Skin cancer diagnosis with Reflectance confocal microscopy: Reproducibility of feature recognition and accuracy of diagnosis

Francesca Farnetani, Alon Scope, Ralph P. Braun, Salvador Gonzalez, Pascale Guitera, Josep Malvehy, Marco Manfredini, Ashfaq A. Marghoob, Elvira Moscarella, Margaret Oliviero, Susana Puig, Harold S. Rabinovitz, Ignazio Stanganelli, Caterina Longo, Carlotta Malagoli, Marco Vinceti, Giovanni Pellacani

Research output: Contribution to journalArticle

61 Citations (Scopus)

Abstract

IMPORTANCE: Reflectance confocal microscopy (RCM) studies have been performed to identify criteria for diagnosis of skin neoplasms. However, RCM-based diagnosis is operator dependent. Hence, reproducibility of RCM criteria needs to be tested. OBJECTIVE: To test interobserver reproducibility of recognition of previously published RCM descriptors and accuracy of RCM-based skin cancer diagnosis. DESIGN, SETTING, AND PARTICIPANTS: Observational retrospectiveweb-based study of a set of RCM images collected at a tertiary academic medical center. Nine dermatologists (6 of whom had ≥3 years of RCM experience) from 6 countries evaluated an RCM study set from 100 biopsy-proven lesions, including 55 melanocytic nevi, 20 melanomas, 15 basal cell carcinomas, 7 solar lentigines or seborrheic keratoses, and 3 actinic keratoses. Between June 15, 2010, and October 21, 2010, participanting dermatologists, blinded to histopathological diagnosis, evaluated 3 RCM mosaic images per lesion for the presence of predefined RCM descriptors. MAIN OUTCOMES AND MEASURES: The main outcomewas identification of RCM descriptors with fair to good interrater agreement (κ statistic ≥0.3) and independent correlation with malignant vs benign diagnosis on discriminant analysis. Additional measures included sensitivity and specificity for diagnosis of malignant vs benign for each evaluator, for majority diagnosis (rendered by ≥5 of 9 evaluators), and for experienced vs recent RCM users. RESULTS: Eight RCM descriptors showed fair to good reproducibility and were independently associated with a specific diagnosis. Of these, the presence of pagetoid cells, atypical cells at the dermal-epidermal junction, and irregular epidermal architecture were associated with melanoma. Aspecific junctional pattern, basaloid cords, and ulceration were associated with basal cell carcinomas. Ringed junctional pattern and dermal nests were associated with nevi. The mean sensitivity for the group of evaluators was 88.9% (range, 82.9%-100%), and the mean specificity was 79.3%(range, 69.2%-90.8%). Majority diagnosis showed sensitivity of 100% and specificity of 80.0%. Sensitivity was higher for experienced vs recent RCM users (91.0% vs 84.8%), but specificity was similar (80.0%vs 77.9%). CONCLUSIONS AND RELEVANCE: The study highlights key RCM diagnostic criteria for melanoma and basal cell carcinoma that are reproducibly recognized among RCM users. Diagnostic accuracy increases with experience. The higher accuracy of majority diagnosis suggests that there is intrinsically more diagnostic information in RCM images than is currently used by individual evaluators.

Original languageEnglish
Pages (from-to)1075-1080
Number of pages6
JournalJAMA Dermatology
Volume151
Issue number10
DOIs
Publication statusPublished - Oct 1 2015

Fingerprint

Skin Neoplasms
Confocal Microscopy
Basal Cell Carcinoma
Melanoma
Seborrheic Keratosis
Lentigo
Nevi and Melanomas
Actinic Keratosis
Pigmented Nevus
Sensitivity and Specificity
Skin
Nevus
Discriminant Analysis

ASJC Scopus subject areas

  • Dermatology
  • Medicine(all)

Cite this

Farnetani, F., Scope, A., Braun, R. P., Gonzalez, S., Guitera, P., Malvehy, J., ... Pellacani, G. (2015). Skin cancer diagnosis with Reflectance confocal microscopy: Reproducibility of feature recognition and accuracy of diagnosis. JAMA Dermatology, 151(10), 1075-1080. https://doi.org/10.1001/jamadermatol.2015.0810

Skin cancer diagnosis with Reflectance confocal microscopy : Reproducibility of feature recognition and accuracy of diagnosis. / Farnetani, Francesca; Scope, Alon; Braun, Ralph P.; Gonzalez, Salvador; Guitera, Pascale; Malvehy, Josep; Manfredini, Marco; Marghoob, Ashfaq A.; Moscarella, Elvira; Oliviero, Margaret; Puig, Susana; Rabinovitz, Harold S.; Stanganelli, Ignazio; Longo, Caterina; Malagoli, Carlotta; Vinceti, Marco; Pellacani, Giovanni.

In: JAMA Dermatology, Vol. 151, No. 10, 01.10.2015, p. 1075-1080.

Research output: Contribution to journalArticle

Farnetani, F, Scope, A, Braun, RP, Gonzalez, S, Guitera, P, Malvehy, J, Manfredini, M, Marghoob, AA, Moscarella, E, Oliviero, M, Puig, S, Rabinovitz, HS, Stanganelli, I, Longo, C, Malagoli, C, Vinceti, M & Pellacani, G 2015, 'Skin cancer diagnosis with Reflectance confocal microscopy: Reproducibility of feature recognition and accuracy of diagnosis', JAMA Dermatology, vol. 151, no. 10, pp. 1075-1080. https://doi.org/10.1001/jamadermatol.2015.0810
Farnetani, Francesca ; Scope, Alon ; Braun, Ralph P. ; Gonzalez, Salvador ; Guitera, Pascale ; Malvehy, Josep ; Manfredini, Marco ; Marghoob, Ashfaq A. ; Moscarella, Elvira ; Oliviero, Margaret ; Puig, Susana ; Rabinovitz, Harold S. ; Stanganelli, Ignazio ; Longo, Caterina ; Malagoli, Carlotta ; Vinceti, Marco ; Pellacani, Giovanni. / Skin cancer diagnosis with Reflectance confocal microscopy : Reproducibility of feature recognition and accuracy of diagnosis. In: JAMA Dermatology. 2015 ; Vol. 151, No. 10. pp. 1075-1080.
@article{f7f43be7c2ff48a49f6066934084c378,
title = "Skin cancer diagnosis with Reflectance confocal microscopy: Reproducibility of feature recognition and accuracy of diagnosis",
abstract = "IMPORTANCE: Reflectance confocal microscopy (RCM) studies have been performed to identify criteria for diagnosis of skin neoplasms. However, RCM-based diagnosis is operator dependent. Hence, reproducibility of RCM criteria needs to be tested. OBJECTIVE: To test interobserver reproducibility of recognition of previously published RCM descriptors and accuracy of RCM-based skin cancer diagnosis. DESIGN, SETTING, AND PARTICIPANTS: Observational retrospectiveweb-based study of a set of RCM images collected at a tertiary academic medical center. Nine dermatologists (6 of whom had ≥3 years of RCM experience) from 6 countries evaluated an RCM study set from 100 biopsy-proven lesions, including 55 melanocytic nevi, 20 melanomas, 15 basal cell carcinomas, 7 solar lentigines or seborrheic keratoses, and 3 actinic keratoses. Between June 15, 2010, and October 21, 2010, participanting dermatologists, blinded to histopathological diagnosis, evaluated 3 RCM mosaic images per lesion for the presence of predefined RCM descriptors. MAIN OUTCOMES AND MEASURES: The main outcomewas identification of RCM descriptors with fair to good interrater agreement (κ statistic ≥0.3) and independent correlation with malignant vs benign diagnosis on discriminant analysis. Additional measures included sensitivity and specificity for diagnosis of malignant vs benign for each evaluator, for majority diagnosis (rendered by ≥5 of 9 evaluators), and for experienced vs recent RCM users. RESULTS: Eight RCM descriptors showed fair to good reproducibility and were independently associated with a specific diagnosis. Of these, the presence of pagetoid cells, atypical cells at the dermal-epidermal junction, and irregular epidermal architecture were associated with melanoma. Aspecific junctional pattern, basaloid cords, and ulceration were associated with basal cell carcinomas. Ringed junctional pattern and dermal nests were associated with nevi. The mean sensitivity for the group of evaluators was 88.9{\%} (range, 82.9{\%}-100{\%}), and the mean specificity was 79.3{\%}(range, 69.2{\%}-90.8{\%}). Majority diagnosis showed sensitivity of 100{\%} and specificity of 80.0{\%}. Sensitivity was higher for experienced vs recent RCM users (91.0{\%} vs 84.8{\%}), but specificity was similar (80.0{\%}vs 77.9{\%}). CONCLUSIONS AND RELEVANCE: The study highlights key RCM diagnostic criteria for melanoma and basal cell carcinoma that are reproducibly recognized among RCM users. Diagnostic accuracy increases with experience. The higher accuracy of majority diagnosis suggests that there is intrinsically more diagnostic information in RCM images than is currently used by individual evaluators.",
author = "Francesca Farnetani and Alon Scope and Braun, {Ralph P.} and Salvador Gonzalez and Pascale Guitera and Josep Malvehy and Marco Manfredini and Marghoob, {Ashfaq A.} and Elvira Moscarella and Margaret Oliviero and Susana Puig and Rabinovitz, {Harold S.} and Ignazio Stanganelli and Caterina Longo and Carlotta Malagoli and Marco Vinceti and Giovanni Pellacani",
year = "2015",
month = "10",
day = "1",
doi = "10.1001/jamadermatol.2015.0810",
language = "English",
volume = "151",
pages = "1075--1080",
journal = "JAMA Dermatology",
issn = "2168-6068",
publisher = "American Medical Association",
number = "10",

}

TY - JOUR

T1 - Skin cancer diagnosis with Reflectance confocal microscopy

T2 - Reproducibility of feature recognition and accuracy of diagnosis

AU - Farnetani, Francesca

AU - Scope, Alon

AU - Braun, Ralph P.

AU - Gonzalez, Salvador

AU - Guitera, Pascale

AU - Malvehy, Josep

AU - Manfredini, Marco

AU - Marghoob, Ashfaq A.

AU - Moscarella, Elvira

AU - Oliviero, Margaret

AU - Puig, Susana

AU - Rabinovitz, Harold S.

AU - Stanganelli, Ignazio

AU - Longo, Caterina

AU - Malagoli, Carlotta

AU - Vinceti, Marco

AU - Pellacani, Giovanni

PY - 2015/10/1

Y1 - 2015/10/1

N2 - IMPORTANCE: Reflectance confocal microscopy (RCM) studies have been performed to identify criteria for diagnosis of skin neoplasms. However, RCM-based diagnosis is operator dependent. Hence, reproducibility of RCM criteria needs to be tested. OBJECTIVE: To test interobserver reproducibility of recognition of previously published RCM descriptors and accuracy of RCM-based skin cancer diagnosis. DESIGN, SETTING, AND PARTICIPANTS: Observational retrospectiveweb-based study of a set of RCM images collected at a tertiary academic medical center. Nine dermatologists (6 of whom had ≥3 years of RCM experience) from 6 countries evaluated an RCM study set from 100 biopsy-proven lesions, including 55 melanocytic nevi, 20 melanomas, 15 basal cell carcinomas, 7 solar lentigines or seborrheic keratoses, and 3 actinic keratoses. Between June 15, 2010, and October 21, 2010, participanting dermatologists, blinded to histopathological diagnosis, evaluated 3 RCM mosaic images per lesion for the presence of predefined RCM descriptors. MAIN OUTCOMES AND MEASURES: The main outcomewas identification of RCM descriptors with fair to good interrater agreement (κ statistic ≥0.3) and independent correlation with malignant vs benign diagnosis on discriminant analysis. Additional measures included sensitivity and specificity for diagnosis of malignant vs benign for each evaluator, for majority diagnosis (rendered by ≥5 of 9 evaluators), and for experienced vs recent RCM users. RESULTS: Eight RCM descriptors showed fair to good reproducibility and were independently associated with a specific diagnosis. Of these, the presence of pagetoid cells, atypical cells at the dermal-epidermal junction, and irregular epidermal architecture were associated with melanoma. Aspecific junctional pattern, basaloid cords, and ulceration were associated with basal cell carcinomas. Ringed junctional pattern and dermal nests were associated with nevi. The mean sensitivity for the group of evaluators was 88.9% (range, 82.9%-100%), and the mean specificity was 79.3%(range, 69.2%-90.8%). Majority diagnosis showed sensitivity of 100% and specificity of 80.0%. Sensitivity was higher for experienced vs recent RCM users (91.0% vs 84.8%), but specificity was similar (80.0%vs 77.9%). CONCLUSIONS AND RELEVANCE: The study highlights key RCM diagnostic criteria for melanoma and basal cell carcinoma that are reproducibly recognized among RCM users. Diagnostic accuracy increases with experience. The higher accuracy of majority diagnosis suggests that there is intrinsically more diagnostic information in RCM images than is currently used by individual evaluators.

AB - IMPORTANCE: Reflectance confocal microscopy (RCM) studies have been performed to identify criteria for diagnosis of skin neoplasms. However, RCM-based diagnosis is operator dependent. Hence, reproducibility of RCM criteria needs to be tested. OBJECTIVE: To test interobserver reproducibility of recognition of previously published RCM descriptors and accuracy of RCM-based skin cancer diagnosis. DESIGN, SETTING, AND PARTICIPANTS: Observational retrospectiveweb-based study of a set of RCM images collected at a tertiary academic medical center. Nine dermatologists (6 of whom had ≥3 years of RCM experience) from 6 countries evaluated an RCM study set from 100 biopsy-proven lesions, including 55 melanocytic nevi, 20 melanomas, 15 basal cell carcinomas, 7 solar lentigines or seborrheic keratoses, and 3 actinic keratoses. Between June 15, 2010, and October 21, 2010, participanting dermatologists, blinded to histopathological diagnosis, evaluated 3 RCM mosaic images per lesion for the presence of predefined RCM descriptors. MAIN OUTCOMES AND MEASURES: The main outcomewas identification of RCM descriptors with fair to good interrater agreement (κ statistic ≥0.3) and independent correlation with malignant vs benign diagnosis on discriminant analysis. Additional measures included sensitivity and specificity for diagnosis of malignant vs benign for each evaluator, for majority diagnosis (rendered by ≥5 of 9 evaluators), and for experienced vs recent RCM users. RESULTS: Eight RCM descriptors showed fair to good reproducibility and were independently associated with a specific diagnosis. Of these, the presence of pagetoid cells, atypical cells at the dermal-epidermal junction, and irregular epidermal architecture were associated with melanoma. Aspecific junctional pattern, basaloid cords, and ulceration were associated with basal cell carcinomas. Ringed junctional pattern and dermal nests were associated with nevi. The mean sensitivity for the group of evaluators was 88.9% (range, 82.9%-100%), and the mean specificity was 79.3%(range, 69.2%-90.8%). Majority diagnosis showed sensitivity of 100% and specificity of 80.0%. Sensitivity was higher for experienced vs recent RCM users (91.0% vs 84.8%), but specificity was similar (80.0%vs 77.9%). CONCLUSIONS AND RELEVANCE: The study highlights key RCM diagnostic criteria for melanoma and basal cell carcinoma that are reproducibly recognized among RCM users. Diagnostic accuracy increases with experience. The higher accuracy of majority diagnosis suggests that there is intrinsically more diagnostic information in RCM images than is currently used by individual evaluators.

UR - http://www.scopus.com/inward/record.url?scp=84944345325&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944345325&partnerID=8YFLogxK

U2 - 10.1001/jamadermatol.2015.0810

DO - 10.1001/jamadermatol.2015.0810

M3 - Article

C2 - 25993262

AN - SCOPUS:84944345325

VL - 151

SP - 1075

EP - 1080

JO - JAMA Dermatology

JF - JAMA Dermatology

SN - 2168-6068

IS - 10

ER -