1
|
Trager MH, Gordon ER, Breneman A, Weng C, Samie FH. Artificial intelligence for nonmelanoma skin cancer. Clin Dermatol 2024:S0738-081X(24)00100-7. [PMID: 38925444 DOI: 10.1016/j.clindermatol.2024.06.016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/28/2024]
Abstract
Nonmelanoma skin cancers (NMSCs) are among the top five most common cancers globally. NMSC is an area with great potential for novel application of diagnostic tools including artificial intelligence (AI). In this scoping review, we aimed to describe the applications of AI in the diagnosis and treatment of NMSC. Twenty-nine publications described AI applications to dermatopathology including lesion classification and margin assessment. Twenty-five publications discussed AI use in clinical image analysis, showing that algorithms are not superior to dermatologists and may rely on unbalanced, nonrepresentative, and nontransparent training data sets. Sixteen publications described the use of AI in cutaneous surgery for NMSC including use in margin assessment during excisions and Mohs surgery, as well as predicting procedural complexity. Eleven publications discussed spectroscopy, confocal microscopy, thermography, and the AI algorithms that analyze and interpret their data. Ten publications pertained to AI applications for the discovery and use of NMSC biomarkers. Eight publications discussed the use of smartphones and AI, specifically how they enable clinicians and patients to have increased access to instant dermatologic assessments but with varying accuracies. Five publications discussed large language models and NMSC, including how they may facilitate or hinder patient education and medical decision-making. Three publications pertaining to the skin of color and AI for NMSC discussed concerns regarding limited diverse data sets for the training of convolutional neural networks. AI demonstrates tremendous potential to improve diagnosis, patient and clinician education, and management of NMSC. Despite excitement regarding AI, data sets are often not transparently reported, may include low-quality images, and may not include diverse skin types, limiting generalizability. AI may serve as a tool to increase access to dermatology services for patients in rural areas and save health care dollars. These benefits can only be achieved, however, with consideration of potential ethical costs.
Collapse
Affiliation(s)
- Megan H Trager
- Department of Dermatology, Columbia University Irving Medical Center, New York, NY, USA
| | - Emily R Gordon
- Columbia University Vagelos College of Physicians and Surgeons, New York, NY, USA
| | - Alyssa Breneman
- Department of Dermatology, Columbia University Irving Medical Center, New York, NY, USA
| | - Chunhua Weng
- Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, USA
| | - Faramarz H Samie
- Department of Dermatology, Columbia University Irving Medical Center, New York, NY, USA.
| |
Collapse
|
2
|
Gordon ER, Trager MH, Kontos D, Weng C, Geskin LJ, Dugdale LS, Samie FH. Ethical considerations for artificial intelligence in dermatology: a scoping review. Br J Dermatol 2024; 190:789-797. [PMID: 38330217 DOI: 10.1093/bjd/ljae040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Revised: 12/26/2023] [Accepted: 01/23/2024] [Indexed: 02/10/2024]
Abstract
The field of dermatology is experiencing the rapid deployment of artificial intelligence (AI), from mobile applications (apps) for skin cancer detection to large language models like ChatGPT that can answer generalist or specialist questions about skin diagnoses. With these new applications, ethical concerns have emerged. In this scoping review, we aimed to identify the applications of AI to the field of dermatology and to understand their ethical implications. We used a multifaceted search approach, searching PubMed, MEDLINE, Cochrane Library and Google Scholar for primary literature, following the PRISMA Extension for Scoping Reviews guidance. Our advanced query included terms related to dermatology, AI and ethical considerations. Our search yielded 202 papers. After initial screening, 68 studies were included. Thirty-two were related to clinical image analysis and raised ethical concerns for misdiagnosis, data security, privacy violations and replacement of dermatologist jobs. Seventeen discussed limited skin of colour representation in datasets leading to potential misdiagnosis in the general population. Nine articles about teledermatology raised ethical concerns, including the exacerbation of health disparities, lack of standardized regulations, informed consent for AI use and privacy challenges. Seven addressed inaccuracies in the responses of large language models. Seven examined attitudes toward and trust in AI, with most patients requesting supplemental assessment by a physician to ensure reliability and accountability. Benefits of AI integration into clinical practice include increased patient access, improved clinical decision-making, efficiency and many others. However, safeguards must be put in place to ensure the ethical application of AI.
Collapse
Affiliation(s)
- Emily R Gordon
- Columbia University Vagelos College of Physicians and Surgeons, New York, NY, USA
| | - Megan H Trager
- Columbia University Irving Medical Center, Departments of Dermatology
| | - Despina Kontos
- University of Pennsylvania, Perelman School of Medicine, Department of Radiology, Philadelphia, PA, USA
- Radiology
| | | | - Larisa J Geskin
- Columbia University Irving Medical Center, Departments of Dermatology
| | - Lydia S Dugdale
- Columbia University Vagelos College of Physicians and Surgeons, Department of Medicine, Center for Clinical Medical Ethics, New York, NY, USA
| | - Faramarz H Samie
- Columbia University Irving Medical Center, Departments of Dermatology
| |
Collapse
|
3
|
Raghavendra PVSP, Charitha C, Begum KG, Prasath VBS. Deep Learning-Based Skin Lesion Multi-class Classification with Global Average Pooling Improvement. J Digit Imaging 2023; 36:2227-2248. [PMID: 37407845 PMCID: PMC10501971 DOI: 10.1007/s10278-023-00862-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2023] [Revised: 05/26/2023] [Accepted: 05/26/2023] [Indexed: 07/07/2023] Open
Abstract
Cancerous skin lesions are one of the deadliest diseases that have the ability in spreading across other body parts and organs. Conventionally, visual inspection and biopsy methods are widely used to detect skin cancers. However, these methods have some drawbacks, and the prediction is not highly accurate. This is where a dependable automatic recognition system for skin cancers comes into play. With the extensive usage of deep learning in various aspects of medical health, a novel computer-aided dermatologist tool has been suggested for the accurate identification and classification of skin lesions by deploying a novel deep convolutional neural network (DCNN) model that incorporates global average pooling along with preprocessing to discern the skin lesions. The proposed model is trained and tested on the HAM10000 dataset, which contains seven different classes of skin lesions as target classes. The black hat filtering technique has been applied to remove artifacts in the preprocessing stage along with the resampling techniques to balance the data. The performance of the proposed model is evaluated by comparing it with some of the transfer learning models such as ResNet50, VGG-16, MobileNetV2, and DenseNet121. The proposed model provides an accuracy of 97.20%, which is the highest among the previous state-of-art models for multi-class skin lesion classification. The efficacy of the proposed model is also validated by visualizing the results obtained using a graphical user interface (GUI).
Collapse
Affiliation(s)
| | - C. Charitha
- School of Electrical and Electronics Engineering, SASTRA Deemed to be University, 613401 Thanjavur, India
| | - K. Ghousiya Begum
- School of Electrical and Electronics Engineering, SASTRA Deemed to be University, 613401 Thanjavur, India
| | - V. B. S. Prasath
- Division of Biomedical Informatics, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH 45229 USA
- Department of Pediatrics, College of Medicine, University of Cincinnati, Cincinnati, OH 45257 USA
- Department of Biomedical Informatics, College of Medicine, University of Cincinnati, Cincinnati, OH 45267 USA
- Department of Computer Science, University of Cincinnati, Cincinnati, OH 45221 USA
| |
Collapse
|
4
|
Medical AI and human dignity: Contrasting perceptions of human and artificially intelligent (AI) decision making in diagnostic and medical resource allocation contexts. COMPUTERS IN HUMAN BEHAVIOR 2022. [DOI: 10.1016/j.chb.2022.107296] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/21/2023]
|
5
|
Wen D, Khan SM, Ji Xu A, Ibrahim H, Smith L, Caballero J, Zepeda L, de Blas Perez C, Denniston AK, Liu X, Matin RN. Characteristics of publicly available skin cancer image datasets: a systematic review. LANCET DIGITAL HEALTH 2021; 4:e64-e74. [PMID: 34772649 DOI: 10.1016/s2589-7500(21)00252-1] [Citation(s) in RCA: 59] [Impact Index Per Article: 19.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/06/2021] [Revised: 08/26/2021] [Accepted: 10/21/2021] [Indexed: 12/17/2022]
Abstract
Publicly available skin image datasets are increasingly used to develop machine learning algorithms for skin cancer diagnosis. However, the total number of datasets and their respective content is currently unclear. This systematic review aimed to identify and evaluate all publicly available skin image datasets used for skin cancer diagnosis by exploring their characteristics, data access requirements, and associated image metadata. A combined MEDLINE, Google, and Google Dataset search identified 21 open access datasets containing 106 950 skin lesion images, 17 open access atlases, eight regulated access datasets, and three regulated access atlases. Images and accompanying data from open access datasets were evaluated by two independent reviewers. Among the 14 datasets that reported country of origin, most (11 [79%]) originated from Europe, North America, and Oceania exclusively. Most datasets (19 [91%]) contained dermoscopic images or macroscopic photographs only. Clinical information was available regarding age for 81 662 images (76·4%), sex for 82 848 (77·5%), and body site for 79 561 (74·4%). Subject ethnicity data were available for 1415 images (1·3%), and Fitzpatrick skin type data for 2236 (2·1%). There was limited and variable reporting of characteristics and metadata among datasets, with substantial under-representation of darker skin types. This is the first systematic review to characterise publicly available skin image datasets, highlighting limited applicability to real-life clinical settings and restricted population representation, precluding generalisability. Quality standards for characteristics and metadata reporting for skin image datasets are needed.
Collapse
Affiliation(s)
- David Wen
- Oxford University Clinical Academic Graduate School, University of Oxford, Oxford, UK; Institute of Clinical Sciences, University of Birmingham, Birmingham, UK; Royal Berkshire Hospital, Royal Berkshire NHS Foundation Trust, Reading, UK
| | - Saad M Khan
- Royal Berkshire Hospital, Royal Berkshire NHS Foundation Trust, Reading, UK
| | - Antonio Ji Xu
- Department of Dermatology, Churchill Hospital, Oxford University Hospitals NHS Foundation Trust, Oxford, UK
| | - Hussein Ibrahim
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK; Academic Unit of Ophthalmology, Institute of Inflammation and Ageing, University of Birmingham, Birmingham, UK; Centre for Regulatory Science and Innovation, Birmingham Health Partners, Birmingham, UK
| | | | | | | | | | - Alastair K Denniston
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK; Academic Unit of Ophthalmology, Institute of Inflammation and Ageing, University of Birmingham, Birmingham, UK; Centre for Regulatory Science and Innovation, Birmingham Health Partners, Birmingham, UK; Health Data Research UK, London, UK; National Institute for Health Research Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS Foundation Trust, London, UK; UCL Institute of Ophthalmology, London, UK
| | - Xiaoxuan Liu
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK; Academic Unit of Ophthalmology, Institute of Inflammation and Ageing, University of Birmingham, Birmingham, UK; Centre for Regulatory Science and Innovation, Birmingham Health Partners, Birmingham, UK; Health Data Research UK, London, UK
| | - Rubeta N Matin
- Department of Dermatology, Churchill Hospital, Oxford University Hospitals NHS Foundation Trust, Oxford, UK.
| |
Collapse
|
6
|
Gao S, He L, Chen Y, Li D, Lai K. Public Perception of Artificial Intelligence in Medical Care: Content Analysis of Social Media. J Med Internet Res 2020; 22:e16649. [PMID: 32673231 PMCID: PMC7385634 DOI: 10.2196/16649] [Citation(s) in RCA: 48] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2019] [Revised: 04/02/2020] [Accepted: 05/31/2020] [Indexed: 01/22/2023] Open
Abstract
Background High-quality medical resources are in high demand worldwide, and the application of artificial intelligence (AI) in medical care may help alleviate the crisis related to this shortage. The development of the medical AI industry depends to a certain extent on whether industry experts have a comprehensive understanding of the public’s views on medical AI. Currently, the opinions of the general public on this matter remain unclear. Objective The purpose of this study is to explore the public perception of AI in medical care through a content analysis of social media data, including specific topics that the public is concerned about; public attitudes toward AI in medical care and the reasons for them; and public opinion on whether AI can replace human doctors. Methods Through an application programming interface, we collected a data set from the Sina Weibo platform comprising more than 16 million users throughout China by crawling all public posts from January to December 2017. Based on this data set, we identified 2315 posts related to AI in medical care and classified them through content analysis. Results Among the 2315 identified posts, we found three types of AI topics discussed on the platform: (1) technology and application (n=987, 42.63%), (2) industry development (n=706, 30.50%), and (3) impact on society (n=622, 26.87%). Out of 956 posts where public attitudes were expressed, 59.4% (n=568), 34.4% (n=329), and 6.2% (n=59) of the posts expressed positive, neutral, and negative attitudes, respectively. The immaturity of AI technology (27/59, 46%) and a distrust of related companies (n=15, 25%) were the two main reasons for the negative attitudes. Across 200 posts that mentioned public attitudes toward replacing human doctors with AI, 47.5% (n=95) and 32.5% (n=65) of the posts expressed that AI would completely or partially replace human doctors, respectively. In comparison, 20.0% (n=40) of the posts expressed that AI would not replace human doctors. Conclusions Our findings indicate that people are most concerned about AI technology and applications. Generally, the majority of people held positive attitudes and believed that AI doctors would completely or partially replace human ones. Compared with previous studies on medical doctors, the general public has a more positive attitude toward medical AI. Lack of trust in AI and the absence of the humanistic care factor are essential reasons why some people still have a negative attitude toward medical AI. We suggest that practitioners may need to pay more attention to promoting the credibility of technology companies and meeting patients’ emotional needs instead of focusing merely on technical issues.
Collapse
Affiliation(s)
- Shuqing Gao
- Faculty of Psychology, Beijing Normal University, Beijing, China
| | - Lingnan He
- School of Communication and Design, Sun Yat-Sen University, Guangzhou, China.,Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion, Guangzhou, China
| | - Yue Chen
- School of Communication and Design, Sun Yat-Sen University, Guangzhou, China
| | - Dan Li
- School of Journalism and Communication, Jinan University, Guangzhou, China
| | - Kaisheng Lai
- School of Journalism and Communication, Jinan University, Guangzhou, China
| |
Collapse
|