Faculty Bibliography

Incorporation of dermoscopy and artificial intelligence (AI) is improving healthcare professionals' ability to diagnose melanoma earlier, but these algorithms often suffer from a "black box" issue, where decision-making processes are not transparent, limiting their utility for training healthcare providers. To address this, an automated approach for generating melanoma imaging biomarker cues (IBCs), which mimics the screening cues used by expert dermoscopists, was developed. This study created a one-minute learning environment where dermatologists adopted a sensory cue integration algorithm to combine a single IBC with a risk score built on many IBCs, then immediately tested their performance in differentiating melanoma from benign nevi. Ten participants evaluated 78 dermoscopic images, comprised of 39 melanomas and 39 nevi, first without IBCs and then with IBCs. Participants classified each image as melanoma or nevus in both experimental conditions, enabling direct comparative analysis through paired data. With IBCs, average sensitivity improved significantly from 73.69% to 81.57% (p = 0.0051), and the average specificity improved from 60.50% to 67.25% (p = 0.059) for the diagnosis of melanoma. The index of discriminability (d') increased significantly by 0.47 (p = 0.002). Therefore, the incorporation of IBCs can significantly improve physicians' sensitivity in melanoma diagnosis. While more research is needed to validate this approach across other healthcare providers, its use may positively impact melanoma screening practices.

Dermoscopy aids in melanoma detection; however, agreement on dermoscopic features, including those of high clinical relevance, remains poor. In this study, we attempted to evaluate agreement among experts on exemplar images not only for the presence of melanocytic-specific features but also for spatial localization. This was a cross-sectional, multicenter, observational study. Dermoscopy images exhibiting at least 1 of 31 melanocytic-specific features were submitted by 25 world experts as exemplars. Using a web-based platform that allows for image markup of specific contrast-defined regions (superpixels), 20 expert readers annotated 248 dermoscopic images in collections of 62 images. Each collection was reviewed by five independent readers. A total of 4,507 feature observations were performed. Good-to-excellent agreement was found for 14 of 31 features (45.2%), with eight achieving excellent agreement (Gwet's AC >0.75) and seven of them being melanoma-specific features. These features were peppering/granularity (0.91), shiny white streaks (0.89), typical pigment network (0.83), blotch irregular (0.82), negative network (0.81), irregular globules (0.78), dotted vessels (0.77), and blue-whitish veil (0.76). By utilizing an exemplar dataset, a good-to-excellent agreement was found for 14 features that have previously been shown useful in discriminating nevi from melanoma. All images are public (www.isic-archive.com) and can be used for education, scientific communication, and machine learning experiments.

Hair and scalp disorders are of significant interest for physicians dealing with dark phototypes due to their prevalence and potential aesthetic impact resulting from a higher tendency for scarring. In order to facilitate their non-invasive diagnosis, several dermoscopic studies have been published, yet data are sparse and no systematic analysis of the literature has been performed so far. This systematic literature review summarizes published data on trichoscopy of hair and scalp diseases (trichoscopic findings, used setting, pathological correlation, and level of evidence of studies). A total of 60 papers addressing 19 different disorders (eight non-cicatricial alopecias, nine cicatricial alopecias, and two hair shaft disorders) were assessed, for a total of 2636 instances. They included one cross-sectional analysis, 20 case-control studies, 25 case-series, and 14 single case-reports, so the level of evidence was V and IV in 65% and 33% of cases, respectively, with only one study showing a level of evidence of III. Notably, although there is a considerable body of literature on trichoscopy of hair/scalp diseases, our review underlined that potentially significant variables (e.g., disease stage or hair texture) are often not taken into account in published analyses, with possible biases on trichoscopic patterns, especially when it comes to hair shaft changes. Further analyses considering all such issues are therefore needed.

Dermoscopy has been showed to facilitate the non-invasive recognition of several infectious disorders (infectiouscopy) thanks to the detection of peculiar clues. Although most of the knowledge on this topic comes from studies involving light-skinned patients, there is growing evidence about its use also in dark phototypes. This systematic literature review summarizes published data on dermoscopy of parasitic, bacterial, viral and fungal dermatoses (dermoscopic findings, used setting, pathological correlation, and level of evidence of studies) and provides a homogeneous terminology of reported dermoscopic features according to a standardized methodology. A total of 66 papers addressing 41 different dermatoses (14 bacterial, 5 viral, 11 fungal infections, and 11 parasitoses/bites and stings) and involving a total of 1096 instances were included in the analysis. The majority of them displayed a level of evidence of V (44 single case reports and 21 case series), with only 1 study showing a level of evidence of IV (case-control analysis). Moreover, our analysis also highlighted a high variability in the terminology used in the retrieved studies. Thus, although promising, further studies designed according to a systematic and standardized approach are needed for better characterization of dermoscopy of infectious skin infections.

Dermoscopic patterns of inflammatory dermatoses (inflammoscopy) have been extensively studied in the recent years, though data on patients with darker phototypes (IV-VI) are sparse. The aims of this systematic review were to summarize the current state of knowledge on inflammoscopy applied to skin of color and provide a standardized nomenclature of reported findings. Besides dermoscopic features, type of setting and magnification, number of cases, and histopathological correlation were analyzed. Eighty-five papers addressing 78 different dermatoses (25 papulosquamous dermatoses, 19 hyperpigmented dermatoses, eight hypopigmented dermatoses, four granulomatous dermatoses, two sclerotic dermatoses, five facial inflammatory dermatoses, and 15 miscellaneous conditions) for a total of 2073 instances were retrieved. Only one study showed a level of evidence of III (cross-sectional study), whereas 10 and 74 displayed a level of evidence of IV (case-control studies) and V (case-series and case-reports), respectively. Moreover, our analysis also highlighted that most of papers focalized on a limited number of dermatoses, with several conditions having only single dermoscopic descriptions. Additionally, few studies compared findings among phototypes belonging to the "skin of color" spectrum. Further studies designed according to a systematic approach and considering the above-mentioned issues are therefore needed.