Automated Quality Assessment and Protocol Adherence in Teledermatology Image Acquisition

• Rodrigo P. S. Ribeiro UFSC
• Aldo von Wangenheim UFSC

DOI: https://doi.org/10.5753/sbcas_estendido.2024.2256

Abstract

This work addresses the neglected aspect of image quality assessment and adherence to acquisition protocols in teledermatology, proposing machine learning for automation. It focuses on two protocols: Approximation Image and Panoramic Image, predominant in STT/SC exam protocols. Validation involved standard machine learning metrics and an inter-rater agreement study with 11 dermatologists. The combined approach achieved an agreement of 96.68% in an inter-rater study, demonstrating the potential of this automation of image quality assessment and protocol adherence in teledermatology in streamlining specialized analysis.

References

Chan, S., Reddy, V., Myers, B., Thibodeaux, Q., Brownstone, N., and Liao, W. (2020). Machine learning in dermatology: Current applications, opportunities, and limitations. Dermatology and Therapy, 10(3):365–386. Publisher: Springer Science and Business Media LLC.

High, W., Houston, M., Calobrisi, S., Drage, L., and McEvoy, M. (2000). Assessment of the accuracy of low-cost store-and-forward teledermatology consultation. Journal of the American Academy of Dermatology, 42:776–83.

Inacio, A. d. S., Andrade, R., Wangenheim, A. v., and Macedo, D. D. J. (2014). Designing an information retrieval system for the STT/SC. In 2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom). IEEE.

INCA (2023). Estimate | 2023 Cancer Incidence in Brazil. Instituto Nacional de Câncer (Brasil).

Lasierra, N., Alesanco, A., Gilaberte, Y., Magallón-Botaya, R., and García, J. (2012). Lessons learned after a three-year store and forward teledermatology experience using internet: Strengths and limitations. International journal of medical informatics, 81:332–43.

Levin, Y. and Warshaw, E. (2009). Teledermatology: A review of reliability and accuracy of diagnosis and management. Dermatologic clinics, 27:163–76, vii.

Mckoy, K., Antoniotti, N., Armstrong, A., Bashshur, R., Bernard, J., Bernstein, D., Burdick, A., Edison, K., Goldyne, M., Kovarik, C., Krupinski, E., Kvedar, J., Larkey, J., Lee-Keltner, I., Lipoff, J., Oh, D., Pak, H., Seraly, M., Siegel, D., and Whited, J. (2016). Practice guidelines for teledermatology. Telemedicine and e-Health, 22.

Navarrete-Dechent, C., Dusza, S. W., Liopyris, K., Marghoob, A. A., Halpern, A. C., and Marchetti, M. A. (2018). Automated dermatological diagnosis: Hype or reality? Journal of Investigative Dermatology, 138(10):2277–2279.

Nobre, L. F. and von Wangenheim, A. (2012). Development and implementation of a statewide telemedicine/telehealth system in the state of santa catarina, brazil. In Technology Enabled Knowledge Translation for eHealth: Principles and Practice, pages 379–400. Springer New York, New York, NY.

Pai, V. V. and Pai, R. B. (2021). Artificial intelligence in dermatology and healthcare: An overview. Indian Journal of Dermatology, Venereology and Leprology, 0:1–11. Publisher: Scientific Scholar.

Pompl, R., Bunk, W., Dersch, D. R., Horsch, A., Stolz, W., Abmayr, W., Brauer, W., Gläßl, A., Schiffner, R., and Morfill, G. (1999). Charakterisierung der farbeigenschaften melanozytärer hautveränderungen zur unterstützung der früherkennung des malignen melanoms. In Informatik aktuell, pages 160–164. Springer Berlin Heidelberg.

Ribeiro, R. d. P. e. S. and von Wangenheim, A. (2024). Automated image quality and protocol adherence assessment of examinations in teledermatology: First results. Telemedicine and e-Health, 30(4):994–1005. PMID: 37930716.

Thomsen, K., Iversen, L., Titlestad, T. L., and Winther, O. (2019). Systematic review of machine learning for diagnosis and prognosis in dermatology. Journal of Dermatological Treatment, 31(5):496–510.

Wagner, H. M. and Picolotto de Lara, M. (2022). Manual teledermatologia: Técnico.

Wangenheim, A. v. and Nunes, D. H. (2018a). Creating a web infrastructure for the support of clinical protocols and clinical management: An example in teledermatology. Telemedicine and e-Health, 25:781–790.

Wangenheim, A. v. and Nunes, D. H. (2018b). Direct impact on costs of the teledermatology-centered patient triage in the state of santa catarina analysis of the 2014-2018 data. INCoD/UFSC.