A. Murat Maga

This paper introduces a label-informed image registration method that improves registration accuracy for challenging datasets, particularly in developmental studies.

The paper evaluates dense semilandmarks and sliding techniques in 3D geometric morphometrics using real and simulated mouse skull data, finding that sliding can improve or harm results depending on correspondence quality.

This paper introduces a consensus atlas generation method to reduce reference bias in automated landmarking, showing improved reproducibility and reduced variance across datasets.

The paper introduces an open-source photogrammetry workflow using 3D Slicer and SlicerMorph to generate high-quality 3D models of biological specimens, showing improved accuracy over existing methods.

The paper develops a focal-loss transformer model to detect exencephaly in imbalanced micro-CT embryo data, achieving high accuracy and interpretable saliency maps.

The paper introduces a semi-automated pipeline to quantify craniofacial asymmetry in fetal mouse imaging, identifying gene knockout strains with significant asymmetry.

This paper introduces a 3D morphological simulation approach to test phenotype detection methods, showing that detectability depends on effect size, sample size, and ROI selection.

This paper develops a deep learning method for automatic landmark acquisition in geometric morphometrics, showing it is faster and comparable in accuracy to existing methods on rodent mandible datasets.

This study evaluates a semi-automated tool to quantify craniofacial variations in zebrafish models of human skeletal diseases, finding phenotypic differences for four genes and parallels to human symptoms for two.

This paper introduces MEMOS, a deep learning tool for segmenting 50 anatomical structures in mouse embryos, validated against atlas-based methods and knockout strain data.

This paper uses computational anatomy to quantify 3D craniofacial phenotypes in zebrafish mutants, identifying shape differences in bmp1a mutants.