-
Cancers Jun 2022Non-melanoma skin cancer (NMSC) treated with nonsurgical therapies can be monitored with noninvasive skin imaging. The precision of dermoscopy, reflectance confocal... (Review)
Review
BACKGROUND/OBJECTIVES
Non-melanoma skin cancer (NMSC) treated with nonsurgical therapies can be monitored with noninvasive skin imaging. The precision of dermoscopy, reflectance confocal microscopy (RCM) and optical coherence tomography (OCT) in detecting clearance is unclear. We aim to report the proportion of persisting tumors identified with noninvasive technologies available in the literature.
METHODS
A systematic literature search was conducted on the PubMed and Cochrane Public Library Databases for articles published prior to November 2021. Statistical analyses were conducted with MedCalc 14.8.1 software.
RESULTS
A total of eight studies (352 lesions) reporting noninvasive imaging for NMSC clearance following nonsurgical treatment were included. Most ( = 7) reported basal cell carcinoma (BCC), and one study reported squamous cell carcinoma (SCC) clearance. A meta-analysis of the BCC clearance revealed that the summary effect for RCM was higher, as compared to the other techniques. Interestingly, the sensitivity and specificity for OCT were 86.4% (95% CI: 65.1-97.1) and 100% (95% CI: 94.8-100.0), respectively, whilst, for RCM, they reached 100% (95%CI: 86.8-100) and 72.5% (95% CI: 64.4-79.7), respectively.
CONCLUSIONS
Routine clinical examination and dermoscopy underperform when employed for NMSC clearance monitoring, although they represent the first approach to the patient. OCT and RCM seem to improve the detection of persistent BCC after medical treatment.
PubMed: 35740502
DOI: 10.3390/cancers14122836 -
JAMA Dermatology Sep 2021Dermoscopy increases the diagnostic accuracy for melanoma. However, the accuracy of individual structures and patterns used in melanoma detection has not been... (Meta-Analysis)
Meta-Analysis
IMPORTANCE
Dermoscopy increases the diagnostic accuracy for melanoma. However, the accuracy of individual structures and patterns used in melanoma detection has not been systematically evaluated.
OBJECTIVE
To assess the diagnostic accuracy of individual dermoscopic structures and patterns used in melanoma detection.
DATA SOURCES
A search of Ovid Medline, Embase, Cochrane CENTRAL, Scopus, and Web of Science was conducted from inception to July 2020.
STUDY SELECTION
Studies evaluating the dermoscopic structures and patterns among melanomas in comparison with nonmelanoma lesions were included. Excluded were studies with fewer than 3 patients, studies in languages other than English or Spanish, studies not reporting dermoscopic structures per lesion type, and studies assessing only nail, mucosal, acral, facial, or metastatic melanomas or melanomas on chronically sun-damaged skin. Multiple reviewers applied these criteria, and 0.7% of studies met selection criteria.
DATA EXTRACTION AND SYNTHESIS
The Preferred Reporting Items for Systematic Reviews and Meta-analyses reporting guideline and Meta-analysis of Observational Studies in Epidemiology reporting guideline were followed. Guidelines were applied via independent extraction by multiple observers. Data were pooled using a random-effects model.
MAIN OUTCOMES AND MEASURES
The prespecified outcome measures were diagnostic accuracy (sensitivity and specificity) and risk (odds ratio [OR]) of melanoma for the following dermoscopic structures/patterns: atypical dots/globules, atypical network, blue-white veil, negative network, off-centered blotch, peripheral-tan structureless areas, atypical vessels (eg, linear irregular, polymorphous), pseudopods, streaks, regression (ie, peppering, scarlike areas), shiny white structures, angulated lines, irregular pigmentation, and a multicomponent pattern.
RESULTS
A total of 40 studies including 22 796 skin lesions and 5736 melanomas were evaluated. The structures and patterns with the highest ORs were shiny white structures (OR, 6.7; 95% CI, 2.5-17.9), pseudopods (OR, 6.7; 95% CI, 2.7-16.1), irregular pigmentation (OR, 6.4; 95% CI, 2.0-20.5), blue-white veil (OR, 6.3; 95% CI, 3.7-10.7), and peppering (OR, 6.3; 95% CI, 2.4-16.1). The structures with the highest specificity were pseudopods (97.3%; 95% CI, 94.3%-98.7%), shiny white structures (93.6%; 95% CI, 85.6%-97.3%), peppering (93.4%; 95% CI, 81.9%-97.8%), and streaks (92.1%; 95% CI, 88.4%-94.7%), whereas features with the highest sensitivity were irregular pigmentation (62.3%; 95% CI, 31.2%-85.8%), blue-white veil (60.6%; 95% CI, 46.7%-72.9%), atypical network (56.8%; 95% CI, 43.6%-69.2%), and a multicomponent pattern (53.7%; 95% CI, 40.4%-66.4%).
CONCLUSIONS AND RELEVANCE
The findings of this systematic review and meta-analysis support the diagnostic importance of dermoscopic structures associated with melanoma detection (eg, shiny white structures, blue-white veil), further corroborate the importance of the overall pattern, and may suggest a hierarchy in the significance of these structures and patterns.
Topics: Dermoscopy; Humans; Melanoma; Pigmentation Disorders; Retrospective Studies; Skin Diseases; Skin Neoplasms
PubMed: 34347005
DOI: 10.1001/jamadermatol.2021.2845 -
Dermatology Practical & Conceptual Oct 2023Over the last few decades, dermoscopy has been showed to facilitate the non-invasive diagnosis of both benign and malignant skin tumors, yet literature data mainly comes... (Review)
Review
Over the last few decades, dermoscopy has been showed to facilitate the non-invasive diagnosis of both benign and malignant skin tumors, yet literature data mainly comes from studies on light photo-types. However, there is growing evidence that skin neoplasms may benefit from dermoscopic assessment even for skin of color. This systematic literature review evaluated published data in dark-skinned patients (dermoscopic features, used setting, pathological correlation, and level of evidence of studies), also providing a standardized and homogeneous terminology for reported dermoscopic findings. A total of 20 articles describing 46 different tumors (four melanocytic neoplasms, eight keratinocytic tumors, 15 adnexal cutaneous neoplasms, seven vascular tumors, four connective tissue tumors, and eight cystic neoplasms/others) for a total of 1724 instances were included in the analysis. Most of them showed a level of evidence of V (12 single case reports and six case series), with only two studies featuring a level of evidence of IV (case-control analysis). Additionally, this review also underlined that some neoplasms and phototypes are underrepresented in published analyses as they included only small samples and mainly certain tones of "dark skin" spectrum (especially phototype IV). Therefore, further studies considering such limitations are required for a better characterization.
PubMed: 37874990
DOI: 10.5826/dpc.1304S1a308S -
International Journal of Environmental... Feb 2021Early detection of melanoma is critical to reduce the mortality and morbidity rates of this tumor. Total body photography (TBP) may aid in the early detection of... (Review)
Review
Early detection of melanoma is critical to reduce the mortality and morbidity rates of this tumor. Total body photography (TBP) may aid in the early detection of melanoma. To summarize the current evidence on TBP for the early detection of melanoma, we performed a systematic literature search in Medline, Embase, and the Cochrane Central Register of Controlled Trials (CENTRAL) for eligible records up to 6th August 2020. Outcomes of interest included melanoma incidence, incisional and excisional biopsy rates, as well as the Breslow's index of detected tumors. Results from individual studies were described qualitatively. The risks of bias and applicability of the included studies was assessed using the QUADAS-2 checklist. In total, 14 studies published between 1997 and 2020 with an overall sample size of = 12082 (range 100-4692) were included in the qualitative analysis. Individuals undergoing TBP showed a trend towards a lower Breslow's thickness and a higher proportion of in situ melanomas compared to those without TBP. The number needed to excise one melanoma varied from 3:1 to 14.3:1 and was better for lesions that arose de novo than for tracked ones. The included studies were judged to be of unclear methodological concern with specific deficiencies in the domains "flow and timing" and "reference standard". The use of TBP can improve the early detection of melanoma in high-risk populations. Future studies are warranted to reduce the heterogeneity of phenotypic risk factor definition and the technical implementation of TBP. Artificial intelligence-assisted analysis of images derived from 3-D TBP systems and digital dermoscopy may further improve the early detection of melanoma.
Topics: Artificial Intelligence; Dermoscopy; Humans; Melanoma; Photography; Sensitivity and Specificity; Skin Neoplasms
PubMed: 33578996
DOI: 10.3390/ijerph18041726 -
Dermatology Practical & Conceptual Nov 2022Several studies investigated the use of dermoscopy in the delineation of basal cell carcinoma (BCC) for Mohs micrographic surgery (MMS) with conflicting results. (Review)
Review
INTRODUCTION
Several studies investigated the use of dermoscopy in the delineation of basal cell carcinoma (BCC) for Mohs micrographic surgery (MMS) with conflicting results.
OBJECTIVES
The purpose of this systematic review with meta-analysis was to evaluate the effectiveness of the use of dermoscopy-guided MMS in the treatment of BCC.
METHODS
We included all comparative studies. Cases of BCC treated using dermoscopy-guided MMS (or slow MMS) were compared to those treated with curettage-guided MMS or "standard" MMS.
RESULTS
A total of 6 studies including 508 BCCs were reviewed. There was no statistically significant difference in the proportion of total margin clearance on the first MMS stage between BCCs removed using dermoscopy-guided MMS and those that had curettage or visual inspection. However, lateral margin involvement was significantly lower in BCCs that had dermoscopy-guided MMS.
CONCLUSIONS
Dermoscopy allows visualization of structures up to 1mm into the dermis. Therefore, it is rational to use it for lateral margin evaluation. Currently, there are two comparative studies showing the efficacy of dermoscopy for lateral margin evaluation during MMS. Future studies are required to develop an evidence-based recommendation regarding the utility of dermoscopy in MMS.
PubMed: 36534540
DOI: 10.5826/dpc.1204a176 -
Cancers Feb 2024The objective of this study is to systematically analyze the current state of the literature regarding novel artificial intelligence (AI) machine learning models... (Review)
Review
BACKGROUND
The objective of this study is to systematically analyze the current state of the literature regarding novel artificial intelligence (AI) machine learning models utilized in non-invasive imaging for the early detection of nonmelanoma skin cancers. Furthermore, we aimed to assess their potential clinical relevance by evaluating the accuracy, sensitivity, and specificity of each algorithm and assessing for the risk of bias.
METHODS
Two reviewers screened the MEDLINE, Cochrane, PubMed, and Embase databases for peer-reviewed studies that focused on AI-based skin cancer classification involving nonmelanoma skin cancers and were published between 2018 and 2023. The search terms included skin neoplasms, nonmelanoma, basal-cell carcinoma, squamous-cell carcinoma, diagnostic techniques and procedures, artificial intelligence, algorithms, computer systems, dermoscopy, reflectance confocal microscopy, and optical coherence tomography. Based on the search results, only studies that directly answered the review objectives were included and the efficacy measures for each were recorded. A QUADAS-2 risk assessment for bias in included studies was then conducted.
RESULTS
A total of 44 studies were included in our review; 40 utilizing dermoscopy, 3 using reflectance confocal microscopy (RCM), and 1 for hyperspectral epidermal imaging (HEI). The average accuracy of AI algorithms applied to all imaging modalities combined was 86.80%, with the same average for dermoscopy. Only one of the three studies applying AI to RCM measured accuracy, with a result of 87%. Accuracy was not measured in regard to AI based HEI interpretation.
CONCLUSION
AI algorithms exhibited an overall favorable performance in the diagnosis of nonmelanoma skin cancer via noninvasive imaging techniques. Ultimately, further research is needed to isolate pooled diagnostic accuracy for nonmelanoma skin cancers as many testing datasets also include melanoma and other pigmented lesions.
PubMed: 38339380
DOI: 10.3390/cancers16030629 -
The Lancet. Digital Health Jan 2022Publicly available skin image datasets are increasingly used to develop machine learning algorithms for skin cancer diagnosis. However, the total number of datasets and...
Publicly available skin image datasets are increasingly used to develop machine learning algorithms for skin cancer diagnosis. However, the total number of datasets and their respective content is currently unclear. This systematic review aimed to identify and evaluate all publicly available skin image datasets used for skin cancer diagnosis by exploring their characteristics, data access requirements, and associated image metadata. A combined MEDLINE, Google, and Google Dataset search identified 21 open access datasets containing 106 950 skin lesion images, 17 open access atlases, eight regulated access datasets, and three regulated access atlases. Images and accompanying data from open access datasets were evaluated by two independent reviewers. Among the 14 datasets that reported country of origin, most (11 [79%]) originated from Europe, North America, and Oceania exclusively. Most datasets (19 [91%]) contained dermoscopic images or macroscopic photographs only. Clinical information was available regarding age for 81 662 images (76·4%), sex for 82 848 (77·5%), and body site for 79 561 (74·4%). Subject ethnicity data were available for 1415 images (1·3%), and Fitzpatrick skin type data for 2236 (2·1%). There was limited and variable reporting of characteristics and metadata among datasets, with substantial under-representation of darker skin types. This is the first systematic review to characterise publicly available skin image datasets, highlighting limited applicability to real-life clinical settings and restricted population representation, precluding generalisability. Quality standards for characteristics and metadata reporting for skin image datasets are needed.
Topics: Datasets as Topic; Dermoscopy; Humans; Machine Learning; Skin Neoplasms
PubMed: 34772649
DOI: 10.1016/S2589-7500(21)00252-1 -
Acta Dermato-venereologica Oct 2021Trichotillomania is formally classified as a mental health disorder, but it is commonly diagnosed by dermatologists. The aim of this systematic review is to assess the...
Trichotillomania is formally classified as a mental health disorder, but it is commonly diagnosed by dermatologists. The aim of this systematic review is to assess the diagnostic value of trichoscopy in diagnosing trichotillomania. The analysis identified the 7 most specific trichoscopic features in trichotillomania. These features had the following prevalence and specificity: trichoptilosis (57.5%; 73/127 and 97.5%, respectively), v-sign (50.4%; 63/125 and 99%), hook hairs (43.1%; 28/65 and 100%), flame hairs (37.1%; 52/140 and 96.5%), coiled hairs (36.8%; 46/125 and 99.6%), tulip hairs (36.4%; 28/77 and 89.6%), and hair powder (35.6%; 42/118 and 97.9%). The 2 most common, but least specific, features were broken hairs and black dots. In conclusion, trichoscopy is a reliable new diagnostic method for hair loss caused by hair pulling. Trichoscopy should be included as a standard procedure in the differential diagnosis of trichotillomania in clinical practice.
Topics: Alopecia; Dermoscopy; Diagnosis, Differential; Hair; Humans; Trichotillomania
PubMed: 34184065
DOI: 10.2340/00015555-3859 -
Journal of Medical Internet Research Jul 2021Recent years have been witnessing a substantial improvement in the accuracy of skin cancer classification using convolutional neural networks (CNNs). CNNs perform on par... (Review)
Review
BACKGROUND
Recent years have been witnessing a substantial improvement in the accuracy of skin cancer classification using convolutional neural networks (CNNs). CNNs perform on par with or better than dermatologists with respect to the classification tasks of single images. However, in clinical practice, dermatologists also use other patient data beyond the visual aspects present in a digitized image, further increasing their diagnostic accuracy. Several pilot studies have recently investigated the effects of integrating different subtypes of patient data into CNN-based skin cancer classifiers.
OBJECTIVE
This systematic review focuses on the current research investigating the impact of merging information from image features and patient data on the performance of CNN-based skin cancer image classification. This study aims to explore the potential in this field of research by evaluating the types of patient data used, the ways in which the nonimage data are encoded and merged with the image features, and the impact of the integration on the classifier performance.
METHODS
Google Scholar, PubMed, MEDLINE, and ScienceDirect were screened for peer-reviewed studies published in English that dealt with the integration of patient data within a CNN-based skin cancer classification. The search terms skin cancer classification, convolutional neural network(s), deep learning, lesions, melanoma, metadata, clinical information, and patient data were combined.
RESULTS
A total of 11 publications fulfilled the inclusion criteria. All of them reported an overall improvement in different skin lesion classification tasks with patient data integration. The most commonly used patient data were age, sex, and lesion location. The patient data were mostly one-hot encoded. There were differences in the complexity that the encoded patient data were processed with regarding deep learning methods before and after fusing them with the image features for a combined classifier.
CONCLUSIONS
This study indicates the potential benefits of integrating patient data into CNN-based diagnostic algorithms. However, how exactly the individual patient data enhance classification performance, especially in the case of multiclass classification problems, is still unclear. Moreover, a substantial fraction of patient data used by dermatologists remains to be analyzed in the context of CNN-based skin cancer classification. Further exploratory analyses in this promising field may optimize patient data integration into CNN-based skin cancer diagnostics for patients' benefits.
Topics: Dermoscopy; Humans; Melanoma; Neural Networks, Computer; Skin Neoplasms
PubMed: 34255646
DOI: 10.2196/20708 -
JAMA Dermatology Oct 2019To date, no concerted effort has been made to date to evaluate the literature on number-needed-to-biopsy (NNB) metrics, particularly to account for the differences in...
IMPORTANCE
To date, no concerted effort has been made to date to evaluate the literature on number-needed-to-biopsy (NNB) metrics, particularly to account for the differences in clinician type and melanoma prevalence in certain geographic locations.
OBJECTIVE
To review and synthesize worldwide data for NNB for the diagnosis of cutaneous melanoma.
DATA SOURCE
MEDLINE, Embase, and PubMed databases were searched for English-language articles published worldwide from January 1, 2000, to November 28, 2018.
STUDY SELECTION
A total of 46 studies were included that addressed NNB for at least 3681 clinicians worldwide and included 455 496 biopsied tumors and 29 257 melanomas; primary care practitioner (PCP) data were only available from Australia.
DATA EXTRACTION AND SYNTHESIS
Articles were screened for eligibility, and possible overlapping data sets were resolved. Data extracted included clinician specialization, use of dermoscopy, geographic region and location-specific health care system, study design, number of benign tumors, number of melanomas, and NNB. The review followed the PRISMA guidelines.
MAIN OUTCOME AND MEASURES
The NNB for the diagnosis of cutaneous melanoma.
RESULTS
A total of 46 studies were included that addressed NNB for at least 3681 clinicians worldwide and included 455 496 biopsied tumors and 29 257 melanomas; primary care practitioner (PCP) data were only available from Australia. The reported NNB ranged from 2.2 to 287, and the weighted mean NNB for all included publications was 15.6. The exclusion of publications structured as all biopsied tumors, owing to variable data characterization, resulted in reported NNB ranging from 2.2 to 30.5, with a global weighted mean NNB of 14.8 for all clinicians, 7.5 for all dermatologists, 14.6 for Australian PCPs, and 13.2 for all US-based dermatological practitioners, including dermatologists and advanced practice professionals. The summary effect size (ES) demonstrates that a mean 4% of biopsies demonstrated melanoma for study stratum A (all biopsied skin tumors, ES, 0.04; 95% CI, 0.03-0.05), and a mean 12% of biopsies demonstrated melanoma for study strata B (melanocytic tumors on pathology review, ES, 0.12; 95% CI, 0.10-0.14) and C (clinical concern for melanoma, ES; 0.12; 95% CI, 0.09-0.14).
CONCLUSIONS AND RELEVANCE
The existing NNB for cutaneous melanoma appeared to vary widely worldwide, lacking standardization in the metric and its reporting, and according to clinician characteristics as well; the NNB of US-based clinicians may warrant further exploration.
PubMed: 31290958
DOI: 10.1001/jamadermatol.2019.1514