Dermoscopy in differential diagnosis of inflammatory dermatoses and mycosis fungoides

Bilgic, Sultan A; Çiçek, Demet; Demir, Betül

doi:10.1111/ijd.14925

Cited by 23 publications

(35 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although it is traditionally used in the assessment of both melanocytic and non-melanocytic proliferative lesions as well as hair disorders [1][2][3], dermoscopy is increasingly gaining appreciation in the spectrum of non-tumoral skin conditions (i.e. general dermatology), including inflammatory, pigmentary, infectious and infiltrative dermatoses, with consequent reduction in the number of cases requiring biopsy [3][4][5][6][7][8][9][10][11][12]. In this regard, such a technique has been shown to have further applications apart from assisting the clinical diagnosis, including predicting and monitoring therapeutic outcomes, with the consequent improvement/optimization of the management of non-tumoral dermatoses [3][4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Dermoscopy in Monitoring and Predicting Therapeutic Response in General Dermatology (Non-Tumoral Dermatoses): An Up-To-Date Overview

Errichetti

2020

Dermatol Ther (Heidelb)

View full text Add to dashboard Cite

Besides the well-known use in supporting the non-invasive diagnosis of non-tumoral dermatoses (general dermatology), dermoscopy has been shown to be a promising tool also in predicting and monitoring therapeutic outcomes of such conditions, with the consequent improvement/optimization of their treatment. In the present paper, we sought to provide an up-to-date overview on the use of dermoscopy in highlighting response predictor factors and evaluating therapeutic results in the field of general dermatology according to the current literature data. Several dermatoses may somehow benefit from such applications, including inflammatory conditions (psoriasis, lichen planus, dermatitis, granulomatous conditions, erythro-telangiectatic rosacea, Zoon balanitis and vulvitis, cutaneous mastocytosis, morphea and extra-genital lichen sclerosus), pigmentary disorders (vitiligo and melasma) and infectious dermatoses (scabies, pediculosis, demodicosis and viral warts).

show abstract

Section: Introductionmentioning

confidence: 99%

Dermoscopy in Monitoring and Predicting Therapeutic Response in General Dermatology (Non-Tumoral Dermatoses): An Up-To-Date Overview

Errichetti

2020

Dermatol Ther (Heidelb)

View full text Add to dashboard Cite

show abstract

“…Therefore, there is a need to develop a system that can also detect other skin tumors that have a pigmented appearance similar to malignant melanoma. There are also erythematosus skin malignancies, such as mycosis fungoides [6], extramammary Paget's disease [7], and actinic keratosis [8], which is a premalignant tumor of squamous cell carcinoma. It is often difficult to distinguish these cancers from eczema.…”

Section: Introductionmentioning

confidence: 99%

The Development of a Skin Cancer Classification System for Pigmented Skin Lesions Using Deep Learning

Jinnai¹,

Yamazaki²,

Hirano

et al. 2020

Biomolecules

176

View full text Add to dashboard Cite

Recent studies have demonstrated the usefulness of convolutional neural networks (CNNs) to classify images of melanoma, with accuracies comparable to those achieved by dermatologists. However, the performance of a CNN trained with only clinical images of a pigmented skin lesion in a clinical image classification task, in competition with dermatologists, has not been reported to date. In this study, we extracted 5846 clinical images of pigmented skin lesions from 3551 patients. Pigmented skin lesions included malignant tumors (malignant melanoma and basal cell carcinoma) and benign tumors (nevus, seborrhoeic keratosis, senile lentigo, and hematoma/hemangioma). We created the test dataset by randomly selecting 666 patients out of them and picking one image per patient, and created the training dataset by giving bounding-box annotations to the rest of the images (4732 images, 2885 patients). Subsequently, we trained a faster, region-based CNN (FRCNN) with the training dataset and checked the performance of the model on the test dataset. In addition, ten board-certified dermatologists (BCDs) and ten dermatologic trainees (TRNs) took the same tests, and we compared their diagnostic accuracy with FRCNN. For six-class classification, the accuracy of FRCNN was 86.2%, and that of the BCDs and TRNs was 79.5% (p = 0.0081) and 75.1% (p < 0.00001), respectively. For two-class classification (benign or malignant), the accuracy, sensitivity, and specificity were 91.5%, 83.3%, and 94.5% by FRCNN; 86.6%, 86.3%, and 86.6% by BCD; and 85.3%, 83.5%, and 85.9% by TRN, respectively. False positive rates and positive predictive values were 5.5% and 84.7% by FRCNN, 13.4% and 70.5% by BCD, and 14.1% and 68.5% by TRN, respectively. We compared the classification performance of FRCNN with 20 dermatologists. As a result, the classification accuracy of FRCNN was better than that of the dermatologists. In the future, we plan to implement this system in society and have it used by the general public, in order to improve the prognosis of skin cancer.

show abstract

“…Dermoscopy is nowadays a key part of the diagnostic process when it comes to proliferative lesions (melanocytic and nonmelanocytic) and hair disorders as it allows providers to appreciate characteristics not visible to the naked eye 1 . Additionally, this technique is also gaining appreciation in the spectrum of non‐neoplastic skin conditions (i.e., general dermatology), including inflammatory, infectious, and infiltrative dermatoses 2‐11 . In this regard, several diseases have been shown to benefit from dermoscopic examination, especially papulosquamous and granulomatous dermatoses 7,11 .…”

Section: Introductionmentioning

confidence: 99%

Dermoscopy in general dermatology (non‐neoplastic dermatoses): pitfalls and tips

Errichetti

2021

Int J Dermatology

View full text Add to dashboard Cite

BackgroundDermoscopy is gaining appreciation in the spectrum of non‐neoplastic skin conditions, especially papulosquamous and granulomatous dermatoses. However, the use of dermoscopy in such diseases has not yet acquired a standard role in daily practice due to the lack of a structured approach as well as possible pitfalls limiting its accuracy. MethodsA descriptive analysis of the most common limitations/pitfalls described in the literature regarding dermoscopy of non‐neoplastic dermatoses was performed, also providing possible tips to deal with them. ResultsThe following items were analyzed: “two‐step” dermoscopic procedure and basic dermoscopic parameters in non‐neoplastic dermatoses, uniform dotted vessels in dermatoses other than psoriasis, pseudo‐Wickham striae, yellow sero‐crusts in non‐eczematous dermatoses, peripheral scaling collarette in conditions other than pityriasis rosea, orange areas in non‐granulomatous dermatoses, and dermoscopic variability of Grover disease according to histological subtype. ConclusionsDermoscopy is candidate to become a relevant part of diagnostic approach to non‐neoplastic dermatoses, yet only the use of a systematic/validated methodology and the in‐depth knowledge of possible pitfalls may optimize its use in this field.

show abstract

Dermoscopy in differential diagnosis of inflammatory dermatoses and mycosis fungoides

Cited by 23 publications

References 17 publications

Dermoscopy in Monitoring and Predicting Therapeutic Response in General Dermatology (Non-Tumoral Dermatoses): An Up-To-Date Overview

Dermoscopy in Monitoring and Predicting Therapeutic Response in General Dermatology (Non-Tumoral Dermatoses): An Up-To-Date Overview

The Development of a Skin Cancer Classification System for Pigmented Skin Lesions Using Deep Learning

Dermoscopy in general dermatology (non‐neoplastic dermatoses): pitfalls and tips

Contact Info

Product

Resources

About