Literature DB >> 17854361

Can automated dermoscopy image analysis instruments provide added benefit for the dermatologist? A study comparing the results of three systems.

A Perrinaud1, O Gaide, L E French, J-H Saurat, A A Marghoob, R P Braun.   

Abstract

BACKGROUND: Instruments designed to provide computer program-driven diagnosis of dermoscopic images of lesions are now commercially available. Multiple publications tout the improved diagnostic accuracy of these instruments compared with that of clinicians.
OBJECTIVES: Our aim was to evaluate the actual usefulness of these instruments for dermatologists practising in a pigmented lesion clinic.
METHODS: Over a 4-month period we subjected lesions, which were being evaluated in one of our clinics, to automated computer diagnosis performed by three commercially available instruments. We intentionally included three groups of lesions: group 1 lesions were suspicious melanocytic lesions that were scheduled to be excised; group 2 lesions were nonmelanocytic lesions; group 3 lesions were clinically obvious melanomas. The automated diagnoses provided by the instruments were compared with the dermoscopy diagnosis of experienced physicians and with histopathology.
RESULTS: We included a total of 107 lesions. One imaging system's computer algorithm was unable to analyse one third of the lesions. All three instruments' computer algorithms were able to identify the clinically obvious melanomas (group 3) correctly. However, all three systems tended to overdiagnose by incorrectly classifying most seborrhoeic keratoses (group 2) as potential malignant lesions. Concerning the suspect melanocytic lesions (group 1), which are precisely the lesions for which a dermatologist would welcome a second opinion, we found significant variability in the diagnostic accuracy of the instruments tested. However, all three systems providing computer-assisted diagnosis had a tendency to overdiagnose benign melanocytic lesions as potential melanomas.
CONCLUSIONS: Although the image analysis systems tested by us correctly identified the clinically obvious melanomas, they were not able to discriminate between most dysplastic naevi and early malignant melanoma. Thus, for the moment these computer-assisted diagnostic imaging machines provide little to no added benefit for the experienced dermatologist/dermoscopist.

Entities:  

Mesh:

Year:  2007        PMID: 17854361     DOI: 10.1111/j.1365-2133.2007.08168.x

Source DB:  PubMed          Journal:  Br J Dermatol        ISSN: 0007-0963            Impact factor:   9.302


  13 in total

1.  Automatic lesion border selection in dermoscopy images using morphology and color features.

Authors:  Nabin K Mishra; Ravneet Kaur; Reda Kasmi; Jason R Hagerty; Robert LeAnder; Ronald J Stanley; Randy H Moss; William V Stoecker
Journal:  Skin Res Technol       Date:  2019-03-14       Impact factor: 2.365

Review 2.  Current and emerging technologies in melanoma diagnosis: the state of the art.

Authors:  Estee L Psaty; Allan C Halpern
Journal:  Clin Dermatol       Date:  2009 Jan-Feb       Impact factor: 3.541

3.  Detection of Malignant Melanoma Using Artificial Intelligence: An Observational Study of Diagnostic Accuracy.

Authors:  Michael Phillips; Jack Greenhalgh; Helen Marsden; Ioulios Palamaras
Journal:  Dermatol Pract Concept       Date:  2019-12-31

4.  Automatic segmentation of dermoscopic images by iterative classification.

Authors:  Maciel Zortea; Stein Olav Skrøvseth; Thomas R Schopf; Herbert M Kirchesch; Fred Godtliebsen
Journal:  Int J Biomed Imaging       Date:  2011-07-17

5.  Visual inspection and dermoscopy, alone or in combination, for diagnosing keratinocyte skin cancers in adults.

Authors:  Jacqueline Dinnes; Jonathan J Deeks; Naomi Chuchu; Rubeta N Matin; Kai Yuen Wong; Roger Benjamin Aldridge; Alana Durack; Abha Gulati; Sue Ann Chan; Louise Johnston; Susan E Bayliss; Jo Leonardi-Bee; Yemisi Takwoingi; Clare Davenport; Colette O'Sullivan; Hamid Tehrani; Hywel C Williams
Journal:  Cochrane Database Syst Rev       Date:  2018-12-04

6.  Computer-assisted diagnosis techniques (dermoscopy and spectroscopy-based) for diagnosing skin cancer in adults.

Authors:  Lavinia Ferrante di Ruffano; Yemisi Takwoingi; Jacqueline Dinnes; Naomi Chuchu; Susan E Bayliss; Clare Davenport; Rubeta N Matin; Kathie Godfrey; Colette O'Sullivan; Abha Gulati; Sue Ann Chan; Alana Durack; Susan O'Connell; Matthew D Gardiner; Jeffrey Bamber; Jonathan J Deeks; Hywel C Williams
Journal:  Cochrane Database Syst Rev       Date:  2018-12-04

7.  Visual inspection for diagnosing cutaneous melanoma in adults.

Authors:  Jacqueline Dinnes; Jonathan J Deeks; Matthew J Grainge; Naomi Chuchu; Lavinia Ferrante di Ruffano; Rubeta N Matin; David R Thomson; Kai Yuen Wong; Roger Benjamin Aldridge; Rachel Abbott; Monica Fawzy; Susan E Bayliss; Yemisi Takwoingi; Clare Davenport; Kathie Godfrey; Fiona M Walter; Hywel C Williams
Journal:  Cochrane Database Syst Rev       Date:  2018-12-04

8.  Definition of an automated Content-Based Image Retrieval (CBIR) system for the comparison of dermoscopic images of pigmented skin lesions.

Authors:  Alfonso Baldi; Raffaele Murace; Emanuele Dragonetti; Mario Manganaro; Oscar Guerra; Stefano Bizzi; Luca Galli
Journal:  Biomed Eng Online       Date:  2009-08-16       Impact factor: 2.819

9.  The feasibility of using manual segmentation in a multifeature computer-aided diagnosis system for classification of skin lesions: a retrospective comparative study.

Authors:  Wen-Yu Chang; Adam Huang; Yin-Chun Chen; Chi-Wei Lin; John Tsai; Chung-Kai Yang; Yin-Tseng Huang; Yi-Fan Wu; Gwo-Shing Chen
Journal:  BMJ Open       Date:  2015-05-03       Impact factor: 2.692

10.  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.

Authors:  Kajsa Møllersen; Herbert Kirchesch; Maciel Zortea; Thomas R Schopf; Kristian Hindberg; Fred Godtliebsen
Journal:  Biomed Res Int       Date:  2015-11-26       Impact factor: 3.411

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.