DERMA-OCTA: A Comprehensive Dataset and Preprocessing Pipeline for Dermatological OCTA Vessel Segmentation

Abstract Optical coherence tomography angiography (OCTA) has emerged as a promising tool for non-invasive vascular imaging in dermatology. However, the field lacks standardized methods for processing and analyzing these complex images, as well as sufficient annotated datasets for developing automate...

Full description

Saved in:
Bibliographic Details
Main Authors: Giulia Rotunno, Massimo Salvi, Julia Deinsberger, Lisa Krainz, Benedikt Weber, Christoph Sinz, Harald Kittler, Leopold Schmetterer, Wolfgang Drexler, Mengyang Liu, Kristen M. Meiburger
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-05763-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226659805265920
author Giulia Rotunno
Massimo Salvi
Julia Deinsberger
Lisa Krainz
Benedikt Weber
Christoph Sinz
Harald Kittler
Leopold Schmetterer
Wolfgang Drexler
Mengyang Liu
Kristen M. Meiburger
author_facet Giulia Rotunno
Massimo Salvi
Julia Deinsberger
Lisa Krainz
Benedikt Weber
Christoph Sinz
Harald Kittler
Leopold Schmetterer
Wolfgang Drexler
Mengyang Liu
Kristen M. Meiburger
author_sort Giulia Rotunno
collection DOAJ
description Abstract Optical coherence tomography angiography (OCTA) has emerged as a promising tool for non-invasive vascular imaging in dermatology. However, the field lacks standardized methods for processing and analyzing these complex images, as well as sufficient annotated datasets for developing automated analysis tools. We present DERMA-OCTA, the first open-access dermatological OCTA dataset, comprising 330 volumetric scans from 74 subjects with various skin conditions. The dataset contains the original 2D and 3D OCTA acquisitions, as well as versions processed with five different preprocessing methods, and the reference 2D and 3D segmentations. For each version, segmentation labels are provided, generated using the U-Net architecture as 2D and 3D segmentation approaches. By providing high-resolution, annotated OCTA data across a range of skin pathologies, this dataset offers a valuable resource for training deep learning models, benchmarking segmentation algorithms, and facilitating research into non-invasive skin imaging. The DERMA-OCTA dataset is freely downloadable.
format Article
id doaj-art-9184fc9eadd24ff8b45087f311e13a3a
institution Kabale University
issn 2052-4463
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-9184fc9eadd24ff8b45087f311e13a3a2025-08-24T11:07:14ZengNature PortfolioScientific Data2052-44632025-08-0112111010.1038/s41597-025-05763-6DERMA-OCTA: A Comprehensive Dataset and Preprocessing Pipeline for Dermatological OCTA Vessel SegmentationGiulia Rotunno0Massimo Salvi1Julia Deinsberger2Lisa Krainz3Benedikt Weber4Christoph Sinz5Harald Kittler6Leopold Schmetterer7Wolfgang Drexler8Mengyang Liu9Kristen M. Meiburger10PolitoBIOMed Lab, Department of Electronics and Telecommunications, Politecnico di TorinoPolitoBIOMed Lab, Department of Electronics and Telecommunications, Politecnico di TorinoDepartment of Dermatology, Medical University of ViennaCenter for Medical Physics and Biomedical Engineering, Medical University of ViennaDepartment of Dermatology, Medical University of ViennaMelanoma Institute Australia, The University of SydneyDepartment of Dermatology, Medical University of ViennaCenter for Medical Physics and Biomedical Engineering, Medical University of ViennaCenter for Medical Physics and Biomedical Engineering, Medical University of ViennaCenter for Medical Physics and Biomedical Engineering, Medical University of ViennaPolitoBIOMed Lab, Department of Electronics and Telecommunications, Politecnico di TorinoAbstract Optical coherence tomography angiography (OCTA) has emerged as a promising tool for non-invasive vascular imaging in dermatology. However, the field lacks standardized methods for processing and analyzing these complex images, as well as sufficient annotated datasets for developing automated analysis tools. We present DERMA-OCTA, the first open-access dermatological OCTA dataset, comprising 330 volumetric scans from 74 subjects with various skin conditions. The dataset contains the original 2D and 3D OCTA acquisitions, as well as versions processed with five different preprocessing methods, and the reference 2D and 3D segmentations. For each version, segmentation labels are provided, generated using the U-Net architecture as 2D and 3D segmentation approaches. By providing high-resolution, annotated OCTA data across a range of skin pathologies, this dataset offers a valuable resource for training deep learning models, benchmarking segmentation algorithms, and facilitating research into non-invasive skin imaging. The DERMA-OCTA dataset is freely downloadable.https://doi.org/10.1038/s41597-025-05763-6
spellingShingle Giulia Rotunno
Massimo Salvi
Julia Deinsberger
Lisa Krainz
Benedikt Weber
Christoph Sinz
Harald Kittler
Leopold Schmetterer
Wolfgang Drexler
Mengyang Liu
Kristen M. Meiburger
DERMA-OCTA: A Comprehensive Dataset and Preprocessing Pipeline for Dermatological OCTA Vessel Segmentation
Scientific Data
title DERMA-OCTA: A Comprehensive Dataset and Preprocessing Pipeline for Dermatological OCTA Vessel Segmentation
title_full DERMA-OCTA: A Comprehensive Dataset and Preprocessing Pipeline for Dermatological OCTA Vessel Segmentation
title_fullStr DERMA-OCTA: A Comprehensive Dataset and Preprocessing Pipeline for Dermatological OCTA Vessel Segmentation
title_full_unstemmed DERMA-OCTA: A Comprehensive Dataset and Preprocessing Pipeline for Dermatological OCTA Vessel Segmentation
title_short DERMA-OCTA: A Comprehensive Dataset and Preprocessing Pipeline for Dermatological OCTA Vessel Segmentation
title_sort derma octa a comprehensive dataset and preprocessing pipeline for dermatological octa vessel segmentation
url https://doi.org/10.1038/s41597-025-05763-6
work_keys_str_mv AT giuliarotunno dermaoctaacomprehensivedatasetandpreprocessingpipelinefordermatologicaloctavesselsegmentation
AT massimosalvi dermaoctaacomprehensivedatasetandpreprocessingpipelinefordermatologicaloctavesselsegmentation
AT juliadeinsberger dermaoctaacomprehensivedatasetandpreprocessingpipelinefordermatologicaloctavesselsegmentation
AT lisakrainz dermaoctaacomprehensivedatasetandpreprocessingpipelinefordermatologicaloctavesselsegmentation
AT benediktweber dermaoctaacomprehensivedatasetandpreprocessingpipelinefordermatologicaloctavesselsegmentation
AT christophsinz dermaoctaacomprehensivedatasetandpreprocessingpipelinefordermatologicaloctavesselsegmentation
AT haraldkittler dermaoctaacomprehensivedatasetandpreprocessingpipelinefordermatologicaloctavesselsegmentation
AT leopoldschmetterer dermaoctaacomprehensivedatasetandpreprocessingpipelinefordermatologicaloctavesselsegmentation
AT wolfgangdrexler dermaoctaacomprehensivedatasetandpreprocessingpipelinefordermatologicaloctavesselsegmentation
AT mengyangliu dermaoctaacomprehensivedatasetandpreprocessingpipelinefordermatologicaloctavesselsegmentation
AT kristenmmeiburger dermaoctaacomprehensivedatasetandpreprocessingpipelinefordermatologicaloctavesselsegmentation