4 papers
Meta-D: Metadata-Aware Architectures for Brain Tumor Analysis and Missing-Modality Segmentation
SangHyuk Kim, Daniel Haehn, Sumientra Rampersad
We present Meta-D, an architecture that explicitly leverages categorical scanner metadata such as MRI sequence and plane orientation to guide feature extraction for brain tumor ana…
MRI Plane Orientation Detection using a Context-Aware 2.5D Model
SangHyuk Kim, Daniel Haehn, Sumientra Rampersad
Humans can easily identify anatomical planes (axial, coronal, and sagittal) on a 2D MRI slice, but automated systems struggle with this task. Missing plane orientation metadata can…
Melanoma Detection with Uncertainty Quantification
SangHyuk Kim, Edward Gaibor, Brian Matejek +1
Early detection of melanoma is crucial for improving survival rates. Current detection tools often utilize data-driven machine learning methods but often overlook the full integrat…
Boostlet.js: Image processing plugins for the web via JavaScript injection
Edward Gaibor, Shruti Varade, Rohini Deshmukh +5
Can web-based image processing and visualization tools easily integrate into existing websites without significant time and effort? Our Boostlet.js library addresses this challenge…