Dermatology: Practical and Conceptual Research Letter | Dermatol Pract Concept. 2025;15(2):4896 1 International Survey on Dermoscopic Image Management: ISIC Data on Capture, Storage, and AI Integration in Dermatology Aarthi Parvathaneni1, Madison M. Taylor1,2, T. Austin Black1,2, Kelly C. Nelson2 1 John P. and Katherine G. McGovern Medical School at The University of Texas Health Science Center at Houston, Houston, Texas, USA 2 Department of Dermatology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA Citation: Parvathaneni A, Taylor MM, Black TA, Nelson KC. International Survey on Dermoscopic Image Management: ISIC Data on Capture, Storage, and AI Integration in Dermatology. Dermatol Pract Concept. 2025;15(2):4896. DOI: https://doi.org/10.5826/ dpc.1502a4896 Accepted: October 21, 2024; Published: April 2025 Copyright: ©2025 Parvathaneni et al. This is an open-access article distributed under the terms of the Creative Commons Attribution- NonCommercial License (BY-NC-4.0), https://creativecommons.org/licenses/by-nc/4.0/, which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original authors and source are credited. Key words: Dermoscopy, Dermatology, Image Storage, Database Management Systems, Artificial Intelligence Funding: None. Competing Interests: None. Authorship: All authors have contributed significantly to this publication. Corresponding Author: T. Austin Black, BS. 6431, Fannin St, Houston, TX 77030. ORCID ID: 0000-0001-9685-5078. E-mail: troy.a.black@uth.tmc.edu Introduction The International Skin Imaging Collaboration (ISIC) Archive is the largest repository of dermoscopic images available for educational purposes and the development and validation of artificial intelligence (AI) [1]. While the utilization of AI in skin cancer detection shows promise, current results are lim- ited, as datasets are predominantly composed of Caucasian patients [2]. Increasing the diversity of image uploads helps create a more representative dataset, which can be used to enhance the accuracy of AI. Additionally, because variations in image storage, query, and sharing exist globally and across practice types, broad investigation into industry practices can enhance archive development and utilization. In hopes of increasing diverse representation and overall utilization of the ISIC Archive, we surveyed dermatologists across the globe regarding image handling behaviors and opportunities to improve usability of the platform. Findings The MD Anderson IRB reviewed and approved a 22- question survey, distributed via the International Dermoscopy Soci- ety (IDS) website and ISIC email Listserv between October 6,2023 and February 6,2026 10/6/23 and 2/6/24. Collected data were both quantitative and qualitative in nature, with three reviewers (AP, MT, TAB) independently analyzing qual- itative data. A total of 228 responses were recorded, with the majority of respondents practicing in Europe (46.56%) in either independent (42.02%) or academic (25.46%) settings (Table 1). Common methods for image storage included per- sonal devices (45.09%), secure software (28.60%), and of- fice devices (24.63%), with 48.26% of respondents adding metadata to images (Supplementary Table S1). The majority of participants (87.20%) were unfamiliar with the ISIC Ar- chive. Top barriers to sharing images were legality (43.14%) and personal resources (29.41%). Respondents would be 2 Research Letter | Dermatol Pract Concept. 2025;15(2):4896 Table 1. Global Dermatology Image Use, Handling, and Sharing Practices Among Survey Respondents. Category Subcategory # (%) Respondent Demographics Geographic Location Europe 61 (46.5) N. America 20 (15.3) S. America 18 (13.7) Africa 12 (9.1) Asia 12 (9.1) Australia 8 (6.1) Practice Setting* Independent 137 (42.0) Hospital 89 (27.3) Academic 83 (25.5) Government Agency 12 (3.7) Image Sharing Are you familiar with the ISIC Archive? No 184 (87.2) Yes 27 (12.8) What would motivate you to share images with the ISIC Archive for educational purposes?* Self-Advancement 37 (25.3) 1.1 Acknowledgment of contribution 8 (5.5) 1.2 Financial incentives 5 (3.4) 1.3 Publication opportunities 11 (7.5) 1.4 Self-educational improvement 13 (8.9) Facilitation of process and assurance of platform security 61 (41.8) Community promotion 33 (22.6) No issues with sharing images 15 (10.3) What barriers would you anticipate in sharing images with the ISIC Archive for educational purposes?* Legality 66 (43.1) 1.1 HIPAA/Patient privacy 19 (12.4) 1.2 Hospital/Employer regulations 5 (3.3) 1.3 National regulations 6 (3.9) 1.4 Patient consent/Copyright 36 (23.5) Personal Resources 45 (29.4) No anticipated barriers 28 (18.3) Archive infrastructure 7 (4.6) Improper/Unauthorized use of uploaded images 7 (4.6) Image Handling After capturing clinical images, do youadd metadata? No 104 (51.7) Yes 97 (48.3) Research Letter | Dermatol Pract Concept. 2025;15(2):4896 3 more motivated to share their images through facilitation of the upload process and assurances of platform security (41.78%) (Supplementary Table S1). Additional data analy- sis can be found in Supplementary Table S1. Conclusions Two consistent themes were identified in the response con- tent: patient consent/privacy concerns and a lack of platform awareness. Given that dermoscopic images only capture approximately 12 millimeters of skin, they are considered de-identified and do not require consent for archiving or sharing. Open-source archives should include clear word- ing reassuring providers of their ability to store and share dermoscopic images. Additionally, providers wish to be made aware of available platforms and their usability, including access to platform training and/or straightforward upload- ing modalities. These implementations, along with promo- tion of platform availability, could increase engagement. Best practices for image technique and general storage have previously been reported [3, 4]. When dermoscopic image sharing is intended, our recommendations for efficient stor- age include removal of patient-identifying metadata, storage on an internet-accessible drive or device, and image/location labeling with the histopathologically confirmed diagnosis. Limitations This study was limited to ISIC and IDS members. Category Subcategory # (%) If yes, what metadata do you add?* 1 – Identification Information 87 (30.9) 1.1 Date 48 (17.0) 1.2 Patient identifier 30 (10.6) 1.3 Who took the photograph 9 (3.2) 2 – Clinical Notes 36 (12.8) 2.1 Actual diagnosis 22 (7.8) 2.2 Diagnostic clues 6 (2.1) 2.3 Pertinent patient medical history 8 (2.8) 3 – Image Description 36 (12.8) 3.1 General lesion description 11 (3.9) 3.2 Lesion evolution 1 (0.4) 3.3 Lesion location 20 (7.1) 3.4 Lesion size/measurement 2 (0.7) 3.5 Technical image specifications 2 (0.7) 4 – Yes, no further information provided 19 (6.7) How do you store clinical images?* Personal device 216 (45.1) Secure software (EMR) 137 (28.6) Office device 118 (24.6) Online Storage 6 (1.3) Does not store images 2 (0.4) Storage system security characteristics Secured 97 (42.9) Unsure 78 (34.5) Encrypted 29 (12.8) Neither 22 (9.7) *Respondents could indicate more than one response Table 1. Global Dermatology Image Use, Handling, and Sharing Practices Among Survey Respondents. (continued) 4 Research Letter | Dermatol Pract Concept. 2025;15(2):4896 2. Adamson AS, Smith A. Machine Learning and Health Care Dis- parities in Dermatology. JAMA Dermatol. 2018 Nov 1;154(11): 1247-1248. DOI: 10.1001/jamadermatol.2018.2348. PMID: 30073260. 3. Finnane A, Curiel-Lewandrowski C, Wimberley G, et al. Interna- tional Society of Digital Imaging of the Skin (ISDIS) for the Inter- national Skin Imaging Collaboration (ISIC). Proposed Technical Guidelines for the Acquisition of Clinical Images of Skin-Related Conditions. JAMA Dermatol. 2017 May 1;153(5):453-457. DOI: 10.1001/jamadermatol.2016.6214. PMID: 28241182. 4. Gandhi S, Kaliyadan F, Chatterjee K, Sharma A. “Storage, Backup and Archiving of Images”- E-Dermatology Task Force (IADVL Academy). Indian Dermatol Online J. 2022 May 5; 13(3):321-325. DOI: 10.4103/idoj.idoj_642_21. PMID: 3836 4421 The ISIC Archive is a promising database with significant potential for expanded reach and impact. This study high- lights generalized industry practices and beliefs regarding dermoscopic image handling, offering insights for optimiz- ing archive development and awareness. Addressing respon- dents’ concerns could encourage increased image uploads, enhance the database’s effectiveness for education and AI development, and ultimately improve disease identification. References 1. The International Skin Imaging Collaboration. ISIC, www.isic -archive.com/. Accessed 12 May 2023.