Automated Epiluminescence Microscopy: Human vs Machine in the Diagnosis of Melanoma

Menzies, Scott W.

doi:10.1001/archderm.135.12.1538

Cited by 41 publications

(25 citation statements)

References 24 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…48,[75][76][77][78] Some systems even offer the potential of ''computerassisted diagnosis.'' [79][80][81][82][83][84][85][86][87][88][89][90][91][92][93][94] Because diagnostic accuracy with dermoscopy has been shown to depend on the experience of the dermatologist, such objective systems might help less-experienced dermatologists in the future.…”

Section: Perspectivesmentioning

confidence: 99%

Dermoscopy of pigmented skin lesions

Braun

Rabinovitz

Oliviero

et al. 2005

Journal of the American Academy of Dermatology

311

186

View full text Add to dashboard Cite

Section: Perspectivesmentioning

confidence: 99%

Dermoscopy of pigmented skin lesions

Braun

Rabinovitz

Oliviero

et al. 2005

Journal of the American Academy of Dermatology

311

186

View full text Add to dashboard Cite

“…At present, experienced examiners can even reach a diagnostic accuracy up to 95% [Meyer, 1997;Kittler et al, 2002;Stolz et al, 2002]. Similar values could be provided by computer-based expert systems using digital dermoscopy [Schindewolf et al, 1994;Horsch et al, 1997;Binder et al, 1998;Menzies, 1999;Pompl et al, 1999;Seidenari et al, 1999]. Digital images bear also the possibility of teledermoscopy by connecting private dermatological practices with specialists at a dermoscopy center [Glaessl et al, 1999;Piccolo et al, 1999;Glaessl et al, 2000;Argenziano et al, 2000;Braun et al, 2000].…”

Section: Patientenvertrauen In Dermatoskopische Methoden Zur Entdeckumentioning

confidence: 92%

Patients’ Confidence in Dermoscopical Methods for Detection of Malignant Melanoma

Schiffner¹,

Schiffner-Rohe²,

Landthaler³

2002

Dermatol Psychosom

View full text Add to dashboard Cite

Background: At present, different methods are available for the detection of malignant melanoma or for monitoring of melanocytic nevi (MN). Diagnostic accuracy and time consumption increase from naked-eye inspection (NEI) to handheld dermoscopy (HHD), digital dermoscopy (DD) including image analysis, and teledermoscopy (TD) supported by a specialist in dermoscopy. Effectiveness in daily routine depends on both physician’s experience and patient’s compliance. Objective: To analyse patient’s confidence in these diagnostic tools. Material and Methods: A self-administered survey was performed in consecutive patients after examination of MN at 13 private dermatological practices and at the Department of Dermatology of the University of Regensburg. Confidence was assessed by a 5-step ordinal scale ranging from 1 to 5 (higher values indicate higher confidence) and by willingness-to-pay (wtp) as health-economic instrument. Additionally, wtp was assessed for a hypothetical method promising 100% accuracy. Results: Data of 96 patients (mean age 35 years, 56% female) could be analysed. Mean confidence was 1.8 ± 0.9 for NEI, 2.9 ± 0.8 for HHD, 4.3 ± 0.6 for DD, and 4.8 ± 0.7 for TD. Mean wtp per examination was 0.6% ± 0.9 of monthly income (EUR 12.70 ± 15.40) for NEI, 1.2% ± 1.8 (EUR 23.60 ± 20.40) for HHD, 2.9% ± 3.1 (EUR 55.50 ± 42.30) for DD, 3.2% ± 3.9 (EUR 57.90 ± 42.60) for TD, and 5.3% ± 8.1 (EUR 96.10 ± 69.10) for the hypothetical method. Differences between methods were statistically significant (p < 0.001). Compared to the hypothetical method, NEI achieved only 13.2%, HHD 24.6%, DD 57.7%, and TD 60.2% of maximum confidence. Conclusions: Patients’ confidence was highest for TD, HHD was clearly underestimated. Wtp was similar for DD and TD – the best methods available at present – but still 40% lower than for a hypothetical diagnostic method providing 100% accuracy. Better information of patients about the diagnostic accuracy of different methods for detection of malignant melanoma is necessary in order to increase their confidence and compliance.

show abstract

“…One of the most common approaches is to derive basic statistics of colour properties in RGB or other colour spaces. Mean, standard deviation and other simple measures are computed for colours occurring in the lesion and in the surrounding skin, providing colour-related quantitative parameters for subsequent lesion classification [9, 11, 12,25,26,27,28,29,30]. …”

Section: Discussionmentioning

confidence: 99%

Colour Clusters for Computer Diagnosis of Melanocytic Lesions

Seidenari

Grana²,

Pellacani³

2007

Dermatology

View full text Add to dashboard Cite

Background: To overcome subjectivity and variability in the interpretation of dermoscopic images, image analysis programs, enabling the numerical description of melanocytic lesion images, have been developed. Objectives: Our aim was to assess a method for the description of colours in melanocytic lesion images, based on the subdivision of image colours into red, green and blue clusters. Methods: Melanomas and naevi of the test set were described by means of 23 colour clusters previously selected by a training set comprising 369 melanocytic lesion images. The diagnostic performance obtained by this automated method was compared to sensitivity and specificity of diagnosis of 4 dermatologists. Results: Colour cluster values significantly differed between melanomas and naevi. Moreover, sensitivity and specificity values of computer diagnosis were similar to those achieved by the dermatologists. Conclusion: Our image analysis program based on the assessment of one single parameter has the diagnostic accuracy of dermatologists employing dermoscopy on a regular basis.

show abstract

Automated Epiluminescence Microscopy: Human vs Machine in the Diagnosis of Melanoma

Cited by 41 publications

References 24 publications

Dermoscopy of pigmented skin lesions

Dermoscopy of pigmented skin lesions

Patients’ Confidence in Dermoscopical Methods for Detection of Malignant Melanoma

Colour Clusters for Computer Diagnosis of Melanocytic Lesions

Contact Info

Product

Resources

About