The SLICE-3D dataset: 400,000 skin lesion image crops extracted from 3D TBP for skin cancer detection.

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.

Patient demographic characteristics and risk factors associated with sun protection behaviours in specialist melanoma clinics.

OBJECTIVE: We investigated the association between sun protection behaviours and demographic and melanoma risk characteristics of patients attending Australian melanoma specialist clinics. This may assist in targeting and tailoring melanoma prevention patient education for people at high-risk and specific population subgroups. METHODS: A cross-sectional analysis of questionnaire data collected from participants attending the dermatology clinics at two major melanoma centres in Sydney, Australia between February 2021 and September 2023. The primary outcome was Sun Protection Habits (SPH) index (a summary score measured as habitual past month use of sunscreen, hats, sunglasses, a shirt with sleeves that covers the shoulders, limiting midday sun exposure and seeking shade, using a Likert scale). The primary analysis considered the SPH index and its component items scored as continuous. RESULTS: Data from 883 people were analysed. Factors associated with less frequent sun protection behaviours overall included male gender, no personal history of melanoma, lower perceived risk, lower calculated 10-year risk of developing melanoma, and no private health insurance. People aged >61 years reported lower use of sunscreen but higher use of hats and sleeved-shirts compared with people in the younger age group. There was no difference in overall sun protection behaviours according to family history of melanoma, country of birth or by lifetime melanoma risk among people without a personal history of melanoma. CONCLUSIONS: These findings highlight the potential for targeting high-risk individuals with less frequent use of sun protection for patient education, public health messaging and ultimately improving sun protection behaviours.

Examining labelling guidelines for AI-based software as a medical device: A review and analysis of dermatology mobile applications in Australia.

In recent years, there has been a surge in the development of AI-based Software as a Medical Device (SaMD), particularly in visual specialties such as dermatology. In Australia, the Therapeutic Goods Administration (TGA) regulates AI-based SaMD to ensure its safe use. Proper labelling of these devices is crucial to ensure that healthcare professionals and the general public understand how to use them and interpret results accurately. However, guidelines for labelling AI-based SaMD in dermatology are lacking, which may result in products failing to provide essential information about algorithm development and performance metrics. This review examines existing labelling guidelines for AI-based SaMD across visual medical specialties, with a specific focus on dermatology. Common recommendations for labelling are identified and applied to currently available dermatology AI-based SaMD mobile applications to determine usage of these labels. Of the 21 AI-based SaMD mobile applications identified, none fully comply with common labelling recommendations. Results highlight the need for standardized labelling guidelines. Ensuring transparency and accessibility of information is essential for the safe integration of AI into health care and preventing potential risks associated with inaccurate clinical decisions.

Skin Cancer Referrals by Non-Medical Practitioners: A Prospective Observational Study.

The aim of this study was to investigate the appropriateness of suspected skin cancer referrals made by non-medical practitioners (NMPs) and compare this to referrals made by local General Practitioners (GPs). Data were collected prospectively from patients referred to a UK hospital dermatology department from primary care. The profession of the referrer was ascertained from review of referral letters and direct questioning. Patient records and subsequent histology reports were reviewed to determine ultimate diagnosis. 668/753 patients (88.7%) were referred by GPs versus 85/753 (11.3%) by NMPs. 340/668 (50.1%) of patients in the GP group and 47/85 (55.3%) in the NMP group were discharged without intervention (p = 0.45). An ultimate diagnosis of skin malignancy was made in 196/668 (29.3%) patients in the GP and 25/85 (29.4%)) in the NMP group (p = 0.99). These early data suggest significant potential for NMPs to become more involved in skin lesion assessment.

Minimum labelling requirements for dermatology artificial intelligence-based Software as Medical Device (SaMD): A consensus statement.

BACKGROUND/OBJECTIVES: Artificial intelligence (AI) holds remarkable potential to improve care delivery in dermatology. End users (health professionals and general public) of AI-based Software as Medical Devices (SaMD) require relevant labelling information to ensure that these devices can be used appropriately. Currently, there are no clear minimum labelling requirements for dermatology AI-based SaMDs. METHODS: Common labelling recommendations for AI-based SaMD identified in a recent literature review were evaluated by an Australian expert panel in digital health and dermatology via a modified Delphi consensus process. A nine-point Likert scale was used to indicate importance of 10 items, and voting was conducted to determine the specific characteristics to include for some items. Consensus was achieved when more than 75% of the experts agreed that inclusion of information was necessary. RESULTS: There was robust consensus supporting inclusion of all proposed items as minimum labelling requirements; indication for use, intended user, training and test data sets, algorithm design, image processing techniques, clinical validation, performance metrics, limitations, updates and adverse events. Nearly all suggested characteristics of the labelling items received endorsement, except for some characteristics related to performance metrics. Moreover, there was consensus that uniform labelling criteria should apply across all AI categories and risk classes set out by the Therapeutic Goods Administration. CONCLUSIONS: This study provides critical evidence for setting labelling standards by the Therapeutic Goods Administration to safeguard patients, health professionals, consumers, industry, and regulatory bodies from AI-based dermatology SaMDs that do not currently provide adequate information about how they were developed and tested.

Position statement of the EADV Artificial Intelligence (AI) Task Force on AI-assisted smartphone apps and web-based services for skin disease.

BACKGROUND: As the use of smartphones continues to surge globally, mobile applications (apps) have become a powerful tool for healthcare engagement. Prominent among these are dermatology apps powered by Artificial Intelligence (AI), which provide immediate diagnostic guidance and educational resources for skin diseases, including skin cancer. OBJECTIVE: This article, authored by the EADV AI Task Force, seeks to offer insights and recommendations for the present and future deployment of AI-assisted smartphone applications (apps) and web-based services for skin diseases with emphasis on skin cancer detection. METHODS: An initial position statement was drafted on a comprehensive literature review, which was subsequently refined through two rounds of digital discussions and meticulous feedback by the EADV AI Task Force, ensuring its accuracy, clarity and relevance. RESULTS: Eight key considerations were identified, including risks associated with inaccuracy and improper user education, a decline in professional skills, the influence of non-medical commercial interests, data security, direct and indirect costs, regulatory approval and the necessity of multidisciplinary implementation. Following these considerations, three main recommendations were formulated: (1) to ensure user trust, app developers should prioritize transparency in data quality, accuracy, intended use, privacy and costs; (2) Apps and web-based services should ensure a uniform user experience for diverse groups of patients; (3) European authorities should adopt a rigorous and consistent regulatory framework for dermatology apps to ensure their safety and accuracy for users. CONCLUSIONS: The utilisation of AI-assisted smartphone apps and web-based services in diagnosing and treating skin diseases has the potential to greatly benefit patients in their dermatology journeys. By prioritising innovation, fostering collaboration and implementing effective regulations, we can ensure the successful integration of these apps into clinical practice.

International expert recommendations on image acquisition for in vivo reflectance confocal microscopy of cutaneous tumors.

BACKGROUND: No international recommendations exist for a minimum imaging requirement per lesion using reflectance confocal microscopy (RCM). This may be beneficial given the increasing use of remote RCM interpretation internationally. OBJECTIVE: To develop international expert recommendations for image acquisition using tissue-coupled RCM for diagnosis of cutaneous tumors. METHODS: Using a modified Delphi approach, a core group developed the scope and drafted initial recommendations before circulation to a larger group, the Cutaneous Imaging Expert Resource Group of the American Academy of Dermatology. Each review round consisted of a period of open comment, followed by revisions. RESULTS: The recommendations were developed after 5 alternating rounds of review among the core group and the Cutaneous Imaging Expert Resource Group. These were divided into subsections of imaging personnel, recommended lesion criteria, clinical and lesion information to be provided, lesion preparation, image acquisition, mosaic cube settings, and additional captures based on lesion characteristics and suspected diagnosis. LIMITATIONS: The current recommendations are limited to tissue-coupled RCM for diagnosis of cutaneous tumors. It is one component of the larger picture of quality assurance and will require ongoing review. CONCLUSIONS: These recommendations serve as a resource to facilitate quality assurance, economical use of time, accurate diagnosis, and international collaboration.

Dermoscopy of Lentiginous Melanomas and Equivocal Benign Pigmented Macules of the Scalp: A Case-Control Multicentric Study.

INTRODUCTION: Although the dermoscopic features of facial lentiginous melanomas (LM), including lentigo maligna and lentigo maligna melanoma, have been extensively studied, the literature about those located on the scalp is scarce. This study aims to describe the dermoscopic features of scalp LM and assess the diagnostic accuracy of dermoscopy to discriminate them from equivocal benign pigmented macules. METHODS: Consecutive cases of scalp LM and histopathology-proven benign but clinically equivocal pigmented macules (actinic keratoses, solar lentigos, seborrhoeic keratoses, and lichen planus-like keratoses) from four referral centres were included. Dermoscopic features were analysed by two blinded experts. The diagnostic performance of a predictive model was assessed. RESULTS: 56 LM and 44 controls were included. Multiple features previously described for facial and extrafacial LM were frequently identified in both groups. Expert's sensitivity to diagnose scalp LM was 76.8% (63.6-87.0) and 78.6% (65.6-88.4), with specificity of 54.5% (38.9-69.6) and 56.8% (41.0-71.7), and fair agreement (kappa coefficient 0.248). The strongest independent predictors of malignancy were (OR, 95% CI) chaos of colour (15.43, 1.48-160.3), pigmented reticular lines (14.96, 1.68-132.9), increased density of vascular network (3.45, 1.09-10.92), and perifollicular grey circles (2.89, 0.96-8.67). The predictive model achieved 85.7% (73.8-93.6) sensitivity, 61.4% (45.5-75.6) specificity, and 81.5 (73.0-90.0) area under curve to discriminate benign and malignant lesions. A diagnostic flowchart was proposed, which should improve the diagnostic performance of dermoscopy. CONCLUSION: Both facial and extrafacial dermoscopic patterns can be identified in scalp LM, with considerable overlap with benign pigmented macules, leading to low specificity and interobserver agreement on dermoscopy.

Lentigo maligna and lentigo maligna melanoma in patients younger than 50†years: a multicentre international clinical-dermoscopic study.

BACKGROUND: Lentigo maligna/lentigo maligna melanoma (LM/LMM) is usually diagnosed in older patients, when lesions are larger. However, it is important to detect it at an earlier stage to minimize the area for surgical procedure. OBJECTIVES: To determine and define clinical, dermoscopic and reflectance confocal microscopy (RCM) features of LM/LMM in patients < 50 years old. METHODS: This was a multicentre study involving tertiary referral centres for skin cancer management. The study included cases of consecutively excised LM/LMM arising in patients < 50 years of age with a histopathological diagnosis of LM/LMM and a complete set of clinical and dermoscopic images; RCM images were considered when present. RESULTS: In total, 85 LM/LMM of the face from 85 patients < 50 years were included in the study. A regression model showed a direct association with the size of the lesion (R2 = 0.08; P = 0.01) and with the number of dermoscopic features at diagnosis (R2 = 0.12; P < 0.01). In a multivariable analysis, an increasing number of dermoscopic features correlated with increased patient age (P < 0.01), while the presence of grey colour was a predictor of younger age at diagnosis (P = 0.03). RCM revealed the presence of melanoma diagnostic features in all cases (pagetoid cells and atypical nesting). CONCLUSIONS: LM is not a disease limited to older people as previously thought. LM presenting in young adults tends to be smaller and with fewer dermoscopic features, making its diagnosis challenging. Careful evaluation of facial pigmented lesions prior to cosmetic procedures is imperative to avoid incorrectly treating early LM as a benign lesion.

Full-body skin examination in screening for cutaneous malignancy: a focus on concealed sites and the practices of Australian dermatologists.

BACKGROUND: Full-body skin examination (FSE) is a vital practice in the diagnosis of cutaneous malignancy. Precisely how FSE should be conducted with respect to concealed site inclusion remains poorly elucidated. OBJECTIVE: To establish the approach of Australian dermatologists to concealed site examination (CSE). METHODS: A cross-sectional study was performed consisting of an online self-administered 11-question survey delivered to fellows of the Australasian College of Dermatologists. RESULTS: There were 237 respondents. Anogenitalia was the least often examined concealed site (4.6%), and 59.9, 32.9, and 14.3% reported always examining the scalp, breasts, and oral mucosa, respectively. Patient concern was the most frequently cited factor prompting examination, while many cited low incidence of pathology and limited chaperone availability as the main barriers to routine examination of these sites. CONCLUSION: Most Australian dermatologists do not routinely examine breasts, oral mucosal, or anogenital sites as part of an FSE. Emphasis should be made on identifying individual patient risk factors and education regarding self-examination of sensitive sites. A consensus approach to the conduct of the FSE, including concealed sites, is needed to better delineate clinician responsibilities and address medicolegal implications.

Comparison of humans versus mobile phone-powered artificial intelligence for the diagnosis and management of pigmented skin cancer in secondary care: a multicentre, prospective, diagnostic, clinical trial.

BACKGROUND: Diagnosis of skin cancer requires medical expertise, which is scarce. Mobile phone-powered artificial intelligence (AI) could aid diagnosis, but it is unclear how this technology performs in a clinical scenario. Our primary aim was to test in the clinic whether there was equivalence between AI algorithms and clinicians for the diagnosis and management of pigmented skin lesions. METHODS: In this multicentre, prospective, diagnostic, clinical trial, we included specialist and novice clinicians and patients from two tertiary referral centres in Australia and Austria. Specialists had a specialist medical qualification related to diagnosing and managing pigmented skin lesions, whereas novices were dermatology junior doctors or registrars in trainee positions who had experience in examining and managing these lesions. Eligible patients were aged 18-99 years and had a modified Fitzpatrick I-III skin type; those in the diagnostic trial were undergoing routine excision or biopsy of one or more suspicious pigmented skin lesions bigger than 3 mm in the longest diameter, and those in the management trial had baseline total-body photographs taken within 1-4 years. We used two mobile phone-powered AI instruments incorporating a simple optical attachment: a new 7-class AI algorithm and the International Skin Imaging Collaboration (ISIC) AI algorithm, which was previously tested in a large online reader study. The reference standard for excised lesions in the diagnostic trial was histopathological examination; in the management trial, the reference standard was a descending hierarchy based on histopathological examination, comparison of baseline total-body photographs, digital monitoring, and telediagnosis. The main outcome of this study was to compare the accuracy of expert and novice diagnostic and management decisions with the two AI instruments. Possible decisions in the management trial were dismissal, biopsy, or 3-month monitoring. Decisions to monitor were considered equivalent to dismissal (scenario A) or biopsy of malignant lesions (scenario B). The trial was registered at the Australian New Zealand Clinical Trials Registry ACTRN12620000695909 (Universal trial number U1111-1251-8995). FINDINGS: The diagnostic study included 172 suspicious pigmented lesions (84 malignant) from 124 patients and the management study included 5696 pigmented lesions (18 malignant) from the whole body of 66 high-risk patients. The diagnoses of the 7-class AI algorithm were equivalent to the specialists' diagnoses (absolute accuracy difference 1·2% [95% CI -6·9 to 9·2]) and significantly superior to the novices' ones (21·5% [13·1 to 30·0]). The diagnoses of the ISIC AI algorithm were significantly inferior to the specialists' diagnoses (-11·6% [-20·3 to -3·0]) but significantly superior to the novices' ones (8·7% [-0·5 to 18·0]). The best 7-class management AI was significantly inferior to specialists' management (absolute accuracy difference in correct management decision -0·5% [95% CI -0·7 to -0·2] in scenario A and -0·4% [-0·8 to -0·05] in scenario B). Compared with the novices' management, the 7-class management AI was significantly inferior (-0·4% [-0·6 to -0·2]) in scenario A but significantly superior (0·4% [0·0 to 0·9]) in scenario B. INTERPRETATION: The mobile phone-powered AI technology is simple, practical, and accurate for the diagnosis of suspicious pigmented skin cancer in patients presenting to a specialist setting, although its usage for management decisions requires more careful execution. An AI algorithm that was superior in experimental studies was significantly inferior to specialists in a real-world scenario, suggesting that caution is needed when extrapolating results of experimental studies to clinical practice. FUNDING: MetaOptima Technology.

Delphi Consensus Among International Experts on the Diagnosis, Management, and Surveillance for Lentigo Maligna.

INTRODUCTION: Melanoma of the lentigo maligna (LM) type is challenging. There is lack of consensus on the optimal diagnosis, treatment, and follow-up. OBJECTIVES: To obtain general consensus on the diagnosis, treatment, and follow-up for LM. METHODS: A modified Delphi method was used. The invited participants were either members of the International Dermoscopy Society, academic experts, or authors of published articles relating to skin cancer and melanoma. Participants were required to respond across three rounds using a 4-point Likert scale). Consensus was defined as >75% of participants agreeing/strongly agreeing or disagreeing/strongly disagreeing. RESULTS: Of the 31 experts invited to participate in this Delphi study, 29 participants completed Round 1 (89.9% response rate), 25/31 completed Round 2 (77.5% response rate), and 25/31 completed Round 3 (77.5% response rate). Experts agreed that LM diagnosis should be based on a clinical and dermatoscopic approach (92%) followed by a biopsy. The most appropriate primary treatment of LM was deemed to be margin-controlled surgery (83.3%), although non-surgical modalities, especially imiquimod, were commonly used either as alternative off-label primary treatment in selected patients or as adjuvant therapy following surgery; 62% participants responded life-long clinical follow-up was needed for LM. CONCLUSIONS: Clinical and histological diagnosis of LM is challenging and should be based on macroscopic, dermatoscopic, and RCM examination followed by a biopsy. Different treatment modalities and follow-up should be carefully discussed with the patient.

Effect of Histopathological Explanations for Dermoscopic Criteria on Learning Curves in Skin Cancer Training: a Randomized Controlled Trial.

INTRODUCTION: Case-based training improves novices pattern recognition and diagnostic accuracy in skin cancer diagnostics. However, it is unclear how pattern recognition is best taught in conjunction with the knowledge needed to justify a diagnosis. OBJECTIVES: The aim of this study was to examine whether an explanation of the underlying histopathological reason for dermoscopic criteria improves skill acquisition and retention during case-based training in skin cancer diagnostics. METHODS: In this double-blinded randomized controlled trial, medical students underwent eight days of case-based training in skin cancer diagnostics, which included access to written diagnosis modules. The modules dermoscopic subsections differed between the study groups. All participants received a general description of the criteria, but the intervention group additionally received a histopathological explanation. RESULTS: Most participants (78%) passed a reliable test in skin cancer diagnostics, following a mean training time of 217 minutes. Access to histopathological explanations did not affect participants' learning curves or skill retention. CONCLUSIONS: The histopathological explanation did not affect the students, but the overall educational approach was efficient and scalable.

Skin cancer-related conditions managed in general practice in Australia, 2000-2016: a nationally representative, cross-sectional survey.

OBJECTIVE: Skin cancer is Australia's most common and costly cancer. We examined the frequency of Australian general practice consultations for skin cancer-related conditions, by patient and general practitioner (GP) characteristics and by time period. DESIGN: Nationally representative, cross-sectional survey of general practice clinical activity. SETTING, PARTICIPANTS: Patients aged 15 years or older having a skin cancer-related condition managed by GPs in the Bettering the Evaluation And Care of Health study between April 2000 and March 2016. PRIMARY OUTCOME MEASURES: Proportions and rates per 1000 encounters. RESULTS: In this period, 15 678 GPs recorded 1 370 826 patient encounters, of which skin cancer-related conditions were managed 65 411 times (rate of 47.72 per 1000 encounters, 95% CI 46.41 to 49.02). Across the whole period, 'skin conditions' managed were solar keratosis (29.87%), keratinocyte cancer (24.85%), other skin lesion (12.93%), nevi (10.98%), skin check (10.37%), benign skin neoplasm (8.76%) and melanoma (2.42%). Over time, management rates increased for keratinocyte cancers, skin checks, skin lesions, benign skin neoplasms and melanoma; but remained stable for solar keratoses and nevi. Skin cancer-related encounter rates were higher for patients aged 65-89 years, male, living in Queensland or in regional or remote areas, with lower area-based socioeconomic status, of English-speaking background, Veteran card holders and non-healthcare card holders; and for GPs who were aged 35-44 years or male. CONCLUSION: These findings show the spectrum and burden of skin cancer-related conditions managed in general practice in Australia, which can guide GP education, policy and interventions to optimise skin cancer prevention and management.

Computer-Aided Diagnosis of Melanoma Subtypes Using Reflectance Confocal Images.

Lentigo maligna (LM) is an early form of pre-invasive melanoma that predominantly affects sun-exposed areas such as the face. LM is highly treatable when identified early but has an ill-defined clinical border and a high rate of recurrence. Atypical intraepidermal melanocytic proliferation (AIMP), also known as atypical melanocytic hyperplasia (AMH), is a histological description that indicates melanocytic proliferation with uncertain malignant potential. Clinically and histologically, AIMP can be difficult to distinguish from LM, and indeed AIMP may, in some cases, progress to LM. The early diagnosis and distinction of LM from AIMP are important since LM requires a definitive treatment. Reflectance confocal microscopy (RCM) is an imaging technique often used to investigate these lesions non-invasively, without biopsy. However, RCM equipment is often not readily available, nor is the associated expertise for RCM image interpretation easy to find. Here, we implemented a machine learning classifier using popular convolutional neural network (CNN) architectures and demonstrated that it could correctly classify lesions between LM and AIMP on biopsy-confirmed RCM image stacks. We identified local z-projection (LZP) as a recent fast approach for projecting a 3D image into 2D while preserving information and achieved high-accuracy machine classification with minimal computational requirements.

Junctional Nevus and Early Melanoma on Sun-Damaged Skin of the Head/Neck: a Clinico-Pathologic Challenge.

INTRODUCTION: Melanoma on the head/neck area can show subtle clinical, dermoscopic and histologic features at early stages, being difficult to differentiate from junctional nevi. OBJECTIVES: This case series aims to raise awareness on the topic of misdiagnosis of early lentigo maligna as junctional nevi. METHODS: From the databases of three pigmented lesion clinics in Italy, Australia, and France, we retrieved all cases of lesions of the head/neck area with an initial histopathologic diagnosis of junctional nevus (JN) or dysplastic junctional nevus (DJN) which subsequently recurred and were ultimately diagnosed as melanoma. Moreover, we also retrieved those cases with an initial diagnosis of JN/DJN made on a partial biopsy that were diagnosed as melanoma after complete surgical removal. RESULTS: Here we report 14 cases in which the initial histologic diagnosis was junctional nevus or dysplastic junctional nevus. The lesions recurred over time with a final diagnosis of lentigo maligna. CONCLUSIONS: Clinicians should critically question a given histologic diagnosis of junctional or dysplastic junctional nevus on the head/neck area if the clinical or dermoscopic features are discordant. Clinico-pathologic correlation is the best way to increase diagnostic accuracy and optimize management for the patient.