2024 detailed session2024-10-02T02:49:40+00:00

Detailed Session

Session

  • Title : AI: Advanced Eyes on skin
  • MERZ Room : Level 1, Hangang Hall, Avenue

Chair

Jane Yoo United States

Soo Ick Cho South Korea

Lecture & Speaker

HoursSpeakersTitle
14:40 - 14:56 Dongheon Lee

Application of deep learning in dermatology: Issues of uncertainty and anonymization

The integration of deep learning technologies into dermatology presents significant opportunities for
enhancing diagnostic accuracy and patient care. However, the practical deployment of these AI
models introduces critical challenges related to uncertainty quantification and patient data privacy.
This presentation will explore the current applications of deep learning in dermatology, with a focus
on addressing the issues of uncertainty in AI predictions and the importance of data anonymization.
This presentation aims to provide dermatologists with a comprehensive understanding of the
challenges and considerations involved in adopting deep learning technologies

14:56 - 15:12 Jane Yoo

AI for the dermatologist: Promises and perils

Background:
The prevalence of burnout among U.S. dermatologists has surged, reaching 49% in 2023, with a growing volume of bureaucratic tasks (e.g. charting, paperwork) the leading factor behind the professional fatigue. We seek to explore the competitive landscape and efficacy of AI-powered patient documentation to alleviate burnout among dermatologists by optimizing documentation practices while maintaining accuracy.
Methods
We conducted a review of eighteen AI-powered automated documentation products available in the current healthcare landscape, focusing on their integration with EHR systems, HIPAA compliance, language support, mobile accessibility, and consumer type.
Results
The survey revealed AI-powered documentation tools with various features. They aim to reduce clinician burden, enhance workflow, decrease burnout risk, and allow physicians to focus more on patient interaction during visits.
Conclusion:
As the technology continues to evolve, AI-powered documentation products have the potential to become an integral part of medicine by enhancing the physician-patient relationship and the overall healthcare system. Thorough evaluation of these products in clinical settings are needed to assess their efficacy. Longitudinal studies should be conducted to determine their impact on physician well-being. Collaboration between stakeholders, including healthcare workers, researchers, developers, and regulatory agencies, is needed to establish guidelines for integration and use of these products.

15:12 - 15:28 Anesia Tania

AI-powered imaging for pigmentary disorders: Advances in diagnosis, monitoring, and treatment response assessment

Pigmentary disorders, encompassing a spectrum of conditions like melasma, vitiligo, and post-inflammatory hyperpigmentation, present significant challenges in dermatological practice. Accurate diagnosis, objective monitoring, and personalized treatment planning are crucial for effective management. This presentation explores the emerging role of artificial intelligence (AI)-powered imaging in revolutionizing the care of patients with pigmentary disorders.

Traditional clinical diagnostic methods, including visual assessment and dermoscopy, are limited by subjectivity and inter-observer variability. With AI-powered algorithms and deep machine learning, recent studies have demonstrated the efficacy in detecting melanoma with high accuracy, comparable to expert dermatologists. Furthermore, AI-assisted dermoscopy has shown promise in improving the diagnostic accuracy of other pigmented lesions.

Beyond diagnosis, AI-powered imaging facilitates precise monitoring of disease progression and treatment response. In melasma, for instance, AI algorithms can quantify changes in pigmentation over time, providing objective data for evaluating treatment efficacy. Similarly, in vitiligo, AI tools can assess the extent of depigmentation and predict treatment response, enabling personalized therapeutic approaches

While AI holds immense promise, it is crucial to acknowledge the need for further research and validation. Large, diverse datasets are essential to ensure the generalizability and fairness of AI algorithms across different skin tones and populations. Ethical considerations, such as data privacy, algorithmic bias, and the potential impact on the dermatologist's role, must also be addressed.

This presentation will showcase the latest advancements in AI-powered imaging for pigmentary disorders, highlighting its potential to help dermatologists enhance diagnostic accuracy, personalize treatment plans, and improve patient outcomes. By embracing AI responsibly and collaboratively, we can usher in a new era of precision and efficiency in dermatological care.

15:28 - 15:44 Marius Khan

AI in medicine: The absence of disruption in dermatologists

Artificial intelligence (AI) has made significant strides in various medical fields, demonstrating promising results and revolutionizing healthcare practices. However, the integration of AI in dermatology has not yet reached its full potential. This presentation explores the current state of AI applications in dermatology, examining the progress made thus far and the unique challenges faced in implementing AI solutions in this specialized field.

We begin by reviewing the existing AI developments in dermatology. Despite some encouraging outcomes, widespread adoption in clinical practice remains limited. The talk then delves into the specific obstacles hindering AI advancement in dermatology.
Finally, we discuss potential strategies to overcome these challenges and accelerate AI integration in dermatology. These may include collaborative efforts to create comprehensive and representative databases and software infrastructures.

15:44 - 16:00 Soo Ick Cho

AI in dermatology: Dermatopathology aspect

Dermatopathology plays a crucial role in diagnosing various skin diseases. However, due to the additional specialized training program required after obtaining board certification in dermatology or pathology, there is a shortage of professionals specializing in this field, while the demand for dermatopathology continues to grow. Recently, artificial intelligence (AI) has been increasingly integrated into various medical fields, including dermatology and pathology, and its role in dermatopathology is expanding. These advances not only enhance the productivity of existing dermatopathologists but also assist general dermatologists and pathologists with less experience in interpreting dermatopathological findings. Moreover, they offer the potential to identify treatment-related or prognostic information, such as mutation status, from basic pathological images, which traditionally required additional tests. This could serve as a foundation for providing personalized treatments to dermatology patients. In this session, we will review recent AI-driven progress in dermatopathology and discuss current constraints and future directions.

Speaker

Dongheon Lee

Fill you affiliation
South Korea

Curriculum Vitae

Dongheon Lee is an Assistant Professor in the Department of Biomedical Engineering at Chungnam National University College of Medicine. Also, he serves as Deputy Director at the Biomedical Engineering Research Institute. He earned his Ph.D. in Bioengineering from Seoul National University. His research interests are medical image analysis, medical AI, and medical extended reality.

Jane Yoo

Mount Sinai School of Medicine New York
United States

Curriculum Vitae

Dr. Jane Yoo is a dual board-certified dermatologist and Mohs surgeon practicing in NYC. She graduated with a BS in Biology from Massachusetts Institute of Technology and also has a master's degree in public policy from Harvard University, with a specialization in Health Policy. She attended the Medical College of Virginia for her medical studies and completed her preliminary internship at St. Luke's-Roosevelt Hospital in NYC. Her dermatology residency was at Albert Einstein College of Medicine and was followed by a Mohs Micrographic Surgery fellowship at Yale School of Medicine.

Anesia Tania

Perdoski (INSDV)
Indonesia

Curriculum Vitae

Name: Anesia Tania
Title: Dermatologist
Birth: 14th May 1989
Residence: Jakarta, Indonesia

Medical Director and Dermatologist at RI Clinic, Jakarta
Medical Coordinator and Dermatologist at Jade Aesthetic Clinic
Vice Chair of the Professional and Education Division of INSDV
Secretary of Dermatovenereology and Aesthetics Training Institution (LPP)
Guest Lecturer for Prima University





Marius Khan

avisé labs GmbH
Germany

Curriculum Vitae

Marius is a dynamic entrepreneur and computer scientist, known for his innovative work in the medical field. As the founder of avisé labs (https://aviselabs.de), he has demonstrated a unique ability to bridge the worlds of medicine and technology. Hailing from a family of doctors, Marius charted his own course, leveraging his expertise to develop international software projects that have made a significant impact in the medical, health and life science industry.

Soo Ick Cho

Ohkims Dermatology
South Korea

Curriculum Vitae

Soo Ick Cho, MD-Ph.D
Medical Director, Lunit, Seoul, Republic of Korea
Board-certified Dermatologist (Korea)
Tel: 82-2-2072-2412 / 82-10-8879-6797
E-mail: sooickcho@lunit.io / chlroe@hotmail.com
ORCID: 0000-0003-3414-9869
________________________________________
Education
Seoul National University College of Medicine, Seoul, Korea
 Mar 2003 – Feb 2009
 Medical Doctor
The University of Catholic College of Medicine, Seoul, Korea
 Mar 2012 – Feb 2020
 Integrated MS/PhD
 Thesis: Identification of herpes zoster high‐risk group using Charlson comorbidity index: A nationwide retrospective cohort study
 Advisor: Prof. Young Min Park
________________________________________
Experience
Hallym University Kangnam Sacred Heart Hospital, Seoul, Korea
 Mar 2009 – Feb 2014
 Intern and resident course of Dermatology
 Advisor: Prof. Chun Wook Park
Seongsan health care post, Jeju, Korea
 Apr 2014 – Apr 2017
 Health director / Medical doctor
 Alternative military service
Seoul National University Hospital, Seoul, Korea
 May 2017 – Apr 2022
 Clinical Fellow / Clinical Assistant Professor / Research Assistant Professor
 Main Hospital, Cancer hospital, and Children’s hospital
Lunit, Seoul, Korea
 Mar 2021 – Now
 Medical director of Oncology division
o Team Leader of Medical Project Management, Medical Affairs (former)
o Team Leader of Medical Data Management, Medical Affairs (current)
o Leading Lunit SCOPE development, including Lunit SCOPE PD-L1, Lunit SCOPE HER2, Lunit SCOPE ER/PR, Lunit SCOPE UIHC, and artifact model.
OKim’s Dermatology Clinic, Seoul, Korea
 Mar 2021 – Now
 Part-time, dermatology clinician
o General dermatology clinician, aesthetic dermatology clinician
o Experience in botulinum toxin, filler, skin booster, various energy based devices and laser devices
The Association of Korean Dermatologists, Seoul, Korea
 Jan 2024 – Now
 Director of Publications
________________________________________
Awards
2017. 4 Commendation of the Minister of Health and Welfare
 Reason: Distinguished Service Award
2018. 8 Award of the Minister of Environment
 Reason: Atopic Dermatitis Prediction Model Using Korea Meteorological Administration Big Data
2020. 2 Academic Award of the Graduate school, The University of Catholic College of Medicine
 Reason: Excellence in Graduate Thesis
2022. 3 Young Investigator Award. The Korean Society for Investigative Dermatology
 Reason: Outstanding among dermatologist researchers under 40 years old in Republic of Korea
________________________________________
Language
English: Advanced
Korean: Fluent (Native)
Japanese: Intermediate
________________________________________
Recent publications (First or Corresponding author in recent 5 years)
Dermatology
1. Early-life diet and persistent atopic dermatitis: A nationwide cohort study. Allergy; In revision
2. Reduced economic disparity in biologics use for psoriasis after introducing the reducing copayment program. Sci Rep 2024;14:4139
3. Explore highly relevant questions in the Baumann skin type questionnaire through the digital skin analyzer: A retrospective single‐center study in South Korea. J Cosmet Dermatol 2023;22:3159-67
4. Pilot study of fractional microneedling radiofrequency for hidradenitis suppurativa assessed by clinical response and histology. Clin Exp Dermatol 2022;47:335-42
5. Risk of Skin Cancer and Actinic Keratosis in Patients with Rosacea: A Nationwide Population-based Cohort Study. Acta Derm Venereol 2022;102:2563
6. Association of COVID-19 with skin diseases and relevant biologics a cross-sectional study using nationwide claim data in South Korea. Br J Dermatol;2021:184:296-303
7. Association of metabolic comorbidities with pediatric psoriasis: A systematic review and meta-analysis. Ann Dermatol 2021;33:203-13
8. Analysis of trends and status of physician-based evaluation methods in acne vulgaris from 2000 to 2019. J Dermatol 2021;48:42-8
9. Intradermal microdroplet injection of diluted Incobotulinumtoxin-A for sebum control, face lifting, and pore size improvement. J Drugs Dermatol 2021;20:49-54
10. Identification of Herpes Zoster High-Risk Group Using Charlson Comorbidity Index: A Nationwide Retrospective Cohort Study. J Dermatol 2020;47:47-53
11. Association of Frequent Intake of Fast Foods, Energy Drinks, or Convenience Food with Atopic Dermatitis in Adolescents. Eur J Nutr 2020;59:3171-82
12. Functional surgery versus amputation for in situ or minimally invasive nail melanoma: A meta-analysis. J Am Acad Dermatol 2019;81:917-22
13. Pruritus in patients under targeted anticancer therapy: a multidimensional analysis using the 5-D itch scale. Acta Dermatol Venereol 2019;99:435-41
14. Local recurrence and metastasis in patients with malignant melanomas after surgery: A single-center analysis of 202 patients in South Korea. Plos One 2019;14:e0213475
15. Analysis of judicial precedents cases regarding skin cancer form 1997 to 2017 in Republic of Korea. Ann Dermatol 2019;31:300-6
16. Analysis of illegal cosmetic procedures performed by skin beautician described in judicial precedents. Korean J Dermatol 2020;58:669-73
17. Periorificial lesions associated with poor prognosis in patients with localized vitiligo: A retrospective study of 126 patients. J Am Acad Dermato 2022;87:927-30
18. Adenotonsillectomy may increase the risk of alopecia areata in childhood: a nationwide population-based cohort study. J Am Acad Dermato 2022;86:1128-31
19. Bidirectional association between psoriasis and inflammatory bowel disease in a pediatric population: a nationwide study in South Korea. J Eur Acad Dermatol Venereol 2022;36:e654-6
20. Inverse association between Helicobacter pylori infection and atopic, skin, and autoimmune diseases: A nationwide population‐based study in South Korea. Allergy 2021;76:3824-6
21. Pregnancy Outcomes in Female Patients with Alopecia Areata: A Nationwide Population-Based Study. J Invest Dermatol 2021;141:1844-7
22. Perceptions and attitudes of medical students regarding artificial intelligence in dermatology. J Eur Acad Dermatol Venereol 2021;35:e72-3
23. Ustekinumab does not increase tuberculosis risk: Results from a national database in South Korea. J Am Acad Dermatol 2020;82:1243-5
________________________________________
Artificial Intelligence
1. Robustness of automated acne lesion detection across various imaging conditions: A comparative analysis with dermatologists. J Eur Acad Dermatol Venereol; In revision
2. Generalizing AI-driven Assessment of Immunohistochemistry across Immunostains and Cancer Types: A Universal Immunohistochemistry Analyzer. NPJ Precis Oncol; In revision
3. Generation of a Melanoma and Nevus Data Set From Unstandardized Clinical Photographs on the Internet. JAMA Dermatology 2023;159:1223-31
4. Deep learning model improves tumor-infiltrating lymphocyte evaluation and therapeutic response prediction in breast cancer. NPJ Breast Cancer 2023;9:71
5. Automated Facial Acne Lesion Detecting and Counting Algorithm for Acne Severity Evaluation and Its Utility in Assisting Dermatologists. Am J Clin Dermatol 2023;24:649-59
6. Practical Training Approaches for Discordant Atopic Dermatitis Severity Datasets: Merging Methods with Soft-label and Train-set Pruning. IEEE J Biomed Health Inform 2023;1:166-75
7. Artificial intelligence–powered programmed death ligand 1 analyser reduces interobserver variation in tumour proportion score for non–small cell lung cancer with better prediction of immunotherapy response. Eur J Cancer 2022;170:17-26
8. Dermatologist-level classification of malignant lip diseases using a deep convolutional neural network. Br J Dermatol;2020;182:1388-94
9. Application of an electronic health record-based deep learning prediction model in dermatology. JAMA Dermatol 2020;156:473-4
________________________________________
Others
1. An Analysis of Judicial Cases Concerning Analgesic-Related Medication Errors in the Republic of Korea. J Patient Saf 2022;18:e439-46
2. Impact of comorbidity burden on mortality in patients with COVID-19: a retrospective analysis of the Korean health insurance database. Sci Rep 2021;11:6375
3. Analysis of Judicial Precedents Cases Regarding Epidural Injection in Chronic Pain Management in Republic of Korea. Reg Anesth Pain Med 2020;45:337-43

Title

Go to Top