1
|
Murphree DH, Puri P, Shamim H, Bezalel SA, Drage LA, Wang M, Pittelkow MR, Carter RE, Davis MDP, Bridges AG, Mangold AR, Yiannias JA, Tollefson MM, Lehman JS, Meves A, Otley CC, Sokumbi O, Hall MR, Comfere N. Deep learning for dermatologists: Part I. Fundamental concepts. J Am Acad Dermatol 2022; 87:1343-1351. [PMID: 32434009 PMCID: PMC7669702 DOI: 10.1016/j.jaad.2020.05.056] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2020] [Revised: 04/16/2020] [Accepted: 05/12/2020] [Indexed: 12/31/2022]
Abstract
Artificial intelligence is generating substantial interest in the field of medicine. One form of artificial intelligence, deep learning, has led to rapid advances in automated image analysis. In 2017, an algorithm demonstrated the ability to diagnose certain skin cancers from clinical photographs with the accuracy of an expert dermatologist. Subsequently, deep learning has been applied to a range of dermatology applications. Although experts will never be replaced by artificial intelligence, it will certainly affect the specialty of dermatology. In this first article of a 2-part series, the basic concepts of deep learning will be reviewed with the goal of laying the groundwork for effective communication between clinicians and technical colleagues. In part 2 of the series, the clinical applications of deep learning in dermatology will be reviewed and limitations and opportunities will be considered.
Collapse
Affiliation(s)
- Dennis H Murphree
- Department of Health Sciences Research, Division of Digital Health Sciences, Mayo Clinic, Rochester, Minnesota; Mayo Clinic Office of Artificial Intelligence in Dermatology.
| | - Pranav Puri
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Mayo Clinic Alix School of Medicine, Scottsdale, Arizona
| | - Huma Shamim
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Spencer A Bezalel
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Lisa A Drage
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Michael Wang
- Department of Dermatology, University of California San Francisco, San Francisco, California
| | - Mark R Pittelkow
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Scottsdale, Arizona
| | - Rickey E Carter
- Department of Health Sciences Research, Division of Biomedical Statistics and Informatics, Mayo Clinic, Jacksonville, Florida
| | - Mark D P Davis
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Alina G Bridges
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota
| | - Aaron R Mangold
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Scottsdale, Arizona
| | | | - Megha M Tollefson
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Julia S Lehman
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota
| | - Alexander Meves
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Clark C Otley
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Olayemi Sokumbi
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Jacksonville, Florida; Department of Laboratory Medicine and Pathology, Mayo Clinic, Jacksonville, Florida
| | - Matthew R Hall
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Jacksonville, Florida
| | - Nneka Comfere
- Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota
| |
Collapse
|
2
|
Puri P, Comfere N, Drage LA, Shamim H, Bezalel SA, Pittelkow MR, Davis MDP, Wang M, Mangold AR, Tollefson MM, Lehman JS, Meves A, Yiannias JA, Otley CC, Carter RE, Sokumbi O, Hall MR, Bridges AG, Murphree DH. Deep learning for dermatologists: Part II. Current applications. J Am Acad Dermatol 2022; 87:1352-1360. [PMID: 32428608 PMCID: PMC7669658 DOI: 10.1016/j.jaad.2020.05.053] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2020] [Revised: 05/07/2020] [Accepted: 05/08/2020] [Indexed: 01/14/2023]
Abstract
Because of a convergence of the availability of large data sets, graphics-specific computer hardware, and important theoretical advancements, artificial intelligence has recently contributed to dramatic progress in medicine. One type of artificial intelligence known as deep learning has been particularly impactful for medical image analysis. Deep learning applications have shown promising results in dermatology and other specialties, including radiology, cardiology, and ophthalmology. The modern clinician will benefit from an understanding of the basic features of deep learning to effectively use new applications and to better gauge their utility and limitations. In this second article of a 2-part series, we review the existing and emerging clinical applications of deep learning in dermatology and discuss future opportunities and limitations. Part 1 of this series offered an introduction to the basic concepts of deep learning to facilitate effective communication between clinicians and technical experts.
Collapse
Affiliation(s)
- Pranav Puri
- Mayo Clinic Alix School of Medicine, Scottsdale, Arizona; Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota
| | - Nneka Comfere
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Rochester, Minnesota; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota.
| | - Lisa A Drage
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Huma Shamim
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Spencer A Bezalel
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Mark R Pittelkow
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Scottsdale, Arizona
| | - Mark D P Davis
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Michael Wang
- Department of Dermatology, University of California San Francisco, San Francisco, California
| | - Aaron R Mangold
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Scottsdale, Arizona
| | - Megha M Tollefson
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Julia S Lehman
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Rochester, Minnesota; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota
| | - Alexander Meves
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | | | - Clark C Otley
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Rochester, Minnesota
| | - Rickey E Carter
- Department of Health Sciences Research, Division of Biomedical Statistics and Informatics, Mayo Clinic, Jacksonville, Florida
| | - Olayemi Sokumbi
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Jacksonville, Florida; Department of Laboratory Medicine and Pathology, Mayo Clinic, Jacksonville, Florida
| | - Matthew R Hall
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Jacksonville, Florida
| | - Alina G Bridges
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Dermatology, Mayo Clinic, Rochester, Minnesota; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota
| | - Dennis H Murphree
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota; Department of Health Sciences Research, Division of Digital Health Sciences, Mayo Clinic, Rochester, Minnesota
| |
Collapse
|
3
|
Puri P, Comfere N, Pittelkow MR, Bezalel SA, Murphree DH. COVID-19: An opportunity to build dermatology's digital future. Dermatol Ther 2020; 33:e14149. [PMID: 32767453 PMCID: PMC7435563 DOI: 10.1111/dth.14149] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2020] [Accepted: 08/03/2020] [Indexed: 01/11/2023]
Affiliation(s)
- Pranav Puri
- Mayo Clinic Alix School of Medicine, Scottsdale, Arizona, USA.,Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota, USA
| | - Nneka Comfere
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota, USA.,Mayo Clinic, Department of Dermatology, Rochester, Minnesota, USA
| | - Mark R Pittelkow
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota, USA.,Depatment of Dermatology, Mayo Clinic, Scottsdale, Arizona, USA
| | - Spencer A Bezalel
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota, USA.,Mayo Clinic, Department of Dermatology, Rochester, Minnesota, USA
| | - Dennis H Murphree
- Mayo Clinic Office of Artificial Intelligence in Dermatology, Rochester, Minnesota, USA.,Department of Health Sciences Research, Mayo Clinic, Rochester, Minnesota, USA
| |
Collapse
|
4
|
Bezalel SA, Otley CC. Invention in Dermatology: A Review. J Drugs Dermatol 2019; 18:904-908. [PMID: 31524346] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Dermatologists are among the most inventive physicians, trained in the multiple disciplines of medical dermatology, surgical dermatology, and dermatopathology. Many of the advances in dermatology practice have been derived from inventive colleagues who identify opportunities for improvement in practice, develop viable prototypes to address these practice opportunities, and persevere through the hard work of developing new technologies to advance the practice of dermatology. In this article, we will review the basic elements of invention, patents, and the range of outcomes associated with the pursuit of invention. Examples of innovative dermatologic technologies and approaches will be reviewed. Opportunities abound for dermatologists to contribute to the advancement of medical care through invention in our specialty. J Drugs Dermatol. 2019;18(9):904-908.
Collapse
|
5
|
Bezalel SA, Onajin O, Gonzalez-Santiago TM, Patel R, Pritt BS, Virk A, Gibson LE, Peters MS. Leprosy in a Midwestern Dermatology Clinic: Report of 9 Patients. Mayo Clin Proc 2019; 94:417-423. [PMID: 30799052 DOI: 10.1016/j.mayocp.2018.11.022] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/11/2018] [Revised: 10/11/2018] [Accepted: 11/19/2018] [Indexed: 10/27/2022]
Abstract
OBJECTIVE To describe the clinical features and epidemiology of leprosy in patients evaluated in a Midwestern dermatology clinic. PATIENTS AND METHODS We performed a retrospective review of clinical and laboratory data from patients with leprosy who were evaluated in the Department of Dermatology at Mayo Clinic in Rochester, Minnesota, from January 1, 1994, through December 31, 2017. RESULTS Nine patients, 7 male and 2 female, were identified, ranging in age from 15 to 63 years (mean age, 38 years). Six of the 9 patients (67%) were foreign-born: 3 from Oceania (2 from Micronesia and 1 from Guam), 1 from Southeast Asia (Indonesia), and 2 from Mexico. Three patients were born in the United States. All 9 patients presented with skin lesions (granulomatous histopathologic type), and 8 had neuropathy. Leprosy was multibacillary in 8 patients and paucibacillary in 1. Two patients experienced a type 1 treatment reaction, and 5 had type 2 reactions. Three of the 9 patients had speciation by polymerase chain reaction (Mycobacterium leprae in 2 and Mycobacterium lepromatosis in 1). CONCLUSION Despite its rarity in the United States, leprosy should be considered in the differential diagnosis when evaluating both foreign- and US-born patients with granulomatous dermatitis and peripheral neuropathy. Because M lepromatosis was not identified until 2008 and requires polymerase chain reaction for diagnosis, the incidence of this species among patients with leprosy diagnosed in earlier years is unknown.
Collapse
Affiliation(s)
| | | | | | - Robin Patel
- Division of Infectious Diseases, Mayo Clinic, Rochester, MN
| | - Bobbi S Pritt
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN; Division of Infectious Diseases, Mayo Clinic, Rochester, MN
| | - Abinash Virk
- Division of Infectious Diseases, Mayo Clinic, Rochester, MN
| | - Lawrence E Gibson
- Department of Dermatology, Mayo Clinic, Rochester, MN; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN
| | - Margot S Peters
- Department of Dermatology, Mayo Clinic, Rochester, MN; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN
| |
Collapse
|
6
|
Virk A, Pritt B, Patel R, Uhl JR, Bezalel SA, Gibson LE, Stryjewska BM, Peters MS. Mycobacterium lepromatosis Lepromatous Leprosy in US Citizen Who Traveled to Disease-Endemic Areas. Emerg Infect Dis 2018; 23:1864-1866. [PMID: 29048278 PMCID: PMC5652441 DOI: 10.3201/eid2311.171104] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022] Open
Abstract
We report Mycobacterium lepromatosis infection in a US-born person with an extensive international travel history. Clinical symptoms, histopathology, and management are similar to those of infections caused by M. leprae. Clinicians should consider this pathogen in the diagnosis of patients with symptoms of leprosy who have traveled to endemic areas.
Collapse
|
7
|
Steffes WE, Bezalel SA, Church AA, Vincek V, Wesson SK. A case of self-healing juvenile cutaneous mucinosis. Dermatol Online J 2015; 21:13030/qt4fr15909. [PMID: 26158364] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2015] [Accepted: 06/15/2015] [Indexed: 06/04/2023] Open
Abstract
IMPORTANCE Self-healing juvenile cutaneous mucinosis is a very rare, self-limiting disease characterized by the abrupt onset of asymptomatic papules and nodules located primarily on the face and periarticular regions of a juvenile patient. There have been less than 20 cases reported since it was first described in 1973. OBSERVATIONS Most cases have been reported in children 15 years and younger. Herein we present a case affecting a 17-year-old. To our knowledge, this the oldest reported patient with this condition in the USA. CONCLUSIONS AND RELEVANCE Despite the rarity of this disease, it is important to keep SHJCM on the differential in pediatric patients presenting with proliferating papules and nodules. Knowledge of this entity may prevent unnecessary diagnostic testing and aggressive treatment in the pediatric population with this self-limited disease.
Collapse
|
8
|
Affiliation(s)
- Spencer A Bezalel
- University of South Florida Morsani College of Medicine, Tampa, Florida
| | - Bruce E Strober
- Department of Dermatology, University of Connecticut School of Medicine, Farmington, Connecticut; Probity Medical Research, Waterloo, Ontario, Canada
| | - Katalin Ferenczi
- Department of Dermatology, University of Connecticut School of Medicine, Farmington, Connecticut
| |
Collapse
|
9
|
Steffes WE, Bezalel SA, Church AA, Vincek V, Wesson SK. A case of self-healing juvenile cutaneous mucinosis. Dermatol Online J 2015. [DOI: 10.5070/d3216027819] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022] Open
|