The diagnostic performance of expert dermoscopists vs a computer-vision system on small-diameter melanomas

Robert J. Friedman, Dina Gutkowicz-Krusin, Michele J. Farber, Melanie Warycha, Lori Schneider-Kels, Nicole Papastathis, Martin C. Mihm, Paul Googe, Roy King, Victor G. Prieto, Alfred W. Kopf, David Polsky, Harold Rabinovitz, Margaret Oliviero, Armand Cognetta, Darrell S. Rigel, Ashfaq Marghoob, Jason Rivers, Robert Johr, Jane M. Grant-Kels & 1 others Hensin Tsao

Research output: Contribution to journalArticle

50 Citations (Scopus)

Abstract

Objective: To evaluate the performance of dermoscopists in diagnosing small pigmented skin lesions (diameter ≤6 mm) compared with an automatic multispectral computer-vision system. Design: Blinded comparison study. Setting: Dermatologic hospital-based clinics and private practice offices. Patients: From a computerized skin imaging database of 990 small (≤6-mm) pigmented skin lesions, all 49 melanomas from 49 patients were included in this study. Fifty randomly selected nonmelanomas from 46 patients served as a control. Main Outcome Measures: Ten dermoscopists independently examined dermoscopic images of 99 pigmented skin lesions and decided whether they identified the lesions as melanoma and whether they would recommend biopsy to rule out melanoma. Diagnostic and biopsy sensitivity and specificity were computed and then compared with the results of the computer-vision system. Results: Dermoscopists were able to correctly identify small melanomas with an average diagnostic sensitivity of 39% and a specificity of 82% and recommended small melanomas for biopsy with a sensitivity of 71% and specificity of 49%, with only fair interobserver agreement (κ=0.31 for diagnosis and 0.34 for biopsy). In comparison, in recommending biopsy to rule out melanoma, the computer-vision system achieved 98% sensitivity and 44% specificity. Conclusions: Differentiation of small melanomas from small benign pigmented lesions challenges even expert physicians. Computer-vision systems can facilitate early detection of small melanomas and may limit the number of biopsies to rule out melanoma performed on benign lesions.

Original languageEnglish (US)
Pages (from-to)476-482
Number of pages7
JournalArchives of Dermatology
Volume144
Issue number4
DOIs
StatePublished - Jan 1 2008

Fingerprint

Artificial Intelligence
Melanoma
Biopsy
Skin
Sensitivity and Specificity
Private Practice
Outcome Assessment (Health Care)
Databases
Physicians

All Science Journal Classification (ASJC) codes

  • Dermatology

Cite this

Friedman, R. J., Gutkowicz-Krusin, D., Farber, M. J., Warycha, M., Schneider-Kels, L., Papastathis, N., ... Tsao, H. (2008). The diagnostic performance of expert dermoscopists vs a computer-vision system on small-diameter melanomas. Archives of Dermatology, 144(4), 476-482. https://doi.org/10.1001/archderm.144.4.476

The diagnostic performance of expert dermoscopists vs a computer-vision system on small-diameter melanomas. / Friedman, Robert J.; Gutkowicz-Krusin, Dina; Farber, Michele J.; Warycha, Melanie; Schneider-Kels, Lori; Papastathis, Nicole; Mihm, Martin C.; Googe, Paul; King, Roy; Prieto, Victor G.; Kopf, Alfred W.; Polsky, David; Rabinovitz, Harold; Oliviero, Margaret; Cognetta, Armand; Rigel, Darrell S.; Marghoob, Ashfaq; Rivers, Jason; Johr, Robert; Grant-Kels, Jane M.; Tsao, Hensin.

In: Archives of Dermatology, Vol. 144, No. 4, 01.01.2008, p. 476-482.

Research output: Contribution to journalArticle

Friedman, RJ, Gutkowicz-Krusin, D, Farber, MJ, Warycha, M, Schneider-Kels, L, Papastathis, N, Mihm, MC, Googe, P, King, R, Prieto, VG, Kopf, AW, Polsky, D, Rabinovitz, H, Oliviero, M, Cognetta, A, Rigel, DS, Marghoob, A, Rivers, J, Johr, R, Grant-Kels, JM & Tsao, H 2008, 'The diagnostic performance of expert dermoscopists vs a computer-vision system on small-diameter melanomas', Archives of Dermatology, vol. 144, no. 4, pp. 476-482. https://doi.org/10.1001/archderm.144.4.476
Friedman RJ, Gutkowicz-Krusin D, Farber MJ, Warycha M, Schneider-Kels L, Papastathis N et al. The diagnostic performance of expert dermoscopists vs a computer-vision system on small-diameter melanomas. Archives of Dermatology. 2008 Jan 1;144(4):476-482. https://doi.org/10.1001/archderm.144.4.476
Friedman, Robert J. ; Gutkowicz-Krusin, Dina ; Farber, Michele J. ; Warycha, Melanie ; Schneider-Kels, Lori ; Papastathis, Nicole ; Mihm, Martin C. ; Googe, Paul ; King, Roy ; Prieto, Victor G. ; Kopf, Alfred W. ; Polsky, David ; Rabinovitz, Harold ; Oliviero, Margaret ; Cognetta, Armand ; Rigel, Darrell S. ; Marghoob, Ashfaq ; Rivers, Jason ; Johr, Robert ; Grant-Kels, Jane M. ; Tsao, Hensin. / The diagnostic performance of expert dermoscopists vs a computer-vision system on small-diameter melanomas. In: Archives of Dermatology. 2008 ; Vol. 144, No. 4. pp. 476-482.
@article{019185e9918d4c8ba61910d8648ca607,
title = "The diagnostic performance of expert dermoscopists vs a computer-vision system on small-diameter melanomas",
abstract = "Objective: To evaluate the performance of dermoscopists in diagnosing small pigmented skin lesions (diameter ≤6 mm) compared with an automatic multispectral computer-vision system. Design: Blinded comparison study. Setting: Dermatologic hospital-based clinics and private practice offices. Patients: From a computerized skin imaging database of 990 small (≤6-mm) pigmented skin lesions, all 49 melanomas from 49 patients were included in this study. Fifty randomly selected nonmelanomas from 46 patients served as a control. Main Outcome Measures: Ten dermoscopists independently examined dermoscopic images of 99 pigmented skin lesions and decided whether they identified the lesions as melanoma and whether they would recommend biopsy to rule out melanoma. Diagnostic and biopsy sensitivity and specificity were computed and then compared with the results of the computer-vision system. Results: Dermoscopists were able to correctly identify small melanomas with an average diagnostic sensitivity of 39{\%} and a specificity of 82{\%} and recommended small melanomas for biopsy with a sensitivity of 71{\%} and specificity of 49{\%}, with only fair interobserver agreement (κ=0.31 for diagnosis and 0.34 for biopsy). In comparison, in recommending biopsy to rule out melanoma, the computer-vision system achieved 98{\%} sensitivity and 44{\%} specificity. Conclusions: Differentiation of small melanomas from small benign pigmented lesions challenges even expert physicians. Computer-vision systems can facilitate early detection of small melanomas and may limit the number of biopsies to rule out melanoma performed on benign lesions.",
author = "Friedman, {Robert J.} and Dina Gutkowicz-Krusin and Farber, {Michele J.} and Melanie Warycha and Lori Schneider-Kels and Nicole Papastathis and Mihm, {Martin C.} and Paul Googe and Roy King and Prieto, {Victor G.} and Kopf, {Alfred W.} and David Polsky and Harold Rabinovitz and Margaret Oliviero and Armand Cognetta and Rigel, {Darrell S.} and Ashfaq Marghoob and Jason Rivers and Robert Johr and Grant-Kels, {Jane M.} and Hensin Tsao",
year = "2008",
month = "1",
day = "1",
doi = "10.1001/archderm.144.4.476",
language = "English (US)",
volume = "144",
pages = "476--482",
journal = "JAMA Dermatology",
issn = "2168-6068",
publisher = "American Medical Association",
number = "4",

}

TY - JOUR

T1 - The diagnostic performance of expert dermoscopists vs a computer-vision system on small-diameter melanomas

AU - Friedman, Robert J.

AU - Gutkowicz-Krusin, Dina

AU - Farber, Michele J.

AU - Warycha, Melanie

AU - Schneider-Kels, Lori

AU - Papastathis, Nicole

AU - Mihm, Martin C.

AU - Googe, Paul

AU - King, Roy

AU - Prieto, Victor G.

AU - Kopf, Alfred W.

AU - Polsky, David

AU - Rabinovitz, Harold

AU - Oliviero, Margaret

AU - Cognetta, Armand

AU - Rigel, Darrell S.

AU - Marghoob, Ashfaq

AU - Rivers, Jason

AU - Johr, Robert

AU - Grant-Kels, Jane M.

AU - Tsao, Hensin

PY - 2008/1/1

Y1 - 2008/1/1

N2 - Objective: To evaluate the performance of dermoscopists in diagnosing small pigmented skin lesions (diameter ≤6 mm) compared with an automatic multispectral computer-vision system. Design: Blinded comparison study. Setting: Dermatologic hospital-based clinics and private practice offices. Patients: From a computerized skin imaging database of 990 small (≤6-mm) pigmented skin lesions, all 49 melanomas from 49 patients were included in this study. Fifty randomly selected nonmelanomas from 46 patients served as a control. Main Outcome Measures: Ten dermoscopists independently examined dermoscopic images of 99 pigmented skin lesions and decided whether they identified the lesions as melanoma and whether they would recommend biopsy to rule out melanoma. Diagnostic and biopsy sensitivity and specificity were computed and then compared with the results of the computer-vision system. Results: Dermoscopists were able to correctly identify small melanomas with an average diagnostic sensitivity of 39% and a specificity of 82% and recommended small melanomas for biopsy with a sensitivity of 71% and specificity of 49%, with only fair interobserver agreement (κ=0.31 for diagnosis and 0.34 for biopsy). In comparison, in recommending biopsy to rule out melanoma, the computer-vision system achieved 98% sensitivity and 44% specificity. Conclusions: Differentiation of small melanomas from small benign pigmented lesions challenges even expert physicians. Computer-vision systems can facilitate early detection of small melanomas and may limit the number of biopsies to rule out melanoma performed on benign lesions.

AB - Objective: To evaluate the performance of dermoscopists in diagnosing small pigmented skin lesions (diameter ≤6 mm) compared with an automatic multispectral computer-vision system. Design: Blinded comparison study. Setting: Dermatologic hospital-based clinics and private practice offices. Patients: From a computerized skin imaging database of 990 small (≤6-mm) pigmented skin lesions, all 49 melanomas from 49 patients were included in this study. Fifty randomly selected nonmelanomas from 46 patients served as a control. Main Outcome Measures: Ten dermoscopists independently examined dermoscopic images of 99 pigmented skin lesions and decided whether they identified the lesions as melanoma and whether they would recommend biopsy to rule out melanoma. Diagnostic and biopsy sensitivity and specificity were computed and then compared with the results of the computer-vision system. Results: Dermoscopists were able to correctly identify small melanomas with an average diagnostic sensitivity of 39% and a specificity of 82% and recommended small melanomas for biopsy with a sensitivity of 71% and specificity of 49%, with only fair interobserver agreement (κ=0.31 for diagnosis and 0.34 for biopsy). In comparison, in recommending biopsy to rule out melanoma, the computer-vision system achieved 98% sensitivity and 44% specificity. Conclusions: Differentiation of small melanomas from small benign pigmented lesions challenges even expert physicians. Computer-vision systems can facilitate early detection of small melanomas and may limit the number of biopsies to rule out melanoma performed on benign lesions.

UR - http://www.scopus.com/inward/record.url?scp=42549085827&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=42549085827&partnerID=8YFLogxK

U2 - 10.1001/archderm.144.4.476

DO - 10.1001/archderm.144.4.476

M3 - Article

VL - 144

SP - 476

EP - 482

JO - JAMA Dermatology

JF - JAMA Dermatology

SN - 2168-6068

IS - 4

ER -