November 2024 in “Image Analysis & Stereology” This study introduced a novel, weakly supervised method for segmenting hair in Scanning Electron Microscope images using simple image-level annotations, achieving over 30% improvement in mean Hausdorff Distance compared to Unet and SAM, while enhancing interpretability and refinement.
6 citations
,
January 2022 in “Database” This database provides detailed physiological parameters of porcine skin to enhance the MPML MechDermA Model, improving dermal absorption predictions for human studies in the Simcyp Simulator.
March 2026 in “Mendeley Data” In this study, researchers developed an open-source browser-based tool to enhance the reproducibility and accuracy of SALT score calculations from scalp photos, aimed particularly at assessing partial regrowth in alopecia areata patients on JAK inhibitor therapy.
3 citations
,
July 2023 in “Nature Communications” This study introduced a multitask learning method to identify shortcut learning in clinical ML systems, revealing it's not always responsible for unfairness and emphasizing the necessity of comprehensive fairness approaches in medical AI.
March 2026 in “Mendeley Data” This tool was developed to enhance reproducibility and sensitivity in measuring partial hair regrowth in alopecia areata patients, particularly those undergoing JAK inhibitor therapy, using scalp photographs.