Deep learning-based detection and classification of geographic atrophy using a deep convolutional neural network classifier
- 164 Downloads
To automatically detect and classify geographic atrophy (GA) in fundus autofluorescence (FAF) images using a deep learning algorithm.
For the automated detection of GA in FAF images, two classifiers were built (GA vs. healthy/GA vs. ORD). The DCNN was trained and validated with 400 FAF images in each case (GA 200, healthy 200, or ORD 200). For the subsequent testing, the built classifiers were then tested with 60 untrained FAF images in each case (AMD 30, healthy 30, or ORD 30). Hereby, both classifiers automatically determined a GA probability score and a normal FAF probability score or an ORD probability score.
To automatically differentiate between dt-GA and ndt-GA, the DCNN was trained and validated with 200 FAF images (dt-GA 72; ndt-GA 138). Afterwards, the built classifier was tested with 20 untrained FAF images (dt-GA 10; ndt-GA 10) and a dt-GA probability score and an ndt-GA probability score was calculated.
For both classifiers, the performance of the training and validation procedure after 500 training steps was measured by determining training accuracy, validation accuracy, and cross entropy.
For the GA classifiers (GA vs. healthy/GA vs. ORD), the achieved training accuracy was 99/98%, the validation accuracy 96/91%, and the cross entropy 0.062/0.100. For the dt-GA classifier, the training accuracy was 99%, the validation accuracy 77%, and the cross entropy 0.166.
The mean GA probability score was 0.981 ± 0.048 (GA vs. healthy)/0.972 ± 0.439 (GA vs. ORD) in the GA image group and 0.01 ± 0.016 (healthy)/0.061 ± 0.072 (ORD) in the comparison groups (p < 0.001). The mean dt-GA probability score was 0.807 ± 0.116 in the dt-GA image group and 0.180 ± 0.100 in the ndt-GA image group (p < 0.001).
For the first time, this study describes the use of a deep learning-based algorithm to automatically detect and classify GA in FAF. Hereby, the created classifiers showed excellent results. With further developments, this model may be a tool to predict the individual progression risk of GA and give relevant information for future therapeutic approaches.
KeywordsDeep learning Machine learning Deep convolutional neural network Geographic atrophy Fundus autofluorescence
Compliance with ethical standards
Conflict of interest
All authors certify that they have no affiliations with/or involvement in any organization or entity with any financial interest (such as honoraria; educational grants; participation in speakers’ bureaus; membership, employment, consultancies, stock ownership, or other equity interest; and expert testimony or patent-licensing arrangements) or non-financial interest (such as personal or professional relationships, affiliations, knowledge or beliefs) in the subject matter or materials discussed in this manuscript.
M. Treder: Allergan, Novartis; J.L. Lauermann: Bayer, Novartis; N. Eter: Allergan, Alimera, Bausch and Lomb, Bayer, Heidelberg Engineering, Novartis, Roche.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
For this type of study formal consent is not required.
- 3.Bindewald A, Schmitz-Valckenberg S, Jorzik J, Dolar-Szczasny J, Sieber H, Keilhauer C, Weinberger A, Dithmar S, Pauleikhoff D, Mansmann U, Wolf S, Holz F (2005) Classification of abnormal fundus autofluorescence patterns in the junctional zone of geographic atrophy in patients with age related macular degeneration. Br J Ophthalmol 89:874–878CrossRefGoogle Scholar
- 9.Yung M, Klufas MA, Sarraf D (2016) Clinical applications of fundus autofluorescence in retinal disease. Int J Retina Vitreous. https://doi.org/10.1186/s40942-016-0035-x
- 25.Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) ImageNet- a large-scale hierarchical image database. CVPR 2009—IEEE conference on computer vision and. Pattern Recogn 2009:248–255Google Scholar
- 26.Szegedy C, Vanhoucke V, Ioffe S, Shlens J (2016) Rethinking the inception architecture for computer vision. IEEE Conf Comput Vis Pattern Recognit 2016:2818–2826Google Scholar
- 27.TensorFlow (2017) http://www.tensorflow.org/tutorials/image_recognition. TensorFlow. Accessed 30 Jan 2018
- 28.Google Developers (2017) https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/#0. Google Developers. Accessed 4 July 2017
- 31.Schmitz-Valckenberg S, Gobel AP, Saur SC, Steinberg JS, Thiele S, Wojek C, Russmann C, Holz FG, For The Modiamd-Study G (2016) Automated retinal image analysis for evaluation of focal hyperpigmentary changes in intermediate age-related macular degeneration. Transl Vis Sci Technol 5:3CrossRefGoogle Scholar
- 36.Schmitz-Valckenberg S, Bindewald-Wittich A, Dolar-Szczasny J, Dreyhaupt J, Wolf S, Scholl HP, Holz FG, Fundus Autofluorescence in Age-Related Macular Degeneration Study G (2006) Correlation between the area of increased autofluorescence surrounding geographic atrophy and disease progression in patients with AMD. Invest Ophthalmol Vis Sci 47:2648–2654CrossRefGoogle Scholar