Search

Background: The application of deep learning (DL) to diagnostic dermatology has been the subject of numerous studies, with some reporting skin lesion classification performance on curated datasets comparable to that of experienced dermatologists. Most skin disease images encountered in clinical settings are macroscopic, without dermoscopic information, and exhibit considerable variability. Further research is necessary to determine the generalizability of DL algorithms across populations and acquisition settings., Objectives: To assess the extent to which DL can generalize to nondermoscopic datasets acquired at the primary-secondary care interface in the National Health Service (NHS); to explore how to obtain a clinically satisfactory performance on nonstandardized, real-world local data without the availability of large diagnostically labelled local datasets; and to measure the impact of pretraining DL algorithms on external, public datasets., Methods: Diagnostic macroscopic image datasets were created from previous referrals from primary to secondary care. These included 2213 images referred from primary care practitioners in NHS Tayside and 1510 images from NHS Forth Valley acquired by medical photographers. Two further datasets with identical diagnostic labels were obtained from sources in the public domain, namely the International Skin Imaging Collaboration (ISIC) dermoscopic dataset and the SD-260 nondermoscopic dataset. DL algorithms, specifically EfficientNets and Self-attention with Window-wise Inner-product based Network (SWIN) transformers, were trained using data from each of these datasets. Algorithms were also fine-tuned on images from the NHS datasets after pretraining on different data combinations, including the larger public-domain datasets. Receiver operating characteristic curves and the area under such curves (AUC) were used to assess performance., Results: SWIN transformers tested on Forth Valley data had AUCs of 0.85 and 0.89 when trained on SD-260 and Forth Valley data, respectively. Training on SD-260 followed by fine tuning of Forth Valley data gave an AUC of 0.91. Similar effects of pretraining and tuning on local data were observed using Tayside data and EfficientNets. Pretraining on the larger dermoscopic image dataset (ISIC 2019) provided no additional benefit., Conclusions: Pretraining on public macroscopic images followed by tuning to local data gave promising results. Further improvements are needed to afford deployment in real clinical pathways. Larger datasets local to the target domain might be expected to yield further improved performance., Competing Interests: Conflict of interests The authors declare no conflicts of interest., (© The Author(s) 2023. Published by Oxford University Press on behalf of British Association of Dermatologists.)

Introduction: Solid organ transplant recipients (SOTRs) are believed to have an increased risk of metastatic cutaneous squamous cell carcinoma (cSCC), but reliable data are lacking regarding the precise incidence and associated risk factors., Methods: In a prospective cohort study, including 19 specialist dermatology outpatient clinics in 15 countries, patient and tumor characteristics were collected using standardized questionnaires when SOTRs presented with a new cSCC. After a minimum of 2 years of follow-up, relevant data for all SOTRs were collected. Cumulative incidence of metastases was calculated by the Aalen-Johansen estimator. Fine and Gray models were used to assess multiple risk factors for metastases., Results: Of 514 SOTRs who presented with 623 primary cSCCs, metastases developed in 37 with a 2-year patient-based cumulative incidence of 6.2%. Risk factors for metastases included location in the head and neck area, local recurrence, size > 2 cm, clinical ulceration, poor differentiation grade, perineural invasion, and deep invasion. A high-stage tumor that is also ulcerated showed the highest risk of metastasis, with a 2-year cumulative incidence of 46.2% (31.9%-68.4%)., Conclusions: SOTRs have a high risk of cSCC metastases and well-established clinical and histologic risk factors have been confirmed. High-stage, ulcerated cSCCs have the highest risk of metastasis., Competing Interests: Conflicts of interest This study was partly sponsored by the European Academy of Dermatology and Venerology (EADV), however this did not affect the content of the manuscript. The authors of this manuscript have no conflicts of interest to disclose as described by the American Journal of Transplantation., (Crown Copyright © 2024. Published by Elsevier Inc. All rights reserved.)

Background: Metastasis of cutaneous squamous cell carcinoma (cSCC) is uncommon. Current staging methods are reported to have sub-optimal performances in metastasis prediction. Accurate identification of patients with tumors at high risk of metastasis would have a significant impact on management., Objective: To develop a robust and validated gene expression profile signature for predicting primary cSCC metastatic risk using an unbiased whole transcriptome discovery-driven approach., Methods: Archival formalin-fixed paraffin-embedded primary cSCC with perilesional normal tissue from 237 immunocompetent patients (151 nonmetastasizing and 86 metastasizing) were collected retrospectively from four centers. TempO-seq was used to probe the whole transcriptome and machine learning algorithms were applied to derive predictive signatures, with a 3:1 split for training and testing datasets., Results: A 20-gene prognostic model was developed and validated, with an accuracy of 86.0%, sensitivity of 85.7%, specificity of 86.1%, and positive predictive value of 78.3% in the testing set, providing more stable, accurate prediction than pathological staging systems. A linear predictor was also developed, significantly correlating with metastatic risk., Limitations: This was a retrospective 4-center study and larger prospective multicenter studies are now required., Conclusion: The 20-gene signature prediction is accurate, with the potential to be incorporated into clinical workflows for cSCC., Competing Interests: Conflict of interest Dr Harwood is honoraria for advisory boards from Sanofi/Regeneron, Almirall, AmLo Biosciences, Incanthera, Leo Pharma, L'Oreal. Other authors have no disclosures., (Copyright © 2023 American Academy of Dermatology, Inc. Published by Elsevier Inc. All rights reserved.)

Background: Providing detailed skin cancer statistics, including incidence and survival, by tumour type and patient characteristics is important for up-to-date epidemiological information., Objectives: To create a new clinically relevant consensus-based classification for registered skin tumours using tumour type and patient characteristics and to describe its application to all registered tumours in England between 2013 and 2019., Methods: Tumours with skin topographical codes (ICD-10) and morphology and behaviour (ICD-O3) were grouped together in an iterative process creating a hierarchical tree structure. The primary-level grouping partitioned skin tumours into skin cancer, melanoma in situ, extramammary Paget disease (EMPD) and tumours of uncertain malignant potential. Second-level groups split skin cancer into keratinocyte cancer (KC), melanoma and rare cancers. The third-level group split KC into basal cell carcinoma (BCC) and squamous cell carcinoma (cSCC). Further groups were split into genital or non-genital, first or subsequent tumour, age, gender, stage, or National Health Service (NHS) region. Incidence counts, Kaplan-Meier and net survival estimates and referral routes [two-week wait (TWW), general practitioner (GP), outpatient] categorisations were calculated for each grouping across all years., Results: A total of 1 445 377 skin cancers and 49 123 precancerous lesions and undefined entities were registered in England between 2013 and 2019. Skin tumours and skin cancer incidence rates are increasing for most tumour types. The most common type of skin cancer was BCC with an incidence rate of 282.36 per 100 000 person-years (PYs) [n = 158 934, 95% confidence interval (CI) 280.98-283.76] in 2019, followed by cSCC with an incidence rate of 85.24 per 100 000 PYs (n = 47 977, 95% CI 84.48-86.00) and melanoma with 27.24 (n = 15 332, 95% CI 26.81-27.67) per 100 000 PYs. Each year approximately 1800 rare skin cancers, 1500 genital cSCCs and 100 cases of EMPD are registered. Of 15 000 melanoma cases, 120 cases of melanoma occur in individuals aged < 25 years annually. One-year and five-year overall net survival varies by tumour type. cSCC 5-year net survival (89.8%, 95% CI 88.8-90.9) was comparable to the net survival of all melanomas (89.6%, 95% CI 88.7-90.6). BCC had excellent survival (overall net survival > 100%). Patients with late-stage melanoma, Merkel cell carcinoma and genital cSCC have a 5-year net survival < 60%. Older patients received fewer TWW referrals than their younger counterparts with the same tumour type at the same location. Patients with acral lentiginous melanoma had fewer TWW referrals and more standard GP referrals than patients with common melanomas., Conclusions: 'Get Data Out' Skin provides detailed and up-to-date statistics on all registrable skin tumours in England, including for the first time precancerous lesions and rare subtypes of common cancers. These data can be used by clinicians, researchers and commissioners to better understand skin cancer and improve resource allocation., Competing Interests: Conflicts of interest B.v.B. is an employee of the British Association of Dermatologists. N.J.L. is a trustee of the British Association of Dermatologists. N.R. is a Deputy Editor at the BJD., (© The Author(s) 2023. Published by Oxford University Press on behalf of British Association of Dermatologists.)

Background: Melanoma is common with increasing incidence. Guidelines recommend monthly total skin self-examinations (TSSEs) by survivors to detect recurrent and new primary melanomas. TSSE is underperformed despite evidence of benefit., Objective: This study compares the effect on psychological well-being and TSSE practice of a self-directed digital intervention with treatment as usual in patients treated for a first stage 0 to IIC primary cutaneous melanoma within the preceding 60 months., Methods: This randomized clinical trial was conducted at 2 UK National Health Service hospitals (Aberdeen Royal Infirmary, Grampian, and Addenbrooke's, Cambridge). Adults (≥18 years) diagnosed with a first 0 to IIC primary cutaneous melanoma were randomized to receive Achieving Self-directed Integrated Cancer Aftercare (ASICA), a tablet-based intervention prompting and supporting TSSE in survivors of melanoma, or to usual care. The hypothesis was that ASICA would increase TSSE practice in users affected by melanoma and compared with controls without affecting psychological well-being. The main primary outcomes were melanoma worry (Melanoma Worry Scale), anxiety and depression (Hospital Anxiety and Depression Scale), and quality of life (EQ-5D-5L) as well as secondary outcomes collected using postal questionnaires 3, 6, and 12 months following randomization., Results: A total of 240 recruits were randomized (1:1) into the ASICA (n=121, 50.4%) or control (n=119, 49.6%) groups. There were no significant differences between groups for melanoma worry at 12 months (mean difference: 0.12, 95% CI -0.6 to 0.84; P=.74), 3 months (0.23, 95% CI -0.31 to 0.78; P=.40), or 6 months (-0.1, 95% CI -0.7 to 0.51; P=.76). The ASICA group had lower anxiety scores at 12 months (-0.54, 95% CI -1.31 to 0.230; P=.17), 3 months (-0.13, 95% CI -0.79 to 0.54; P=.71), and significantly at 6 months (-1.00, 95% CI -1.74 to -0.26; P=.009). Depression scores were similar, being lower at 12 months (-0.44, 95% CI -1.11 to 0.23; P=.20) and 3 months (-0.24, 95% CI -0.84 to 0.35; P=.42) but only significantly lower at 6 months (-0.77, 95% CI -1.41 to -0.12; P=.02). The ASICA group had significantly higher quality of life scores at 12 months (0.044, 95% CI 0.003-0.085; P=.04) and 6 months (0.070, 95% CI 0.032-0.107; P<.001) and nonsignificantly at 3 months (0.024, 95% CI -0.006 to 0.054; P=.11). ASICA users reported significantly more regular (>5) TSSEs during the study year and significantly higher levels of self-efficacy in conducting TSSE. They also reported significantly higher levels of planning and intention to perform TSSE in the future., Conclusions: Using ASICA for 12 months does not increase melanoma worry, can reduce anxiety and depression, and may improve quality of life. ASICA has the potential to improve the well-being and vigilance of survivors of melanoma and enable the benefits of regular TSSE., Trial Registration: ClinicalTrials.gov NCT03328247; https://clinicaltrials.gov/ct2/show/NCT03328247., International Registered Report Identifier (irrid): RR2-10.1186/s13063-019-3453-x., (©Peter Murchie, Lynda Constable, Susan Hall, William Brant, Julia Allan, Marie Johnston, Judith Masthoff, Amanda Lee, Shaun Treweek, Dolapo Ayansina, Charlotte Proby, Kaz Rahman, Fiona Walter, Nigel Burrows, Amer Durrani, Graeme Maclennan. Originally published in JMIR Cancer (https://cancer.jmir.org), 08.09.2022.)