Search

Abstract AI image classification algorithms have shown promising results when applied to skin cancer detection. Most public skin cancer image datasets are comprised of dermoscopic photos and are limited by selection bias, lack of standardization, and lend themselves to development of algorithms that can only be used by skilled clinicians. The SLICE-3D (“Skin Lesion Image Crops Extracted from 3D TBP”) dataset described here addresses those concerns and contains images of over 400,000 distinct skin lesions from seven dermatologic centers from around the world. De-identified images were systematically extracted from sensitive 3D Total Body Photographs and are comparable in optical resolution to smartphone images. Algorithms trained on lower quality images could improve clinical workflows and detect skin cancers earlier if deployed in primary care or non-clinical settings, where photos are captured by non-expert physicians or patients. Such a tool could prompt individuals to visit a specialized dermatologist. This dataset circumvents many inherent limitations of prior datasets and may be used to build upon previous applications of skin imaging for cancer detection.

Abstract Increasing evidence supports reduced accuracy of noninvasive assessment tools, such as pulse oximetry, temperature probes, and AI skin diagnosis benchmarks, in patients with darker skin tones. The FDA is exploring potential strategies for device regulation to improve performance across diverse skin tones by including skin tone criteria. However, there is no consensus about how prospective studies should perform skin tone assessment in order to take this bias into account. There are several tools available to conduct skin tone assessments including administered visual scales (e.g., Fitzpatrick Skin Type, Pantone, Monk Skin Tone) and color measurement tools (e.g., reflectance colorimeters, reflectance spectrophotometers, cameras), although none are consistently used or validated across multiple medical domains. Accurate and consistent skin tone measurement depends on many factors including standardized environments, lighting, body parts assessed, patient conditions, and choice of skin tone assessment tool(s). As race and ethnicity are inadequate proxies for skin tone, these considerations can be helpful in standardizing the effect of skin tone on studies such as AI dermatology diagnoses, pulse oximetry, and temporal thermometers. Skin tone bias in medical devices is likely due to systemic factors that lead to inadequate validation across diverse skin tones. There is an opportunity for researchers to use skin tone assessment methods with standardized considerations in prospective studies of noninvasive tools that may be affected by skin tone. We propose considerations that researchers must take in order to improve device robustness to skin tone bias.

Abstract Advancements in dermatological artificial intelligence research require high-quality and comprehensive datasets that mirror real-world clinical scenarios. We introduce a collection of 18,946 dermoscopic images spanning from 2010 to 2016, collated at the Hospital Clínic in Barcelona, Spain. The BCN20000 dataset aims to address the problem of unconstrained classification of dermoscopic images of skin cancer, including lesions in hard-to-diagnose locations such as those found in nails and mucosa, large lesions which do not fit in the aperture of the dermoscopy device, and hypo-pigmented lesions. Our dataset covers eight key diagnostic categories in dermoscopy, providing a diverse range of lesions for artificial intelligence model training. Furthermore, a ninth out-of-distribution (OOD) class is also present on the test set, comprised of lesions which could not be distinctively classified as any of the others. By providing a comprehensive collection of varied images, BCN20000 helps bridge the gap between the training data for machine learning models and the day-to-day practice of medical practitioners. Additionally, we present a set of baseline classifiers based on state-of-the-art neural networks, which can be extended by other researchers for further experimentation.

OBJECTIVE:. Pulse oximetry, a ubiquitous vital sign in modern medicine, has inequitable accuracy that disproportionately affects minority Black and Hispanic patients, with associated increases in mortality, organ dysfunction, and oxygen therapy. Previous retrospective studies used self-reported race or ethnicity as a surrogate for skin tone which is believed to be the root cause of the disparity. Our objective was to determine the utility of skin tone in explaining pulse oximetry discrepancies. DESIGN:. Prospective cohort study. SETTING:. Patients were eligible if they had pulse oximetry recorded up to 5 minutes before arterial blood gas (ABG) measurements. Skin tone was measured using administered visual scales, reflectance colorimetry, and reflectance spectrophotometry. PARTICIPANTS:. Admitted hospital patients at Duke University Hospital. INTERVENTIONS:. None. MEASUREMENTS AND MAIN RESULTS:. Sao2–Spo2 bias, variation of bias, and accuracy root mean square, comparing pulse oximetry, and ABG measurements. Linear mixed-effects models were fitted to estimate Sao2–Spo2 bias while accounting for clinical confounders. One hundred twenty-eight patients (57 Black, 56 White) with 521 ABG-pulse oximetry pairs were recruited. Skin tone data were prospectively collected using six measurement methods, generating eight measurements. The collected skin tone measurements were shown to yield differences among each other and overlap with self-reported racial groups, suggesting that skin tone could potentially provide information beyond self-reported race. Among the eight skin tone measurements in this study, and compared with self-reported race, the Monk Scale had the best relationship with differences in pulse oximetry bias (point estimate: –2.40%; 95% CI, –4.32% to –0.48%; p = 0.01) when comparing patients with lighter and dark skin tones. CONCLUSIONS:. We found clinical performance differences in pulse oximetry, especially in darker skin tones. Additional studies are needed to determine the relative contributions of skin tone measures and other potential factors on pulse oximetry discrepancies.

Abstract Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and meta-analysis to evaluate the performance of AI algorithms for skin cancer classification in comparison to clinicians with different levels of expertise. Based on PRISMA guidelines, 3 electronic databases (PubMed, Embase, and Cochrane Library) were screened for relevant articles up to August 2022. The quality of the studies was assessed using QUADAS-2. A meta-analysis of sensitivity and specificity was performed for the accuracy of AI and clinicians. Fifty-three studies were included in the systematic review, and 19 met the inclusion criteria for the meta-analysis. Considering all studies and all subgroups of clinicians, we found a sensitivity (Sn) and specificity (Sp) of 87.0% and 77.1% for AI algorithms, respectively, and a Sn of 79.78% and Sp of 73.6% for all clinicians (overall); differences were statistically significant for both Sn and Sp. The difference between AI performance (Sn 92.5%, Sp 66.5%) vs. generalists (Sn 64.6%, Sp 72.8%), was greater, when compared with expert clinicians. Performance between AI algorithms (Sn 86.3%, Sp 78.4%) vs expert dermatologists (Sn 84.2%, Sp 74.4%) was clinically comparable. Limitations of AI algorithms in clinical practice should be considered, and future studies should focus on real-world settings, and towards AI-assistance.

Abstract Large language models (LLMs) are being integrated into healthcare systems; but these models may recapitulate harmful, race-based medicine. The objective of this study is to assess whether four commercially available large language models (LLMs) propagate harmful, inaccurate, race-based content when responding to eight different scenarios that check for race-based medicine or widespread misconceptions around race. Questions were derived from discussions among four physician experts and prior work on race-based medical misconceptions believed by medical trainees. We assessed four large language models with nine different questions that were interrogated five times each with a total of 45 responses per model. All models had examples of perpetuating race-based medicine in their responses. Models were not always consistent in their responses when asked the same question repeatedly. LLMs are being proposed for use in the healthcare setting, with some models already connecting to electronic health record systems. However, this study shows that based on our findings, these LLMs could potentially cause harm by perpetuating debunked, racist ideas.

Abstract Images depicting dark skin tones are significantly underrepresented in the educational materials used to teach primary care physicians and dermatologists to recognize skin diseases. This could contribute to disparities in skin disease diagnosis across different racial groups. Previously, domain experts have manually assessed textbooks to estimate the diversity in skin images. Manual assessment does not scale to many educational materials and introduces human errors. To automate this process, we present the Skin Tone Analysis for Representation in EDucational materials (STAR-ED) framework, which assesses skin tone representation in medical education materials using machine learning. Given a document (e.g., a textbook in .pdf), STAR-ED applies content parsing to extract text, images, and table entities in a structured format. Next, it identifies images containing skin, segments the skin-containing portions of those images, and estimates the skin tone using machine learning. STAR-ED was developed using the Fitzpatrick17k dataset. We then externally tested STAR-ED on four commonly used medical textbooks. Results show strong performance in detecting skin images (0.96 ± 0.02 AUROC and 0.90 ± 0.06 F1 score) and classifying skin tones (0.87 ± 0.01 AUROC and 0.91 ± 0.00 F1 score). STAR-ED quantifies the imbalanced representation of skin tones in four medical textbooks: brown and black skin tones (Fitzpatrick V-VI) images constitute only 10.5% of all skin images. We envision this technology as a tool for medical educators, publishers, and practitioners to assess skin tone diversity in their educational materials.

Abstract Background Cutaneous metastases in pancreatic cancer (PC) are rare. Herein, we evaluate the clinical, genomic, and other descriptors of patients with PC and cutaneous metastases. Methods Institutional databases were queried, and clinical history, demographics, PC cutaneous metastasis details, and overall survival (OS) from cutaneous metastasis diagnosis were abstracted. OS was estimated using Kaplan–Meier methods. Results Forty patients were identified, and median age (Q1–Q3, IQR) of PC diagnosis was 66.0 (59.3–72.3, 12.9) years. Most patients had Stage IV disease at diagnosis (n = 26, 65%). The most common location of the primary tumor was the tail of the pancreas (n = 17, 43%). The most common cutaneous metastasis site was the abdomen (n = 31, 78%), with umbilical lesions occurring in 74% (n = 23) of abdominal lesions. The median OS (95% CI) was 11.4 months (7.0, 20.4). Twenty‐three patients had umbilical metastases (58%), and 17 patients had non‐umbilical metastases (43%). The median OS (95% CI) was 13.7 (7.0, 28.7) months in patients with umbilical metastases and 8.9 (4.1, Not reached) months in patients with non‐umbilical metastases (p = 0.1). Sixteen of 40 (40%) patients underwent somatic testing, and findings were consistent with known profiles. Germline testing in 12 (30%) patients identified pathogenic variants in patients: CHEK2, BRCA1, and ATM. Conclusion Cutaneous metastases from PC most frequently arise from a pancreas tail primary site and most frequently occur in the umbilicus. Cutaneous metastases may generally be categorized as umbilical or non‐umbilical metastases.

Abstract Alopecia is one of the most common reasons for a dermatology visit among Black patients. Patients with concomitant afro‐textured hair and scarring alopecias are often subjected to delays in diagnosis and treatment. Race‐discordant physicians may find the examination of scarring alopecias in ethnic hair to be daunting. Herein we present a standardized approach to evaluating the hair and scalp in afro‐textured alopecia patients in the hopes of providing a framework and guide for the proper clinical assessment of these patients. This guide focuses on common scarring alopecias specific to this ethnic population including traction alopecia, central centrifugal alopecia, frontal fibrosing alopecia and lichen planopilaris.

BackgroundDermoscopy is commonly used for the evaluation of pigmented lesions, but agreement between experts for identification of dermoscopic structures is known to be relatively poor. Expert labeling of medical data is a bottleneck in the development of machine learning (ML) tools, and crowdsourcing has been demonstrated as a cost- and time-efficient method for the annotation of medical images. ObjectiveThe aim of this study is to demonstrate that crowdsourcing can be used to label basic dermoscopic structures from images of pigmented lesions with similar reliability to a group of experts. MethodsFirst, we obtained labels of 248 images of melanocytic lesions with 31 dermoscopic “subfeatures” labeled by 20 dermoscopy experts. These were then collapsed into 6 dermoscopic “superfeatures” based on structural similarity, due to low interrater reliability (IRR): dots, globules, lines, network structures, regression structures, and vessels. These images were then used as the gold standard for the crowd study. The commercial platform DiagnosUs was used to obtain annotations from a nonexpert crowd for the presence or absence of the 6 superfeatures in each of the 248 images. We replicated this methodology with a group of 7 dermatologists to allow direct comparison with the nonexpert crowd. The Cohen κ value was used to measure agreement across raters. ResultsIn total, we obtained 139,731 ratings of the 6 dermoscopic superfeatures from the crowd. There was relatively lower agreement for the identification of dots and globules (the median κ values were 0.526 and 0.395, respectively), whereas network structures and vessels showed the highest agreement (the median κ values were 0.581 and 0.798, respectively). This pattern was also seen among the expert raters, who had median κ values of 0.483 and 0.517 for dots and globules, respectively, and 0.758 and 0.790 for network structures and vessels. The median κ values between nonexperts and thresholded average–expert readers were 0.709 for dots, 0.719 for globules, 0.714 for lines, 0.838 for network structures, 0.818 for regression structures, and 0.728 for vessels. ConclusionsThis study confirmed that IRR for different dermoscopic features varied among a group of experts; a similar pattern was observed in a nonexpert crowd. There was good or excellent agreement for each of the 6 superfeatures between the crowd and the experts, highlighting the similar reliability of the crowd for labeling dermoscopic images. This confirms the feasibility and dependability of using crowdsourcing as a scalable solution to annotate large sets of dermoscopic images, with several potential clinical and educational applications, including the development of novel, explainable ML tools.

Abstract Conventional tissue sampling can lead to misdiagnoses and repeated biopsies. Additionally, tissue processed for histopathology suffers from poor nucleic acid quality and/or quantity for downstream molecular profiling. Targeted micro-sampling of tissue can ensure accurate diagnosis and molecular profiling in the presence of spatial heterogeneity, especially in tumors, and facilitate acquisition of fresh tissue for molecular analysis. In this study, we explored the feasibility of performing 1–2 mm precision biopsies guided by high-resolution reflectance confocal microscopy (RCM) and optical coherence tomography (OCT), and reflective metallic grids for accurate spatial targeting. Accurate sampling was confirmed with either histopathology or molecular profiling through next generation sequencing (NGS) in 9 skin cancers in 7 patients. Imaging-guided 1–2 mm biopsies enabled spatial targeting for in vivo diagnosis, feature correlation and depth assessment, which were confirmed with histopathology. In vivo 1-mm targeted biopsies achieved adequate quantity and high quality of DNA for next-generation sequencing. Subsequent mutational profiling was confirmed on 1 melanoma in situ and 2 invasive melanomas, using a 505-gene mutational panel called Memorial Sloan Kettering-Integrated mutational profiling of actionable cancer targets (MSK-IMPACT). Differential mutational landscapes, in terms of number and types of mutations, were found between invasive and in situ melanomas in a single patient. Our findings demonstrate feasibility of accurate sampling of regions of interest for downstream histopathological diagnoses and molecular pathology in both in vivo and ex vivo settings with broad diagnostic, therapeutic and research potential in cutaneous diseases accessible by RCM-OCT imaging.

Tertiary lymphoid structures (TLS) are specialized lymphoid formations that serve as local repertoire of T- and B-cells at sites of chronic inflammation, autoimmunity, and cancer. While presence of TLS has been associated with improved response to immune checkpoint blockade therapies and overall outcomes in several cancers, its prognostic value in basal cell carcinoma (BCC) has not been investigated. Herein, we determined the prognostic impact of TLS by relating its prevalence and maturation with outcome measures of anti-tumor immunity, namely tumor infiltrating lymphocytes (TILs) and tumor killing. In 30 distinct BCCs, we show the presence of TLS was significantly enriched in tumors harboring a nodular component and more mature primary TLS was associated with TIL counts. Moreover, assessment of the fibrillary matrix surrounding tumors showed discrete morphologies significantly associated with higher TIL counts, critically accounting for heterogeneity in TIL count distribution within TLS maturation stages. Specifically, increased length of fibers and lacunarity of the matrix with concomitant reduction in density and alignment of fibers were present surrounding tumors displaying high TIL counts. Given the interest in inducing TLS formation as a therapeutic intervention as well as its documented prognostic value, elucidating potential impediments to the ability of TLS in driving anti-tumor immunity within the tumor microenvironment warrants further investigation. These results begin to address and highlight the need to integrate stromal features which may present a hindrance to TLS formation and/or effective function as a mediator of immunotherapy response.

Measurement(s) melanoma • Skin Lesion Technology Type(s) Dermoscopy • digital curation Factor Type(s) approximate age • sex • anatomic site Sample Characteristic - Organism Homo sapiens Machine-accessible metadata file describing the reported data: https://doi.org/10.6084/m9.figshare.13070345

Background: Minimal knowledge exists regarding skin cancers in Black individuals, which may adversely affect patient care. Objectives: To describe clinical features and risk factors of skin cancers in Black individuals. Methods: Retrospective study of Black individuals diagnosed with skin cancer between January 2000 and January 2020 at our institution. Results: 38,589 patients were diagnosed with skin cancer, of which 165 were Black. One-hundred-thirteen of these Black individuals were diagnosed with melanoma, 35 with squamous cell carcinoma (SCC), and 17 with basal cell carcinoma (BCC). Most melanomas (80.0%, n=90) were of the acral subtype; 75% (6 of 8 cases with dermoscopic images) displayed a parallel ridge pattern (PRP). The surrounding uninvolved background skin was visible in 7 cases, all demonstrating a PRP. This disappeared adjacent to most of the melanoma lesions (n=4, 57.1%) – creating a peripheral hypopigmented “halo”. The nonmelanoma skin cancers were pigmented and had similar dermoscopic features as reported in predominantly white populations. Most SCCs (n=5, 71.4%) had a hypopigmented “halo” and most BCCs (n=10, 55.6%) had an accentuated reticular network adjacent to the lesions. Most (80.0%, n=28) SCC patients had a chronic inflammatory condition. Two BCC patients (16.7%) had Gorlin syndrome. Conclusions: Skin cancers are pigmented in Black individuals. In both ALMs and SCCs, we noted a peripheral rim of hypopigmentation between the lesions and the surrounding uninvolved background skin, while BCCs had accentuation of the background pigmentation adjacent to the lesions. Most acral melanomas displayed a PRP, which was also seen in surrounding uninvolved background skin.

There is optimism that artificial intelligence (AI) will result in positive clinical outcomes, which is driving research and investment in the use of AI for skin disease. At present, AI for skin disease is embedded in research and development and not practiced widely in clinical dermatology. Clinical dermatology is also undergoing a technological transformation in terms of the development and adoption of standards that optimizes the quality use of imaging. Digital Imaging and Communications in Medicine (DICOM) is the international standard for medical imaging. DICOM is a continually evolving standard. There is considerable effort being invested in developing dermatology-specific extensions to the DICOM standard. The ability to encode relevant metadata and afford interoperability with the digital health ecosystem (e.g., image repositories, electronic medical records) has driven the initial impetus in the adoption of DICOM for dermatology. DICOM has a dedicated working group whose role is to develop a mechanism to support AI workflows and encode AI artifacts. DICOM can improve AI workflows by encoding derived objects (e.g., secondary images, visual explainability maps, AI algorithm output) and the efficient curation of multi-institutional datasets for machine learning training, testing, and validation. This can be achieved using DICOM mechanisms such as standardized image formats and metadata, metadata-based image retrieval, and de-identification protocols. DICOM can address several important technological and workflow challenges for the implementation of AI. However, many other technological, ethical, regulatory, medicolegal, and workforce barriers will need to be addressed before DICOM and AI can be used effectively in dermatology.

A Correction to this paper has been published: https://doi.org/10.1038/s41597-021-00879-x.

A Correction to this paper has been published: https://doi.org/10.1038/s41597-021-00865-3.