Ender Konukoglu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ender Konukoglu has a total of 132 co-authors. Here are the top co-authors by number of shared publications:
- Anton Sebastian Becker
NYU Langone Health 9 Department of Radiology, New York University Grossman School of Medicine New York, New York
6 shared publications - Mehmet Turan
Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
6 shared publications - Metin Sitti
Physical Intelligence Department, Max Planck Institute for Intelligent Systems, Stuttgart 70569, Germany
6 shared publications - Helder Araujo
University of Coimbra
5 shared publications Moritz Schwyzer
Institute for Diagnostic and Interventional Radiology, University Hospital Zurich, Zurich, Switzerland
5 shared publications- Yasin Almalioglu
Computer Engineering Department Bogazici Univesity Turkey
5 shared publications
Latest Publications
- Open Access
- 29 September 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (5) , 931-933
Editorial for Special Issue on Multimodal Learning, Temporal Modeling, and Foundation Models for Video Understanding
- 29 September 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (5) , 931-933
Open AccessEditorial for Special Issue on Multimodal Learning, Temporal Modeling, and Foundation Models for Video Understanding
- Open Access
AENEAS Project: First real-time intraoperative application of machine vision-based anatomical guidance in neurosurgery
Background and Objectives: We report the first intraoperative deployment of a real-time machine vision system in neurosurgery, derived from our previous anatomical detection work, automatically identifying structures during endoscopic endonasal surgery. Existing systems demonstrate promising performance in offline anatomical recognition, yet so far none have been implemented during live operations. Methods: A real-time anatomy detection model was trained using the YOLOv8 architecture (Ultralytics). Following training completion in the PyTorch environment, the model was exported to ONNX format and further optimized using the NVIDIA TensorRT engine. Deployment was carried out using the NVIDIA Holoscan SDK, the system ran on an NVIDIA Clara AGX developer kit. We used the model for real-time recognition of intraoperative anatomical structures and compared it with the same video labelled manually as reference. Model performance was reported using the average precision at an intersection-over-union threshold of 0.5 (AP50). Furthermore, end-to-end delay from frame acquisition to the display of the annotated output was measured. Results: A mean AP50 of 0.56 was achieved. The model demonstrated reliable detection of the most relevant landmarks in the transsphenoidal corridor. The mean end-to-end latency of the model was 47.81 ms (median 46.57 ms). Conclusion: For the first time, we demonstrate that clinical-grade, real-time machine-vision assistance during neurosurgery is feasible and can provide continuous, automated anatomical guidance from the surgical field. This approach may enhance intraoperative orientation, reduce cognitive load, and offer a powerful tool for surgical training. These findings represent an initial step toward integrating real-time AI support into routine neurosurgical workflows.
Open AccessAENEAS Project: First real-time intraoperative application of machine vision-based anatomical guidance in neurosurgery
Background and Objectives: We report the first intraoperative deployment of a real-time machine vision system in neurosurgery, derived from our previous anatomical detection work, automatically identifying structures during endoscopic endonasal surgery. Existing systems demonstrate promising performance in offline anatomical recognition, yet so far none have been implemented during live operations. Methods: A real-time anatomy detection model was trained using the YOLOv8 architecture (Ultralytics). Following training completion in the PyTorch environment, the model was exported to ONNX format and further optimized using the NVIDIA TensorRT engine. Deployment was carried out using the NVIDIA Holoscan SDK, the system ran on an NVIDIA Clara AGX developer kit. We used the model for real-time recognition of intraoperative anatomical structures and compared it with the same video labelled manually as reference. Model performance was reported using the average precision at an intersection-over-union threshold of 0.5 (AP50). Furthermore, end-to-end delay from frame acquisition to the display of the annotated output was measured. Results: A mean AP50 of 0.56 was achieved. The model demonstrated reliable detection of the most relevant landmarks in the transsphenoidal corridor. The mean end-to-end latency of the model was 47.81 ms (median 46.57 ms). Conclusion: For the first time, we demonstrate that clinical-grade, real-time machine-vision assistance during neurosurgery is feasible and can provide continuous, automated anatomical guidance from the surgical field. This approach may enhance intraoperative orientation, reduce cognitive load, and offer a powerful tool for surgical training. These findings represent an initial step toward integrating real-time AI support into routine neurosurgical workflows.
- Open Access
Anomaly Detection by Clustering DINO Embeddings using a Dirichlet Process Mixture
In this work, we leverage informative embeddings from foundational models for unsupervised anomaly detection in medical imaging. For small datasets, a memory-bank of normative features can directly be used for anomaly detection which has been demonstrated recently. However, this is unsuitable for large medical datasets as the computational burden increases substantially. Therefore, we propose to model the distribution of normative DINOv2 embeddings with a Dirichlet Process Mixture model (DPMM), a non-parametric mixture model that automatically adjusts the number of mixture components to the data at hand. Rather than using a memory bank, we use the similarity between the component centers and the embeddings as anomaly score function to create a coarse anomaly segmentation mask. Our experiments show that through DPMM embeddings of DINOv2, despite being trained on natural images, achieve very competitive anomaly detection performance on medical imaging benchmarks and can do this while at least halving the computation time at inference. Our analysis further indicates that normalized DINOv2 embeddings are generally more aligned with anatomical structures than unnormalized features, even in the presence of anomalies, making them great representations for anomaly detection. The code is available at https://github.com/NicoSchulthess/anomalydino-dpmm.
Open AccessAnomaly Detection by Clustering DINO Embeddings using a Dirichlet Process Mixture
In this work, we leverage informative embeddings from foundational models for unsupervised anomaly detection in medical imaging. For small datasets, a memory-bank of normative features can directly be used for anomaly detection which has been demonstrated recently. However, this is unsuitable for large medical datasets as the computational burden increases substantially. Therefore, we propose to model the distribution of normative DINOv2 embeddings with a Dirichlet Process Mixture model (DPMM), a non-parametric mixture model that automatically adjusts the number of mixture components to the data at hand. Rather than using a memory bank, we use the similarity between the component centers and the embeddings as anomaly score function to create a coarse anomaly segmentation mask. Our experiments show that through DPMM embeddings of DINOv2, despite being trained on natural images, achieve very competitive anomaly detection performance on medical imaging benchmarks and can do this while at least halving the computation time at inference. Our analysis further indicates that normalized DINOv2 embeddings are generally more aligned with anatomical structures than unnormalized features, even in the presence of anomalies, making them great representations for anomaly detection. The code is available at https://github.com/NicoSchulthess/anomalydino-dpmm.
- 21 September 2025
- Published by Springer Nature
- p. 46-56
Anomaly Detection by Clustering DINO Embeddings Using a Dirichlet Process Mixture
- 21 September 2025
- Published by Springer Nature
- p. 46-56
Anomaly Detection by Clustering DINO Embeddings Using a Dirichlet Process Mixture
- Open Access
- 15 July 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 105, 103705
Learning to segment anatomy and lesions from disparately labeled sources in brain MRI
- 15 July 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 105, 103705
Open AccessLearning to segment anatomy and lesions from disparately labeled sources in brain MRI
- Open Access
- 19 June 2025
- Published by Springer Nature in Visual Intelligence
- Vol. 3 (1) , 1-14
When SAM2 meets video camouflaged object segmentation: a comprehensive evaluation and adaptation
This study investigates the application and performance of the Segment Anything Model 2 (SAM2) in the challenging task of video camouflaged object segmentation (VCOS). VCOS involves detecting objects that blend seamlessly in the surroundings for videos due to similar colors and textures and poor light conditions. Compared to the objects in normal scenes, camouflaged objects are much more difficult to detect. SAM2, a video foundation model, has shown potential in various tasks. However, its effectiveness in dynamic camouflaged scenarios remains under-explored. This study presents a comprehensive study on SAM2’s ability in VCOS. First, we assess SAM2’s performance on camouflaged video datasets using different models and prompts (click, box, and mask). Second, we explore the integration of SAM2 with existing multimodal large language models (MLLMs) and VCOS methods. Third, we specifically adapt SAM2 by fine-tuning it on the video camouflaged dataset. Our comprehensive experiments demonstrate that SAM2 has the excellent zero-shot ability to detect camouflaged objects in videos. We also show that this ability could be further improved by specifically adjusting SAM2’s parameters for VCOS.
- 19 June 2025
- Published by Springer Nature in Visual Intelligence
- Vol. 3 (1) , 1-14
Open AccessWhen SAM2 meets video camouflaged object segmentation: a comprehensive evaluation and adaptation
This study investigates the application and performance of the Segment Anything Model 2 (SAM2) in the challenging task of video camouflaged object segmentation (VCOS). VCOS involves detecting objects that blend seamlessly in the surroundings for videos due to similar colors and textures and poor light conditions. Compared to the objects in normal scenes, camouflaged objects are much more difficult to detect. SAM2, a video foundation model, has shown potential in various tasks. However, its effectiveness in dynamic camouflaged scenarios remains under-explored. This study presents a comprehensive study on SAM2’s ability in VCOS. First, we assess SAM2’s performance on camouflaged video datasets using different models and prompts (click, box, and mask). Second, we explore the integration of SAM2 with existing multimodal large language models (MLLMs) and VCOS methods. Third, we specifically adapt SAM2 by fine-tuning it on the video camouflaged dataset. Our comprehensive experiments demonstrate that SAM2 has the excellent zero-shot ability to detect camouflaged objects in videos. We also show that this ability could be further improved by specifically adjusting SAM2’s parameters for VCOS.
- Open Access
AENEAS Project: Machine Vision-Based Real-Time Anatomy Detection. Application to the Pterional Trans-Sylvian Approach
Introduction: Surgical success hinges on two core factors: technical execution and cognitive planning. While the former can be trained and potentially augmented through robotics, the latter — developing an accurate “mental roadmap” of a certain operation — remains complex, deeply individualized and resistant to standardization. In neurosurgery, where minute anatomical distinctions can dictate outcomes, enhancing intraoperative guidance could reduce variability among surgeons and improve global standards. Recent developments in machine vision offer a promising avenue. Previous studies demonstrated that deep learning models could successfully identify anatomical landmarks in highly standardized procedures such as trans-sphenoidal surgery (TSS). However, the applicability of such techniques in more variable and multidimensional intracranial procedures remains unproven. This study investigates whether a deep learning model can recognize key anatomical structures during the more complex pterional trans-sylvian (PTS) approach. Materials and Methods: We developed a deep learning object detection model (YOLOv7x) trained on 5.307 labeled frames from 78 surgical videos of 76 patients undergoing PTS. Surgical steps were standardized, and key anatomical targets—frontal/temporal dura, inferior frontal/superior temporal gyri, optic and olfactory nerves and internal carotid artery (ICA) — were annotated by specifically trained neurosurgical residents and verified by the operating surgeon. Bounding boxes derived from segmentation masks served as training inputs. Performance was evaluated using five-fold cross-validation. Results: The model achieved promising detection performance for deep structures, particularly the optic nerve (AP 50 : 0.73) and ICA (AP 50 : 0.67). Superficial structures, like the dura and the cortical gyri, had lower precision (AP 50 range: 0.25–0.45), likely due to morphological similarity and optical variability. Performance variability across classes reflects the complexity of the anatomical setting along with data limitations. Conclusion: This study shows the feasibility of applying machine vision techniques for anatomical detection in a complex and variable neurosurgical setting. While challenges remain in detecting less distinctive structures, the high accuracy achieved for deep anatomical landmarks validates this approach. These findings mark an essential step towards a machine vision surgical guidance system. Future applications could include real-time anatomical recognition, integration with neuronavigation and the development of AI-supported “surgical roadmaps” to improve intraoperative orientation and global neurosurgical practice.
Open AccessAENEAS Project: Machine Vision-Based Real-Time Anatomy Detection. Application to the Pterional Trans-Sylvian Approach
Introduction: Surgical success hinges on two core factors: technical execution and cognitive planning. While the former can be trained and potentially augmented through robotics, the latter — developing an accurate “mental roadmap” of a certain operation — remains complex, deeply individualized and resistant to standardization. In neurosurgery, where minute anatomical distinctions can dictate outcomes, enhancing intraoperative guidance could reduce variability among surgeons and improve global standards. Recent developments in machine vision offer a promising avenue. Previous studies demonstrated that deep learning models could successfully identify anatomical landmarks in highly standardized procedures such as trans-sphenoidal surgery (TSS). However, the applicability of such techniques in more variable and multidimensional intracranial procedures remains unproven. This study investigates whether a deep learning model can recognize key anatomical structures during the more complex pterional trans-sylvian (PTS) approach. Materials and Methods: We developed a deep learning object detection model (YOLOv7x) trained on 5.307 labeled frames from 78 surgical videos of 76 patients undergoing PTS. Surgical steps were standardized, and key anatomical targets—frontal/temporal dura, inferior frontal/superior temporal gyri, optic and olfactory nerves and internal carotid artery (ICA) — were annotated by specifically trained neurosurgical residents and verified by the operating surgeon. Bounding boxes derived from segmentation masks served as training inputs. Performance was evaluated using five-fold cross-validation. Results: The model achieved promising detection performance for deep structures, particularly the optic nerve (AP 50 : 0.73) and ICA (AP 50 : 0.67). Superficial structures, like the dura and the cortical gyri, had lower precision (AP 50 range: 0.25–0.45), likely due to morphological similarity and optical variability. Performance variability across classes reflects the complexity of the anatomical setting along with data limitations. Conclusion: This study shows the feasibility of applying machine vision techniques for anatomical detection in a complex and variable neurosurgical setting. While challenges remain in detecting less distinctive structures, the high accuracy achieved for deep anatomical landmarks validates this approach. These findings mark an essential step towards a machine vision surgical guidance system. Future applications could include real-time anatomical recognition, integration with neuronavigation and the development of AI-supported “surgical roadmaps” to improve intraoperative orientation and global neurosurgical practice.
- Open Access
- 26 March 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1
Author Correction: Predicting mortality after transcatheter aortic valve replacement using preprocedural CT
- 26 March 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1
Open AccessAuthor Correction: Predicting mortality after transcatheter aortic valve replacement using preprocedural CT
- Open Access
- 19 November 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1
Author Correction: Predicting standardized uptake value of brown adipose tissue from CT scans using convolutional neural networks
- 19 November 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1
Open AccessAuthor Correction: Predicting standardized uptake value of brown adipose tissue from CT scans using convolutional neural networks