Improved identification of potentially dangerous pigmented skin lesions by computerized image analysis
- PMID: 12588225
- DOI: 10.1001/archderm.139.2.195
Improved identification of potentially dangerous pigmented skin lesions by computerized image analysis
Abstract
Background: Melanoma is completely curable if resected early. Unfortunately, early melanoma can be difficult to differentiate from other pigmented lesions. Computerized image analysis instruments have now been developed to assist in determining whether a pigmented lesion is potentially dangerous and requires biopsy. To evaluate whether one such instrument can improve the management of pigmented lesions, we obtained biopsy specimens from 52 pigmented lesions that appeared clinically benign to an experienced dermatologist but were suspicious by image analysis.
Observation: Histologically, 9 (17%) of the lesions that were removed based solely on computer recommendation were potentially dangerous and should have been removed. These included 1 malignant melanoma in situ and 8 dysplastic nevi with moderate to severe cytologic atypia.
Conclusion: The results of the present study indicate that computerized image analysis can improve the evaluation of pigmented skin lesions by identifying clinically unsuspicious, but potentially dangerous, lesions that might have otherwise have been neglected.
Similar articles
-
[Dysplastic melanocytic nevus].Duodecim. 2010;126(21):2492-501. Duodecim. 2010. PMID: 21171474 Review. Finnish.
-
Computer image analysis of pigmented skin lesions.Melanoma Res. 1991 Nov-Dec;1(4):231-6. doi: 10.1097/00008390-199111000-00002. Melanoma Res. 1991. PMID: 1823631
-
Simulators of malignant melanoma of the skin.Eur J Dermatol. 1998 Sep;8(6):388-96. Eur J Dermatol. 1998. PMID: 9729049 Review.
-
Histopathologic correlation of high-risk MelaFindTM lesions: a 3-year experience from a high-risk pigmented lesion clinic.Int J Dermatol. 2019 May;58(5):569-576. doi: 10.1111/ijd.14336. Epub 2018 Dec 13. Int J Dermatol. 2019. PMID: 30549001
-
Management strategies of academic pigmented lesion clinic directors in the United States.J Am Acad Dermatol. 2018 Aug;79(2):367-369. doi: 10.1016/j.jaad.2017.12.069. Epub 2018 Jan 4. J Am Acad Dermatol. 2018. PMID: 29307637 No abstract available.
Cited by
-
Visual inspection and dermoscopy, alone or in combination, for diagnosing keratinocyte skin cancers in adults.Cochrane Database Syst Rev. 2018 Dec 4;12(12):CD011901. doi: 10.1002/14651858.CD011901.pub2. Cochrane Database Syst Rev. 2018. PMID: 30521688 Free PMC article.
-
Automatic diagnosis of melanoma using machine learning methods on a spectroscopic system.BMC Med Imaging. 2014 Oct 13;14:36. doi: 10.1186/1471-2342-14-36. BMC Med Imaging. 2014. PMID: 25311811 Free PMC article.
-
A relative color approach to color discrimination for malignant melanoma detection in dermoscopy images.Skin Res Technol. 2007 Feb;13(1):62-72. doi: 10.1111/j.1600-0846.2007.00192.x. Skin Res Technol. 2007. PMID: 17250534 Free PMC article.
-
Computer-Aided Decision Support for Melanoma Detection Applied on Melanocytic and Nonmelanocytic Skin Lesions: A Comparison of Two Systems Based on Automatic Analysis of Dermoscopic Images.Biomed Res Int. 2015;2015:579282. doi: 10.1155/2015/579282. Epub 2015 Nov 26. Biomed Res Int. 2015. PMID: 26693486 Free PMC article.
-
Visual inspection for diagnosing cutaneous melanoma in adults.Cochrane Database Syst Rev. 2018 Dec 4;12(12):CD013194. doi: 10.1002/14651858.CD013194. Cochrane Database Syst Rev. 2018. PMID: 30521684 Free PMC article.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical