Real-time detection of acromegaly from facial images with artificial intelligence
European Journal of Endocrinology · 10.01.2023 · 188 (1) · 158-165
DOI: 10.1093/ejendo/lvad005 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Journal of Endocrinology, online erschienen am 13.01.2023. Verfasst von Muhammed Kizilgul und 10 weiteren Autor:innen. Beteiligte Einrichtung: University of Health Sciences, Diskapi Yildirim Beyazit Training and Research Hospital, Department of Endocrinology, Ankara, Turkey. Hauptthemen laut MEDLINE: Artificial Intelligence, Acromegaly. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 22 Literaturangaben.
Abstract (Originalsprache)
Objective
Despite improvements in diagnostic methods, acromegaly is still a late-diagnosed disease. In this study, it was aimed to automatically recognize acromegaly disease from facial images by using deep learning methods and to facilitate the detection of the disease.
Design
Cross-sectional, single-centre study Methods The study included 77 acromegaly (52.56 ± 11.74, 34 males/43 females) patients and 71 healthy controls (48.47 ± 8.91, 39 males/32 females), considering gender and age compatibility. At the time of the photography, 56/77 (73%) of the acromegaly patients were in remission. Normalized images were obtained by scaling, aligning, and cropping video frames. Three architectures named ResNet50, DenseNet121, and InceptionV3 were used for the transfer learning-based convolutional neural network (CNN) model developed to classify face images as “Healthy” or “Acromegaly”. Additionally, we trained and integrated these CNN machine learning methods to create an Ensemble Method (EM) for facial detection of acromegaly.
Results
The positive predictive values obtained for acromegaly with the ResNet50, DenseNet121, InceptionV3, and EM were calculated as 0.958, 0.965, 0.962, and 0.997, respectively. The average sensitivity, specificity, precision, and correlation coefficient values calculated for each of the ResNet50, DenseNet121, and InceptionV3 models are quite close. On the other hand, EM outperformed these three CNN architectures and provided the best overall performance in terms of sensitivity, specificity, accuracy, and precision as 0.997, 0.997, 0.997, and 0.998, respectively.
Conclusions
The present study provided evidence that the proposed AcroEnsemble Model might detect acromegaly from facial images with high performance. This highlights that artificial intelligence programs are promising methods for detecting acromegaly in the future.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- University of Health Sciences, Diskapi Yildirim Beyazit Training and Research Hospital, Department of Endocrinology, Ankara, Turkey.
- Sivas Cumhuriyet University, Faculty of Technology, Software Engineering Department, Sivas, Turkey.
- Selçuk University, Faculty of Technology, Computer Engineering Department, Konya, Turkey.
- Ankara University, Elmadağ Vocational School, Computer Technologies Department, Ankara, Turkey.
- Burdur Mehmet Akif Ersoy University, Faculty of Technology, Software Engineering Department, Burdur, Turkey.
- TOBB ETU, Faculty of Science and Literature, Mathematics Department, Ankara, Turkey.
ORCID-Profile: Muhammed Kizilgul, Hayri Bostan
Zitieren
APA
Kizilgul, M., Karakis, R., Dogan, N., Bostan, H., Yapici, M. M., Gul, U., Ucan, B., Duman, E., Duger, H., Cakal, E., & Akin, O. (2023). Real-time detection of acromegaly from facial images with artificial intelligence. European Journal of Endocrinology, 188(1), 158-165. https://doi.org/10.1093/ejendo/lvad005
Vancouver
Kizilgul M, Karakis R, Dogan N, Bostan H, Yapici MM, Gul U, et al. Real-time detection of acromegaly from facial images with artificial intelligence. European Journal of Endocrinology. 2023;188(1):158-165. doi:10.1093/ejendo/lvad005
BibTeX
@article{Kizilgul2023,
author = {Kizilgul, Muhammed and Karakis, Rukiye and Dogan, Nurettin and Bostan, Hayri and Yapici, Muhammed Mutlu and Gul, Umran and Ucan, Bekir and Duman, Elvan and Duger, Hakan and Cakal, Erman and Akin, Omer},
title = {Real-time detection of acromegaly from facial images with artificial intelligence},
journal = {European Journal of Endocrinology},
year = {2023},
volume = {188},
number = {1},
pages = {158--165},
doi = {10.1093/ejendo/lvad005}
}
EUVIMED