Multicenter Morphometric Analysis of Stratum Corneum Nanotexture for Skin Barrier Assessment

Jen-Hung Wang, Chia-Yu Chu, Felipe Colombelli, Ching-Wen Du, Maria Oberländer Christensen, Jorge Pereda, Ivone Jakasa, Sanja Kezic, Jacob P. Thyssen, Edwin En-Te Hwu, Gisele Miranda
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:4316-4341, 2026.

Abstract

Stratum corneum nanotexture (SCN) has emerged as a promising non-invasive biomarker for quantifying skin barrier impairment and the severity of inflammatory skin diseases such as atopic dermatitis (AD). In this multicenter study, we analyzed stratum corneum tape-strip samples from 90 patients with AD and 30 healthy controls recruited in Taiwan and Denmark, yielding a heterogeneous dataset of more than 2,000 SCN images. Participants were evenly stratified into four AD severity groups defined by the Eczema Area and Severity Index (EASI), enabling robust evaluation of SCN-derived metrics across the full spectrum of disease severity. Previous studies have primarily relied on count-based measures to quantify the density of circular nano-size objects (CNOs) in SCN images from single-center cohorts, without leveraging instance-level segmentation or comprehensive morphometric profiling. In this study, we propose and validate a segmentation-based SCN analysis pipeline that integrates YOLOv12 with Segment Anything Model 3 (SAM3) for accurate CNO delineation in a multicenter setting. This framework enables the extraction of detailed morphometric descriptors and facilitates systematic evaluation of SCN-derived biomarkers for quantitative skin barrier assessment in AD.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-wang26h, title = {Multicenter Morphometric Analysis of Stratum Corneum Nanotexture for Skin Barrier Assessment}, author = {Wang, Jen-Hung and Chu, Chia-Yu and Colombelli, Felipe and Du, Ching-Wen and Christensen, Maria Oberl\"ander and Pereda, Jorge and Jakasa, Ivone and Kezic, Sanja and Thyssen, Jacob P. and Hwu, Edwin En-Te and Miranda, Gisele}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {4316--4341}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/wang26h/wang26h.pdf}, url = {https://proceedings.mlr.press/v315/wang26h.html}, abstract = {Stratum corneum nanotexture (SCN) has emerged as a promising non-invasive biomarker for quantifying skin barrier impairment and the severity of inflammatory skin diseases such as atopic dermatitis (AD). In this multicenter study, we analyzed stratum corneum tape-strip samples from 90 patients with AD and 30 healthy controls recruited in Taiwan and Denmark, yielding a heterogeneous dataset of more than 2,000 SCN images. Participants were evenly stratified into four AD severity groups defined by the Eczema Area and Severity Index (EASI), enabling robust evaluation of SCN-derived metrics across the full spectrum of disease severity. Previous studies have primarily relied on count-based measures to quantify the density of circular nano-size objects (CNOs) in SCN images from single-center cohorts, without leveraging instance-level segmentation or comprehensive morphometric profiling. In this study, we propose and validate a segmentation-based SCN analysis pipeline that integrates YOLOv12 with Segment Anything Model 3 (SAM3) for accurate CNO delineation in a multicenter setting. This framework enables the extraction of detailed morphometric descriptors and facilitates systematic evaluation of SCN-derived biomarkers for quantitative skin barrier assessment in AD.} }
Endnote
%0 Conference Paper %T Multicenter Morphometric Analysis of Stratum Corneum Nanotexture for Skin Barrier Assessment %A Jen-Hung Wang %A Chia-Yu Chu %A Felipe Colombelli %A Ching-Wen Du %A Maria Oberländer Christensen %A Jorge Pereda %A Ivone Jakasa %A Sanja Kezic %A Jacob P. Thyssen %A Edwin En-Te Hwu %A Gisele Miranda %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-wang26h %I PMLR %P 4316--4341 %U https://proceedings.mlr.press/v315/wang26h.html %V 315 %X Stratum corneum nanotexture (SCN) has emerged as a promising non-invasive biomarker for quantifying skin barrier impairment and the severity of inflammatory skin diseases such as atopic dermatitis (AD). In this multicenter study, we analyzed stratum corneum tape-strip samples from 90 patients with AD and 30 healthy controls recruited in Taiwan and Denmark, yielding a heterogeneous dataset of more than 2,000 SCN images. Participants were evenly stratified into four AD severity groups defined by the Eczema Area and Severity Index (EASI), enabling robust evaluation of SCN-derived metrics across the full spectrum of disease severity. Previous studies have primarily relied on count-based measures to quantify the density of circular nano-size objects (CNOs) in SCN images from single-center cohorts, without leveraging instance-level segmentation or comprehensive morphometric profiling. In this study, we propose and validate a segmentation-based SCN analysis pipeline that integrates YOLOv12 with Segment Anything Model 3 (SAM3) for accurate CNO delineation in a multicenter setting. This framework enables the extraction of detailed morphometric descriptors and facilitates systematic evaluation of SCN-derived biomarkers for quantitative skin barrier assessment in AD.
APA
Wang, J., Chu, C., Colombelli, F., Du, C., Christensen, M.O., Pereda, J., Jakasa, I., Kezic, S., Thyssen, J.P., Hwu, E.E. & Miranda, G.. (2026). Multicenter Morphometric Analysis of Stratum Corneum Nanotexture for Skin Barrier Assessment. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:4316-4341 Available from https://proceedings.mlr.press/v315/wang26h.html.

Related Material