Mehmet Yiğitsoy
YOU?
Author Swipe
View article: Metadata-Aligned 3D MRI Representations for Contrast Understanding and Quality Control
Metadata-Aligned 3D MRI Representations for Contrast Understanding and Quality Control Open
Magnetic Resonance Imaging suffers from substantial data heterogeneity and the absence of standardized contrast labels across scanners, protocols, and institutions, which severely limits large-scale automated analysis. A unified representa…
View article: Differentially Private Active Learning: Balancing Effective Data Selection and Privacy
Differentially Private Active Learning: Balancing Effective Data Selection and Privacy Open
Active learning (AL) is a widely used technique for optimizing data labeling in machine learning by iteratively selecting, labeling, and training on the most informative data. However, its integration with formal privacy-preserving methods…
View article: Simulation of acquisition shifts in T2 weighted fluid-attenuated inversion recovery magnetic resonance images to stress test artificial intelligence segmentation networks
Simulation of acquisition shifts in T2 weighted fluid-attenuated inversion recovery magnetic resonance images to stress test artificial intelligence segmentation networks Open
We show that these deviations are in the range of values as may be caused by erroneous or individual differences in relaxation times as described by literature. The coefficients of the F1 model function allow for a quantitative comparison …
View article: Simulation of acquisition shifts in T2 Flair MR images to stress test AI segmentation networks
Simulation of acquisition shifts in T2 Flair MR images to stress test AI segmentation networks Open
Purpose: To provide a simulation framework for routine neuroimaging test data, which allows for "stress testing" of deep segmentation networks against acquisition shifts that commonly occur in clinical practice for T2 weighted (T2w) fluid …
View article: Faster and Better: How Anomaly Detection Can Accelerate and Improve Reporting of Head Computed Tomography
Faster and Better: How Anomaly Detection Can Accelerate and Improve Reporting of Head Computed Tomography Open
Background: Most artificial intelligence (AI) systems are restricted to solving a pre-defined task, thus limiting their generalizability to unselected datasets. Anomaly detection relieves this shortfall by flagging all pathologies as devia…
View article: Automated Detection of Ischemic Stroke and Subsequent Patient Triage in Routinely Acquired Head CT
Automated Detection of Ischemic Stroke and Subsequent Patient Triage in Routinely Acquired Head CT Open
Purpose Advanced machine-learning (ML) techniques can potentially detect the entire spectrum of pathology through deviations from a learned norm. We investigated the utility of a weakly supervised ML tool to detect characteristic findings …
View article: Deep Attention Based Semi-supervised 2D-Pose Estimation for Surgical Instruments
Deep Attention Based Semi-supervised 2D-Pose Estimation for Surgical Instruments Open
View article: Microaneurysms segmentation and diabetic retinopathy detection by learning discriminative representations
Microaneurysms segmentation and diabetic retinopathy detection by learning discriminative representations Open
Deep learning techniques are recently being used in fundus image analysis and diabetic retinopathy detection. Microaneurysms are important indicators of diabetic retinopathy progression. The authors introduce a two‐stage deep learning appr…
View article: Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical\n Instruments
Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical\n Instruments Open
For many practical problems and applications, it is not feasible to create a\nvast and accurately labeled dataset, which restricts the application of deep\nlearning in many areas. Semi-supervised learning algorithms intend to improve\nperf…
View article: Deep learning for automatic diabetic retinopathy detection under multiple image quality levels
Deep learning for automatic diabetic retinopathy detection under multiple image quality levels Open
View article: Deep learning for automatic diabetic retinopathy grading of ultra-widefield fundus images
Deep learning for automatic diabetic retinopathy grading of ultra-widefield fundus images Open
View article: Multi-scale Microaneurysms Segmentation Using Embedding Triplet Loss
Multi-scale Microaneurysms Segmentation Using Embedding Triplet Loss Open
View article: Tissue Phenomics for prognostic biomarker discovery in low- and intermediate-risk prostate cancer
Tissue Phenomics for prognostic biomarker discovery in low- and intermediate-risk prostate cancer Open
View article: Local and Global Consistency Measures in Intensity-based Medical Image Registration
Local and Global Consistency Measures in Intensity-based Medical Image Registration Open
This thesis investigates local and global structural consistency measures to be used as regularization constraints in intensity-based registration of partial images for field-of-view extension. The proposed measures are employed in cases w…