Back to Search
Start Over
Are computers better diagnosticians than dermatologists? A discussion of how artificial intelligence can help in diagnosing skin lesions.
- Source :
- British Journal of Dermatology; Sep2020, Vol. 183 Issue 3, pe74-e74, 1p
- Publication Year :
- 2020
-
Abstract
- Skin cancers are the most common cancers in the UK. Malignant Melanoma (MM) is the most dangerous type of skin cancer. Primary Care Physicians (GPs) often have difficulty in distinguishing harmless skin blemishes from MM, leading to many patients being referred to dermatology departments. There have been enormous advances recently in the application of computer‐based Artificial Intelligence (AI) to the field of image analysis. This paper from four authors in London (UK) explores the current position of AI systems in analysing skin lesions (affected patches of skin). Important AI concepts such as convolutional neural networks (CNN) and "deep learning" are explained. By exposing AI systems to hundreds of thousands of pictures of skin lesions, it is possible to "train" them to recognise lesions with a high degree of accuracy. Skin cancer detection, particularly melanoma detection, has now been tested by numerous different groups with multiple AI systems; the most successful ones are generally "convolutional neural networks". When comparing their performance to dermatologists who are presented with photographs of skin lesions, these AI systems perform similarly, if not better, at identifying whether something is a melanoma or a benign (non‐cancerous) mole. However, these programmes are limited by the data sets on which they have been "trained"; for example, a lot of the datasets are trained on Caucasian skin, and will perform less well when detecting melanoma in skin of colour, as they may not have been exposed to enough of this type of image to perform well. They have also not been shown to be particularly useful for diagnosing other types of skin conditions yet and they are not able to provide any kind of explanation for their classification. Because of these limitations, it is unlikely that they will replace dermatologists. The legal framework for AI systems also doesn't allow them to take responsibility for decisions, so responsibility for diagnosis still falls to a responsible clinician. However, in the near future they may well prove to be extremely useful in aiding GPs in making clinical decisions about skin lesions, particularly with regards to urgent referrals to dermatology. Linked Article: Du-Harpur et al. Br J Dermatol 2020; 183:423–430. Linked Article: Du-Harpur et al. Br J Dermatol 2020; 183:423–430. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 00070963
- Volume :
- 183
- Issue :
- 3
- Database :
- Complementary Index
- Journal :
- British Journal of Dermatology
- Publication Type :
- Academic Journal
- Accession number :
- 145489482
- Full Text :
- https://doi.org/10.1111/bjd.19360