) is processed into 20 montage images and mutually aligned according to the automatically detected fovea center. As a second step, the photoreceptors in the montage images are detected using a method based on regional maxima localization, where the detector parameters were determined with Bayesian optimization according to manually labeled photoreceptors by three evaluators. The detection assessment, based on Dice coefficient, ranges from 0.72 to 0.8. In the next step, the corresponding density maps are generated for each of the montage images. As a final step, representative averaged photoreceptor density maps are created for the left and right eye and thus enabling comprehensive analysis across the montage images and a straightforward comparison with available histological data and other published studies. Our proposed method and software thus enable us to generate AO-based photoreceptor density maps for all measured locations fully automatically, and thus it is suitable for large studies, as those are in pressing need for automated approaches. In addition, the application MATADOR (MATlab ADaptive Optics Retinal Image Analysis) that implements the described pipeline and the dataset with photoreceptor labels are made publicly available.

Database Group Faculty of Bio Sciences and Computer Sciences Mittweida University of Applied Sciences Mittweida Germany

Department of Biomedical Engineering Faculty of Electrical Engineering and Communication Brno University of Technology Brno Czech Republic

Department of Medical Data Science Leipzig University Medical Center Leipzig Germany

Department of Ophthalmology Leipzig University Medical Center Leipzig Germany

Equally contributing

Institute for Medical Informatics Statistics and Epidemiology Leipzig University Leipzig Germany

Leipzig Research Centre for Civilization Diseases Leipzig University Leipzig Germany

Universitäts Augenklinik Bern Inselspital Freiburgstr 3010 Bern Switzerland

000      

00000naa a2200000 a 4500

001      

bmc23003021

003      

CZ-PrNML

005      

20230421100039.0

007      

ta

008      

230413s2023 xxu f 000 0|eng||

009      

AR

024    7_

$a 10.1364/BOE.471881 $2 doi

035    __

$a (PubMed)36874506

040    __

$a ABA008 $b cze $d ABA008 $e AACR2

041    0_

$a eng

044    __

$a xxu

100    1_

$a Valterova, Eva $u Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic $u Department of Medical Data Science, Leipzig University Medical Center, Leipzig, Germany

245    10

$a Comprehensive automatic processing and analysis of adaptive optics flood illumination retinal images on healthy subjects / $c E. Valterova, JD. Unterlauft, M. Francke, T. Kirsten, R. Kolar, FG. Rauscher

520    9_

$a This work presents a novel fully automated method for retinal analysis in images acquired with a flood illuminated adaptive optics retinal camera (AO-FIO). The proposed processing pipeline consists of several steps: First, we register single AO-FIO images in a montage image capturing a larger retinal area. The registration is performed by combination of phase correlation and the scale-invariant feature transform method. A set of 200 AO-FIO images from 10 healthy subjects (10 images from left eye and 10 images from right eye) is processed into 20 montage images and mutually aligned according to the automatically detected fovea center. As a second step, the photoreceptors in the montage images are detected using a method based on regional maxima localization, where the detector parameters were determined with Bayesian optimization according to manually labeled photoreceptors by three evaluators. The detection assessment, based on Dice coefficient, ranges from 0.72 to 0.8. In the next step, the corresponding density maps are generated for each of the montage images. As a final step, representative averaged photoreceptor density maps are created for the left and right eye and thus enabling comprehensive analysis across the montage images and a straightforward comparison with available histological data and other published studies. Our proposed method and software thus enable us to generate AO-based photoreceptor density maps for all measured locations fully automatically, and thus it is suitable for large studies, as those are in pressing need for automated approaches. In addition, the application MATADOR (MATlab ADaptive Optics Retinal Image Analysis) that implements the described pipeline and the dataset with photoreceptor labels are made publicly available.

590    __

$a NEINDEXOVÁNO

655    _2

$a časopisecké články $7 D016428

700    1_

$a Unterlauft, Jan D $u Department of Ophthalmology, Leipzig University Medical Center, Leipzig, Germany $u Universitäts-Augenklinik Bern, Inselspital, Freiburgstr., 3010, Bern, Switzerland

700    1_

$a Francke, Mike $u Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Leipzig, Germany

700    1_

$a Kirsten, Toralf $u Department of Medical Data Science, Leipzig University Medical Center, Leipzig, Germany $u Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Leipzig, Germany $u Database Group, Faculty of Bio Sciences and Computer Sciences, Mittweida University of Applied Sciences, Mittweida, Germany

700    1_

$a Kolar, Radim $u Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic $u Equally contributing $1 https://orcid.org/0000000204696397

700    1_

$a Rauscher, Franziska G $u Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Leipzig, Germany $u Leipzig Research Centre for Civilization Diseases (LIFE), Leipzig University, Leipzig, Germany $u Equally contributing $1 https://orcid.org/0000000301830340

773    0_

$w MED00189502 $t Biomedical optics express $x 2156-7085 $g Roč. 14, č. 2 (2023), s. 945-970

856    41

$u https://pubmed.ncbi.nlm.nih.gov/36874506 $y Pubmed

910    __

$a ABA008 $b sig $c sign $y p $z 0

990    __

$a 20230413 $b ABA008

991    __

$a 20230421100032 $b ABA008

999    __

$a ok $b bmc $g 1922748 $s 1189228

BAS    __

$a 3

BAS    __

$a PreBMC-PubMed-not-MEDLINE

BMC    __

$a 2023 $b 14 $c 2 $d 945-970 $e 20230130 $i 2156-7085 $m Biomedical optics express $n Biomed Opt Express $x MED00189502

LZP    __

$a Pubmed-20230413