Aron Kirchhoff

Aron Kirchhoff

Auto-generated profile, based on publicly available information

Aron Kirchhoff

Institute for Genomic Statistics and Bioinformatics, University of Bonn, Bonn, Germany

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 January 2025 in European Journal of Human Genetics
Verified
Journal Article
Open access
PDF file
AKAron Kirchhoff
Aron Kirchhoff
AHAlexander Hustinx
Alexander Hustinx
BJBehnam Javanmardi
Behnam Javanmardi
THTzung-Chien Hsieh
Tzung-Chien Hsieh
FBFabian Brand
Fabian Brand
PKPeter Krawitz
Peter Krawitz
The facial gestalt (overall facial morphology) is a characteristic clinical feature in many genetic disorders that is often essential for suspecting and establishing a specific diagnosis. Therefore, publishing images of individuals affected by pathogenic variants in disease-associated genes has been an important part of scientific communication. Furthermore, medical imaging data is also crucial for teaching and training deep-learning models such as GestaltMatcher. However, medical data is often sparsely available, and sharing patient images involves risks related to privacy and re-identification. Therefore, we explored whether generative neural networks can be used to synthesize accurate portraits for rare disorders. We modified a StyleGAN architecture and trained it to produce artificial condition-specific portraits for multiple disorders. In addition, we present a technique that generates a sharp and detailed average patient portrait for a given disorder. We trained our GestaltGAN on the 20 most frequent disorders from the GestaltMatcher database. We used REAL-ESRGAN to increase the resolution of portraits from the training data with low-quality and colorized black-and-white images. To augment the model’s understanding of human facial features, an unaffected class was introduced to the training data. We tested the validity of our generated portraits with 63 human experts. Our findings demonstrate the model’s proficiency in generating photorealistic portraits that capture the characteristic features of a disorder while preserving patient privacy. Overall, the output from our approach holds promise for various applications, including visualizations for publications and educational materials and augmenting training data for deep learning.

23 May 2025 in European Journal of Human Genetics
Verified
Journal Article
Open access
PDF file
KWKatharina Wenderott
Katharina Wenderott
JKJim Krups
Jim Krups
FZFiona Zaruchas
Fiona Zaruchas
PKPeter Krawitz
Peter Krawitz
MWMatthias Weigl
Matthias Weigl
HLHellen Lesmann
Hellen Lesmann
The diagnosis of rare genetic disorders often involves prolonged delays, with facial features serving as key diagnostic clues. Next-Generation Phenotyping (NGP) tools, such as Face2Gene, utilize Artificial Intelligence (AI)-driven algorithms to analyze patient photographs and list differential diagnoses based on facial dysmorphism. Despite their growing use and proven clinical value, their integration into clinical workflows remains poorly understood. This study evaluates Face2Gene’s implementation into routine clinical care with barriers and facilitators to successful adoption. We conducted a literature review, followed by in-depth interviews with 15 geneticists across university hospitals in Germany. Results showed an overall positive appraisal of the tool among clinicians with emphasis on its usability. Key workflow barriers comprised IT integration and patient consent process. Despite being an additional step in the diagnostic pathway, Face2Gene has been effectively incorporated into geneticists’ diagnostic routines, facilitating decision processes, and potentially expediting diagnoses for some patients. Our findings contribute to the existing literature on NGP technologies by demonstrating that effective integration of Face2Gene can enhance clinicians’ efficiency and quality of work. To maximize impact of NGP technologies in genetic medicine, future implementation efforts should strive for clinicians’ acceptance particularly through user-friendly design and sustained organizational support in course of workflow implementation. Study registration: German Register for Clinical Trials (DRKS) DRKS00032436

25 March 2026 in European Journal of Human Genetics
Verified
Journal Article
Closed access
PDF file
Quentin SabbaghQuentin Sabbagh
Quentin Sabbagh
CCCamille Cenni
Camille Cenni
SHSadegheh Haghshenas
Sadegheh Haghshenas
JAJean-Luc Alessandri
Jean-Luc Alessandri
MBMads Bak
Mads Bak
DGDavid Geneviève
David Geneviève

18 July 2024 in medRxiv
Verified
Preprint
Open access
PDF file
AKAron Kirchhoff
Aron Kirchhoff
AHAlexander Hustinx
Alexander Hustinx
BJBehnam Javanmardi
Behnam Javanmardi
THTzung-Chien Hsieh
Tzung-Chien Hsieh
FBFabian Brand
Fabian Brand
PKPeter Krawitz
Peter Krawitz
The facial gestalt (overall facial morphology) is a characteristic clinical feature in many genetic disorders that is often essential for suspecting and establishing a specific diagnosis. For that reason, publishing images of individuals affected by pathogenic variants in disease-associated genes has been an important part of scientific communication. Furthermore, medical imaging data is also crucial for teaching and training artificial intelligence methods such as GestaltMatcher. However, medical data is often sparsely available and sharing patient images involves risks related to privacy and re-identification. Therefore, we explored whether generative neural networks can be used to synthesize accurate portraits for rare disorders. We modified a StyleGAN architecture and trained it to produce random condition-specific portraits for multiple disorders. We present a technique that generates a sharp and detailed average patient portrait for a given disorder. We trained our GestaltGAN on the 20 most frequent disorders from the GestaltMatcher database. We used REAL-ESRGAN to increase the resolution of portraits from the training data with low quality and colorized black-and-white images. The training data was aligned and cropped to achieve a uniform format. To augment the model’s understanding of human facial features, an unaffected class was introduced to the training data. We tested the validity of our generated portraits with 63 human experts. Our findings demonstrate the model’s proficiency in generating photorealistic portraits that capture the characteristic features of a disorder but preserve the patient’s privacy. Overall, the output from our approach holds promise for various applications, including visualizations for publications, educational materials, as well as augmenting training data for deep learning.

27 March 2026 in medRxiv
Verified
Preprint
Open access
PDF file
EBEike Bolmer
Eike Bolmer
PSPhilipp Schmidt
Philipp Schmidt
IFIsabel Fischer
Isabel Fischer
SRSebastian Rassmann
Sebastian Rassmann
ARAdele Ruder
Adele Ruder
BJBehnam Javanmardi
Behnam Javanmardi
Background: Diagnosing the over 700 known rare bone diseases (RBDs) is inherently challenging and often requires extensive time and multiple clinical visits. Effective treatment, particularly for RBDs with approved therapies, depends on early and precise identification of the specific RBD type. Image recognition artificial intelligence (AI) has the potential to significantly enhance diagnostic processes and improve patient outcomes. Many of these disorders cause characteristic skeletal changes, especially in the hands, and are associated with growth abnormalities. Consequently, affected children routinely undergo hand radiographs for bone age assessment, making these images a widely available yet underutilized diagnostic resource. Materials and Methods: We retrospectively compiled 5,623 multi-institutional hand radiographs from 2,471 patients with 45 different RBDs and 1,382 unaffected controls. We trained two deep learning models: a binary classifier to differentiate between RBD and non-RBD hand radiographs, and a multi-class classifier covering ten RBDs (or RBD groups), using 5-fold cross-validation. Preprocessing included masking, normalization, and data augmentation. Additionally, we applied occlusion sensitivity mapping to visualize class-specific features and evaluated the learned representations through cosine-based retrieval and UMAP projections of the feature space. Results: The affected versus unaffected classifier achieved a balanced accuracy of 85.5% on the test dataset. The ten-class classifier reached a balanced (top-1) accuracy of 76.6%, with top-3 accuracy exceeding 90%. Disorders with highly distinctive phenotypes, such as achondroplasia, achieved accuracies above 95%, whereas phenotypically overlapping disorders, such as ACAN- and SHOX-related short stature, were more frequently confused. Feature space analysis showed that validation samples clustered closely with their respective training distributions, supporting the consistency and generalizability of the learned embeddings. Conclusion: This manuscript presents a proof of principle for the development of Bone2Gene , a next-generation phenotyping (NGP) tool for the detection and differential diagnosis of RBDs, currently based on hand radiographs. Ongoing efforts focus on expanding the dataset to include additional RBDs or RBD groups in the current multi-class classifier for differential diagnosis and to further evaluate its generalizability. The Bone2Gene study is open to collaboration.

26 August 2024 in Research Square
Verified
Preprint
Open access
PDF file
PKPeter Krawitz
Peter Krawitz
AHAlexander Hustinx
Alexander Hustinx
BJBehnam Javanmardi
Behnam Javanmardi
THTzung-Chien Hsieh
Tzung-Chien Hsieh
FBFabian Brand
Fabian Brand
AKAron Kirchhoff
Aron Kirchhoff
The facial gestalt (overall facial morphology) is a characteristic clinical feature in many genetic disorders that is often essential for suspecting and establishing a specific diagnosis. For that reason, publishing images of individuals affected by pathogenic variants in disease-associated genes has been an important part of scientific communication. Furthermore, medical imaging data is also crucial for teaching and training deep-learning models such as GestaltMatcher. However, medical data is often sparsely available, and sharing patient images involves risks related to privacy and re-identification. Therefore, we explored whether generative neural networks can be used to synthesize accurate portraits for rare disorders. We modified a StyleGAN architecture and trained it to produce artifical condition-specific portraits for multiple disorders. In addition, we present a technique that generates a sharp and detailed average patient portrait for a given disorder. We trained our GestaltGAN on the 20 most frequent disorders from the GestaltMatcher database. We used REAL-ESRGAN to increase the resolution of portraits from the training data with low-quality and colorized black-and-white images. To augment the model's understanding of human facial features, an unaffected class was introduced to the training data. We tested the validity of our generated portraits with 63 human experts. Our findings demonstrate the model's proficiency in generating photorealistic portraits that capture the characteristic features of a disorder while preserving patient privacy. Overall the output from our approach holds promise for various applications, including visualizations for publications and educational materials, as well as augmenting training data for deep-learning.