Christoph Grechenig
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Christoph Grechenig has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Axel Gänsslen
Department of Trauma Surgery, Hannover Medical School, Hanover, Germany
2 shared publications - Gloria Maria Hohenberger
Department of Trauma Surgery, State Hospital Feldbach-Fürstenfeld, Feldbach, Austria
2 shared publications Amina Paquay
Neuromuscular Research Department, Center for Anatomy and Cell Biology, Medical University of Vienna, Vienna, Austria
1 shared publication- Andreas Wedrich
Department of Ophthalmology, Medical University of Graz, Graz, Austria
1 shared publication - Andy Sombke
Electron microscopy and functional ultrastructure, Center for Anatomy and Cell Biology, Medical University of Vienna, Vienna, Austria
1 shared publication - Angelika Maria Schwarz
AUVA – Trauma Hospital (UKH) Styria | Graz, Teaching Hospital of the Medical University of Graz, Graz, Austria
1 shared publication
Latest Publications
- Open Access
- 1 October 2025
- Published by Elsevier in Genetics in Medicine
- Vol. 28 (1) , 101595
A recurrent missense variant in the PPIB gene encoding peptidylprolyl isomerase B underlies adult-onset autosomal dominant optic atrophy
- 1 October 2025
- Published by Elsevier in Genetics in Medicine
- Vol. 28 (1) , 101595
Open AccessA recurrent missense variant in the PPIB gene encoding peptidylprolyl isomerase B underlies adult-onset autosomal dominant optic atrophy
- 11 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (4) , 2235-2246
Deep Multimodal Fusion of Data With Heterogeneous Dimensionality via Projective Networks
The use of multimodal imaging has led to significant improvements in the diagnosis and treatment of many diseases. Similar to clinical practice, some works have demonstrated the benefits of multimodal fusion for automatic segmentation and classification using deep learning-based methods. However, current segmentation methods are limited to fusion of modalities with the same dimensionality (e.g., 3D+3D, 2D+2D), which is not always possible, and the fusion strategies implemented by classification methods are incompatible with localization tasks. In this work, we propose a novel deep learning-based framework for the fusion of multimodal data with heterogeneous dimensionality (e.g., 3D+2D) that is compatible with localization tasks. The proposed framework extracts the features of the different modalities and projects them into the common feature subspace. The projected features are then fused and further processed to obtain the final prediction. The framework was validated on the following tasks: segmentation of geographic atrophy (GA), a late-stage manifestation of age-related macular degeneration, and segmentation of retinal blood vessels (RBV) in multimodal retinal imaging. Our results show that the proposed method outperforms the state-of-the-art monomodal methods on GA and RBV segmentation by up to 3.10% and 4.64% Dice, respectively.
- 11 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (4) , 2235-2246
Deep Multimodal Fusion of Data With Heterogeneous Dimensionality via Projective Networks
The use of multimodal imaging has led to significant improvements in the diagnosis and treatment of many diseases. Similar to clinical practice, some works have demonstrated the benefits of multimodal fusion for automatic segmentation and classification using deep learning-based methods. However, current segmentation methods are limited to fusion of modalities with the same dimensionality (e.g., 3D+3D, 2D+2D), which is not always possible, and the fusion strategies implemented by classification methods are incompatible with localization tasks. In this work, we propose a novel deep learning-based framework for the fusion of multimodal data with heterogeneous dimensionality (e.g., 3D+2D) that is compatible with localization tasks. The proposed framework extracts the features of the different modalities and projects them into the common feature subspace. The projected features are then fused and further processed to obtain the final prediction. The framework was validated on the following tasks: segmentation of geographic atrophy (GA), a late-stage manifestation of age-related macular degeneration, and segmentation of retinal blood vessels (RBV) in multimodal retinal imaging. Our results show that the proposed method outperforms the state-of-the-art monomodal methods on GA and RBV segmentation by up to 3.10% and 4.64% Dice, respectively.
- Open Access
- 12 October 2021
- Published by Springer Nature in Scientific Reports
- Vol. 11 (1) , 1-8
Relation of the lumbosacral trunk to the sacro-iliac joint
This study aims to evaluate the relation between the lumbosacral trunk (LT) and the sacro-iliac joint (SIJ). In forty anatomic specimens (hemipelves) a classical antero-lateral approach to the SIJ was performed. The SIJ was marked at the linea terminalis (reference point A). Reference point B was situated at the upper edge of the interosseous sacro-iliac ligament. The length of the SIJ (distance A to B) and the distance between point A and the ventral branch of the fourth (L4) and fifth (L5) lumbar spinal nerves at the linea terminalis were measured. The SIJ had a mean length of 58.0 mm. The ventral branch of L5 was located closer to the SIJ in very long SIJs (mean length: ≥ 6.5 cm; mean distance: 9.8 mm) compared to very short joints (≤ 5 mm; mean distance: 11.3 mm). For the ventral branch of L4, very long SIJs had a mean distance of 7 mm and very short joints an average distance of 9.7 mm between point A and the nerve branch. A safe zone of approximately 1 cm to 2 cm (anterior to posterior) is present on the sacral surface (lateral to medial) for safe fixation of plates during anterior plate stabilization of the SIJ. Pelves with a shorter dorsoventral diameter of the most superior part of the SIJ apparently give more space for inserting plates.
- 12 October 2021
- Published by Springer Nature in Scientific Reports
- Vol. 11 (1) , 1-8
Open AccessRelation of the lumbosacral trunk to the sacro-iliac joint
This study aims to evaluate the relation between the lumbosacral trunk (LT) and the sacro-iliac joint (SIJ). In forty anatomic specimens (hemipelves) a classical antero-lateral approach to the SIJ was performed. The SIJ was marked at the linea terminalis (reference point A). Reference point B was situated at the upper edge of the interosseous sacro-iliac ligament. The length of the SIJ (distance A to B) and the distance between point A and the ventral branch of the fourth (L4) and fifth (L5) lumbar spinal nerves at the linea terminalis were measured. The SIJ had a mean length of 58.0 mm. The ventral branch of L5 was located closer to the SIJ in very long SIJs (mean length: ≥ 6.5 cm; mean distance: 9.8 mm) compared to very short joints (≤ 5 mm; mean distance: 11.3 mm). For the ventral branch of L4, very long SIJs had a mean distance of 7 mm and very short joints an average distance of 9.7 mm between point A and the nerve branch. A safe zone of approximately 1 cm to 2 cm (anterior to posterior) is present on the sacral surface (lateral to medial) for safe fixation of plates during anterior plate stabilization of the SIJ. Pelves with a shorter dorsoventral diameter of the most superior part of the SIJ apparently give more space for inserting plates.