AAD
Author: Willhemenia Loremipsum Special session: Lorem ipsum dolor sit amet Category: Lorem ipsum View all results

Please login or create an account. If you do not have access to this content, you will be shown a 30 second preview and licensing options.

  • Presentation

Updates: Digital Pathology and Artificial Intelligence in Dermatopathology

Description

This presentation discusses the integration of digital pathology and artificial intelligence (AI) in dermatopathology, focusing on their applications, educational benefits, and associated challenges. Digital pathology is transforming diagnosis accuracy, improving intra-observer concordance from 87% to 94% over time, and allowing for effective remote consultations, with an average review time of approximately 10 minutes per slide. AI, especially deep learning, is enhancing diagnostic capabilities by automating processes such as surgical margin assessments and differentiating between various skin lesions. While initial interactions with digital tools can be slow and cumbersome, they ultimately improve workflow efficiency and flexibility. Additionally, educational methods leveraging digital slides allow for more personalized learning, integrating quizzes and video content that cater to resident preferences. However, concerns include the potential loss of competency with glass slides and the need for comprehensive training, particularly as AI algorithms may not be universally applicable. As dermatopathologists navigate the transition to digital systems, they must also weigh the significant financial and operational investments against potential long-term benefits. The future of dermatopathology seems promising with AI augmenting diagnostic precision, but it necessitates careful consideration of algorithm reliability, data privacy, and ethical implications.

View more

Conclusions

  • Digital pathology using whole-slide imaging (WSI) has shown significant accuracy improvements for dermatopathology diagnoses, with intraobserver concordance increasing to 94%.
  • Digital slides are feasible for virtual consultations during Mohs micrographic surgery, achieving a high accuracy rate of 97.2%.
  • Interactive educational tools using digital pathology enhance the learning experience for residents, improving their diagnostic skills and preferences towards virtual slides over glass slides.
  • Residents now prefer digital pathology for its flexibility and convenience, enabling better preparation for board exams.
  • While digital slides improve efficiency and diagnostic accuracy, there is a concern about potential loss of competency with traditional glass slides.
  • The transition to digital pathology involves significant financial investment and operational adjustments, but potential savings may arise from decreased slide requests and improved case turnaround times.
  • Deep learning algorithms in dermatopathology can assist in tasks such as melanoma classification and prognosis prediction, displaying high accuracy while improving the efficiency of pathologists' workflows.
  • Challenges remain in implementing AI, including necessary training datasets, managing learning biases, and ethical concerns regarding data use and privacy.
  • The majority of pathologists express a positive attitude towards AI in dermatopathology, believing it will enhance their practice rather than replace them.
  • Shah KK, Lehman JS, Gibson LE, et al. Validation of diagnostic accuracy with whole-slide imaging compared with glass slide review in dermatopathology. J Am Acad Dermatol. 2016 Dec;75(6):1229-1237.
  • Kent MN, Olsen TG, Feeser TA, et al. Diagnostic Accuracy of Virtual Pathology vs Traditional Microscopy in a Large Dermatopathology Study. JAMA Dermatol. 2017 Dec 1;153(12):1285-1291.
  • Onega T, Barnhill RL, Piepkorn MW, et al. Accuracy of Digital Pathologic Analysis vs Traditional Microscopy in the Interpretation of Melanocytic Lesions. JAMA Dermatol. 2018 Oct 1;154(10):1159-1166.
  • Marsch AF, Espiritu B, Groth J, Hutchens KA. The effectiveness of annotated (vs. non-annotated) digital pathology slides as a teaching tool during dermatology and pathology residencies. J Cutan Pathol. 2014.
  • Harrell J, Nielson C, Konda S, Motaparthi K. Validation of Whole Slide Imaging for Intraoperative Consultation During Mohs Micrographic Surgery. Dermatol Surg. 2021 May 1;47(5):703-705.
  • Gertz R, Longley BJ, Bennett D, Ranheim E, Rajamanickam V, Kawahara T, Endo J. Integrating virtual dermatopathology as part of formative and summative assessment of residents: a feasibility pilot study. J Cutan Pathol. 2015.
  • Ullah E, Parwani A, Baig MM, Singh R. Challenges and barriers of using large language models (LLM) such as ChatGPT for diagnostic medicine with a focus on digital pathology - a recent scoping review. Diagn Pathol. 2024 Feb 27;19(1):43.
  • Geijs DJ, Hillen LM, Dooper S, Winnepenninckx V, Varra V, Carr DR, Shahwan KT, Litjens G, Amir A. Weakly Supervised Classification of Mohs Surgical Sections Using Artificial Intelligence. Mod Pathol. 2025 Feb;38(2):100653.
  • Kulkarni PM, Robinson EJ, Sarin Pradhan J, et al. Deep Learning Based on Standard H&E Images of Primary Melanoma Tumors Identifies Patients at Risk for Visceral Recurrence and Death. Clin Cancer Res. 2020;26(5):1126-1134.
  • Requa J, Godard T, Mandal R, et al. High-fidelity detection, subtyping, and localization of five skin neoplasms using supervised and semi-supervised learning. J Pathol Inform. 2022;14:100159.