TY - JOUR
T1 - BT07 Creation of a skin lesion image pipeline
T2 - key steps in developing a mobile application with DICOM® fields and metadata
AU - Chin, Gillian X. M.
AU - Coon, Andrew
AU - Muthiah, Shareen
AU - Morton, Colin
AU - Fleming, Colin
AU - Wilde, Chris
PY - 2023/6/26
Y1 - 2023/6/26
N2 - A key issue facing artificial intelligence (AI) for dermatology is the lack of standardization around capture, transfer and storage of skin images and clinical data. To assist systematic capture of clinical data, we developed a nationally agreed proposed minimum dataset, based on Digital Imaging and Communications in Medicine (DICOM®) standards. Subsequently, we collaborated with an established image management system (IMS) supplier, Waba [supported by grants from our local National Health Service (NHS) innovation department], to incorporate these fields into a dermatology-specific mobile application (app), facilitating real-time capture and data transfer. We describe our steps in developing this app. The app integrates with the national Patient Administration System (SCI Store), allowing retrieval of real-time patient demographics linked to hospital or Community Health Index number. Each care episode captures a standardized dataset, including lesion views, clinical information and consent level. On episode completion, datasets are securely transferred to the IMS via WiFi or GPRS signal, following a fully auditable pathway. The IMS is a web-based app developed on a Microsoft Structured Query Language server, which allows authenticated users to access our trust’s centralized repository of nonradiological images. Adherence to industry-standard data storage format, patient safety reporting and specific access rights ensure compliance with Caldicott recommendations and data protection standards. For AI research, we are exploring conversion of datasets into DICOM format. Close collaboration between software developers and end users, including clinical photography, dermatology and general practice, was essential for app design. We worked on design architecture through fortnightly technical meetings, scheduled to progress development in months 1–8. Installation and functionality testing was performed in months 9 and 10, followed by comprehensive user testing in months 10–12. Live app test-of-change rollout was performed in months 13–16, with continued usability refinement during this period. To develop a standardized minimum dataset, we conducted a consensus exercise with the British Association of Dermatology AI working group. Based on DICOM standards, a comprehensive international standard for medical imaging, this could improve the quality, availability and interoperability of data for AI development. In summary, we have developed an app to standardize the capture, transmission and storage of skin lesion images and associated metadata. By collaborating with an industry partner with NHS experience, iterative user-led design and national engagement for standard-setting, we believe this is a useful step toward a national UK skin database for training and validating AI systems. Future work is planned to evaluate the output of this data pipeline.
AB - A key issue facing artificial intelligence (AI) for dermatology is the lack of standardization around capture, transfer and storage of skin images and clinical data. To assist systematic capture of clinical data, we developed a nationally agreed proposed minimum dataset, based on Digital Imaging and Communications in Medicine (DICOM®) standards. Subsequently, we collaborated with an established image management system (IMS) supplier, Waba [supported by grants from our local National Health Service (NHS) innovation department], to incorporate these fields into a dermatology-specific mobile application (app), facilitating real-time capture and data transfer. We describe our steps in developing this app. The app integrates with the national Patient Administration System (SCI Store), allowing retrieval of real-time patient demographics linked to hospital or Community Health Index number. Each care episode captures a standardized dataset, including lesion views, clinical information and consent level. On episode completion, datasets are securely transferred to the IMS via WiFi or GPRS signal, following a fully auditable pathway. The IMS is a web-based app developed on a Microsoft Structured Query Language server, which allows authenticated users to access our trust’s centralized repository of nonradiological images. Adherence to industry-standard data storage format, patient safety reporting and specific access rights ensure compliance with Caldicott recommendations and data protection standards. For AI research, we are exploring conversion of datasets into DICOM format. Close collaboration between software developers and end users, including clinical photography, dermatology and general practice, was essential for app design. We worked on design architecture through fortnightly technical meetings, scheduled to progress development in months 1–8. Installation and functionality testing was performed in months 9 and 10, followed by comprehensive user testing in months 10–12. Live app test-of-change rollout was performed in months 13–16, with continued usability refinement during this period. To develop a standardized minimum dataset, we conducted a consensus exercise with the British Association of Dermatology AI working group. Based on DICOM standards, a comprehensive international standard for medical imaging, this could improve the quality, availability and interoperability of data for AI development. In summary, we have developed an app to standardize the capture, transmission and storage of skin lesion images and associated metadata. By collaborating with an industry partner with NHS experience, iterative user-led design and national engagement for standard-setting, we believe this is a useful step toward a national UK skin database for training and validating AI systems. Future work is planned to evaluate the output of this data pipeline.
U2 - 10.1093/bjd/ljad113.373
DO - 10.1093/bjd/ljad113.373
M3 - Article
SN - 0007-0963
VL - 188
SP - iv173-iv174
JO - British Journal of Dermatology
JF - British Journal of Dermatology
IS - Supplement_4
M1 - ljad113.373
ER -