Risk of malignancy in a high-incidence population-based cohort of Faroese patients with inflammatory bowel disease from 1960 to 2020 - a Faroese IBD cohort study.

BACKGROUND: The association between inflammatory bowel disease (IBD) and malignancy remains disputed despite many observational studies. The Faroese population exhibits the highest occurrence of IBD in the world. This study aimed to investigate the cancer risk in Faroese IBD patients in a nationwide IBD cohort. METHODS: This study included all IBD patients diagnosed in the Faroe Islands between 1960 and 2020. Clinical demographics and cancer diagnoses were retrieved from patient files and the Faroese cancer registry. Cancer risk in IBD patients was calculated as standardized incidence ratios (SIRs) based on the Faroese background population's age- and sex-specific cancer incidence rates, retrievable from NORDCAN. RESULTS: The cohort consisted of 699 patients with a total follow-up time of 9,629 person-years. Overall, the risk of cancer was not statistically significantly increased compared to the background population. Patients diagnosed with cancer at age 50-59 years had higher overall cancer risk (SIR 1.8; 95% CI, 1.02-2.99) as did UC patients diagnosed with IBD at 50-59 (SIR 2.1; 95% CI, 1.10-3.54). Absolute numbers were small and no estimates for site-specific cancers reached statistical significance, though lung, breast, and cancer of the female reproductive organs were elevated among IBD and UC patients, and colorectal cancer in CD patients. CONCLUSIONS: This nationwide study found no statistically significantly increased risk of cancer among Faroese patients with CD or UC, except from age 50 to 59 years. While the incidence of IBD is significantly higher in the Faroe Islands than in other countries, risk estimates of cancers are comparable.

The Burden of Multiple Basal Cell Carcinomas: A Population-wide Study.

Basal cell carcinoma (BCC) is a common skin cancer type and affected individuals are known to be at risk of developing multiple consecutive tumours. Research into BCC multiplicity has, thus far, been challenging, due to a lack of national registration. This registry-based cohort study aimed to analyse the occurrence of multiple BCCs in Sweden, and risk factors for subsequent primary BCCs. Data regarding all histopathologically verified, primary BCC tumours in Sweden from 2004 to 2017 was extracted from the Swedish BCC Registry. Risk of developing a subsequent BCC in relation to person-related factors was estimated with Cox regression analysis. Cumulative risk of BCC development after 1 or 3 earlier BCCs was estimated. In total, 39.9% of individuals with a registered BCC had at least 2 registered tumours. The risk of developing a subsequent BCC increased significantly in males, older age, and with residence in southern Sweden. The cumulative 5-year risk of developing an additional BCC after first diagnosis was approximately 30% in males and 27% in females and increased after multiple previous BCCs. This study showed the cumulative risk of a subsequent BCC to increase with a history of multiple BCCs, indicating the need for clinical surveillance in these individuals.

Acral Melanoma Incidence and Survival Trends in 1990-2020: A Nationwide, Population-based Study.

Acral melanoma is a clinical subtype of melanoma with high mortality, on which research is limited in scope. This study aimed to assess incidence trends and melanoma-specific survival rates for acral melanoma in the Swedish population from 1990 to 2020.This cross-sectional study included patients with an acral melanoma diagnosis from 1990 to 2020 from the nationwide, population-based Swedish Melanoma Registry. Analyses on acral melanoma melanoma-specific survival rates were adjusted for age, sex, histopathological subtype, and tumour thickness. Clinicopathological features and melanoma-specific survival rates were compared between diagnostic periods: 1990-1999, 2000-2009, and 2010-2020, respectively. Changes in standardized incidence rates in 1996-2020 were evaluated separately for males and females. In total, 1,000 acral melanomas in 999 patients were included in the study. No significant yearly change in standardized incidence rates for either males or females was observed, even though the absolute number of cases increased. Factors such as male sex, age ≥ 70 years, and Breslow thickness > 1.0 were independently linked to lower melanoma-specific survival. The 5-year melanoma-specific survival across the studied period ranged from 75.8% to 77.9% for females, and from 62.4% to 71.7% for males.

Cancer survival in the Faroe Islands over the last 50 years compared to the other Nordic countries.

As sustained development in cancer treatment protocols have led to improved survival in most areas of the world, surveillance is needed to ensure that small populations follow suit. Our study reports age-standardized relative cancer survival in the Faroe Islands compared to the other Nordic countries. We present 1- and 5-year survival estimates and corresponding 95% confidence intervals for the Faroe Islands and compare them with estimates for the Nordic countries. The data for this article has been obtained through the NORDCAN collaboration (2019 data). Age-standardized relative survival was estimated using shared R codes on individual-level data within each country. Ten-year calendar inclusion periods were used in addition to the usual 5-year calendar periods to include cancer sites with few cases, which is especially beneficial to the smaller populations. The primary findings were that 1- and 5-year survival were consistently lower in the Faroes for the summary group all sites but non-melanoma skin cancer for both women and men. Further, 5-year survival was lower for women with ovarian cancer and men with lung cancer than in other Nordic countries. Previously, breast cancer survival was low in the Faroes but has improved to a comparable level over the last few years. Colorectal cancer survival was relatively high for both sexes. The reported estimates in this article call for further research to investigate the cancers with lower survival and should call for actions to improve the survival of Faroese cancer patients.

Prognostic Significance of Sentinel Lymph Node Status in Thick Primary Melanomas (> 4 mm).

BACKGROUND: The key prognostic factors for staging patients with primary cutaneous melanoma are Breslow thickness, ulceration, and sentinel lymph node (SLN) status. The multicenter selective lymphadenectomy trial (MSLT-I) verified SLN status as the most important prognostic factor for patients with intermediate-thickness melanoma (Breslow thickness, 1-4 mm). Although most international guidelines recommend SLN biopsy (SLNB) also for patients with thick (> 4 mm, pT4) melanomas, its prognostic role has been questioned. The primary aim of this study was to establish whether SLN status is prognostic in T4 melanoma tumors. METHODS: Data for all patients with a diagnosis of primary invasive cutaneous melanoma of Breslow thickness greater than 1 mm in Sweden between 2007 and 2020 were retrieved from the Swedish Melanoma Registry, a large prospective population-based registry. A multivariable Cox proportional hazard model for melanoma-specific survival (MSS) was constructed based on Breslow thickness stratified for SLN status. RESULTS: The study enrolled 10,491 patients, 1943 of whom had a Breslow thickness greater than 4 mm (pT4). A positive SLN was found for 34% of these pT4 patients. The 5-year MSS was 71%, and the 10-year MSS was 62%. There was a statistically significant difference in MSS between the patients with a positive SLN and those with a negative SLN (hazard ratio of 2.4 (95% confidence interval CI 1.6-3.5) for stage T4a and 2.0 (95% CI 1.6-2.5) for satage T4b. CONCLUSION: Sentinel lymph node status gives important prognostic information also for patients with thick (> 4 mm) melanomas, and the authors thus recommend that clinical guidelines be updated to reflect this.

Increasing melanoma incidence and survival trend shifts with improved melanoma-specific survival between 1990 and 2020 in Sweden.

BACKGROUND: Melanoma-specific survival (MSS) is heterogenous between stages and is highly dependent on the T stage for primary localized disease. New systemic therapies for metastatic cutaneous melanoma (CM) have been introduced since 2012 in Sweden. OBJECTIVES: To analyse the incidence and MSS time trends between 1990 and 2020 in Sweden. METHODS: Nationwide, population-based and prospectively collected clinico-pathological data on invasive CM from the Swedish Melanoma Registry (SweMR) were analysed for survival trends between 1990 and 2020 using Kaplan-Meier curves and Cox proportional hazard ratios (HRs). RESULTS: In total, 77 036 primary invasive CMs were diagnosed in 70 511 patients in Sweden between 1990 and 2020. The 5-year MSS [95% confidence interval (CI)] was 88.9% (88.3-89.4) for 1990-2000, 89.2% (88.7-89.6) for 2001-2010 and 93.0% (92.7-93.9) for 2011-2020. The odds ratios for being diagnosed with nodular melanoma (vs. superficial spreading melanoma) was significantly reduced by 20% (2001-2010) and by 46% (2011-2020) vs. the reference period 1990-2000. Overall, the MSS improved over both diagnostic periods (2001-2010 and 2011-2020) vs. the reference period 1990-2000 among men and women, respectively [HRmen: 2001-2010: 0.89 (95% CI 0.82-0.96) and 2011-2020: 0.62 (95% CI 0.56-0.67); HRwomen: 2001-2010: 0.82 (95% CI 0.74-0.91) and 2011-2020: 0.62 (95% CI 0.56-0.70)]. The risk of death from CM was significantly lower in all age groups for both men and women in the most recent diagnostic period (2011-2020 vs.1990-2000). CONCLUSIONS: The results emphasize the improved MSS among men and women in Sweden. The MSS improvements, specifically for the period 2011-2020, may be correlated to the introduction of new systemic therapies and are here shown for the first time in detail for Sweden.

Association of metformin use and survival in patients with cutaneous melanoma and diabetes.

BACKGROUND: Metformin use has been associated with improved survival in patients with different types of cancer, but research regarding the effect of metformin on cutaneous melanoma (CM) survival is sparse and inconclusive. OBJECTIVES: To investigate the association between metformin use and survival among patients with CM and diabetes. METHODS: All adult patients with a primary invasive CM between 2007 and 2014 were identified in the Swedish Melanoma Registry and followed until death, or end of follow-up on 31 December 2017 in this population-based cohort study. Patients with both CM and type 2 diabetes mellitus were assessed further. Overall survival (OS) and melanoma-specific survival (MSS) were the primary endpoints. Cox proportional hazard models estimating crude and adjusted hazard ratios (HRs) and 95% confidence intervals (CIs) were used comparing peridiagnostic use vs. nonuse of metformin. Dose response was evaluated based on defined daily doses. RESULTS: Among a total of 23 507 patients, 1162 patients with CM and type 2 diabetes mellitus were included in the final cohort, with a median follow-up time of 4.1 years (interquartile range 2.4-6.1). Peridiagnostic metformin use was associated with a significantly decreased risk of death by any cause (HR 0.68, 95% CI 0.57-0.81). Cumulative pre- and postdiagnostic metformin use was also associated with improved OS: the HR for prediagnostic use was 0.90 (95% CI 0.86-0.95) for every 6 months of use and the HR for postdiagnostic use ranged from 0.98 (95% CI 0.97-0.98) for 0-6 months to 0.59 (0.49-0.70) for 24-30 months of use. No association was found for metformin use and MSS. CONCLUSIONS: Metformin use was associated with improved OS in patients with CM and diabetes regardless of timing (pre-, post- or peridiagnostic use) and followed a dose-response pattern. However, further research regarding the underlying mechanisms is warranted.

Incidence and trends of basal cell carcinoma in Sweden: a population-based registry study.

BACKGROUND: Basal cell carcinoma (BCC) is the most common skin cancer. Incidence is largely unknown because of incomplete, or lack of, registration in most countries. OBJECTIVES: To assess current incidence rates and recent trends for BCC in the Swedish population. METHODS: Patient- and tumour-related features of all histologically confirmed BCC tumours diagnosed in Sweden from 2004 to 2017 were extracted from the population-based Swedish BCC Registry. Incidence rates were standardized to the 2013 European Standard Population and trends were analysed using Poisson regression models. RESULTS: The age-standardized person-based incidence rate of BCC in Sweden was 405 per 100 000 in 2017, rising from 308 per 100 000 in 2004, corresponding to an annual relative increase of 1·8% (women, 2·1%; men, 1·4%). Incidence was highest in elderly people and the most common tumour site was the head and neck. In 2017, the most common BCC subtypes were nodular and micronodular/infiltrative BCC (each 31%). Incidence of aggressive BCC subtypes increased faster than other subtypes. CONCLUSIONS: BCC incidence rates in Sweden are relatively high and increasing. The increasing trends were more pronounced in women and for aggressive BCC subtypes. What is already known about this topic? Basal cell carcinoma (BCC) is the most common skin cancer in white populations and its incidence is increasing. BCC is seldom registered in national population-based cancer registries, therefore incidence estimates are extrapolated from small studies or incomplete registers. BCC occurs more often in men than in women and occurs most commonly on the head and neck, followed by the trunk. What does this study add? This study provides current BCC incidence rates for an entire European population. Sex-specific trends show that BCC incidence is increasing faster in women in Sweden. Aggressive BCC subtypes appear to be increasing faster than other subtypes.

Cancer in the Faroe Islands from 1960-2019 - incidence, mortality, and comparisons with the other Nordic countries.

Purpose: In this paper, we present age-standardized cancer incidence and mortality rates in the Faroe Islands. We also compare with the Nordic rates and show incidence rate ratios (IRR) and mortality rate ratios (MRR).Materials and methods: The Faroese cancer registry (FCR) was established in 1994, with incidence available from 1960 and mortality from 1983. The FCR is a part of the NORDCAN collaboration, where the different Nordic countries all report anonymized cancer data by standardized methods, ensuring comparability. Validation efforts revealed that 13% of cases had not been reported to the FCR from 2006 to 2019, emphasizing the need for continued validation efforts of cancer registries. After validation, we submitted the updated cancer cases to NORDCAN and now present this data, taken directly from the NORDCAN website (2019 data).Results: We found that the incidence of the summary group all cancers in the Faroe Islands increased from 1960 to 2019, while cancer mortality decreased from 1983 to 2019. Comparisons with Nordic rates showed significantly lower IRRs for cancer in all cancers, bladder and urinary tract, and skin cancer for both sexes, while IRR was lower for breast cancer in women and prostate cancer in men. Contrary, IRR was higher for rectum and kidney cancer in women and esophagus and testicular cancer in men. There was an increased MRR for cancer in female organs, bladder and urinary tract, and kidney cancer in women, and esophagus and pancreas cancer in men. In contrast, malignant hematopoietic diseases and melanoma in women had a lower MRR.Conclusions: Cancer incidence in the Faroe Islands was lower than in the other Nordic countries. Of particular interest, the incidence of testicular cancer saw a steep increase during the last 20 years, and an investigation into possible causes for this is needed.

CDKN2A genetic testing in melanoma-prone families in Sweden in the years 2015-2020: implications for novel national recommendations.

Background: Inherited pathogenic variants (PVs) in the CDKN2A gene are among the strongest known risk factors for cutaneous melanoma. Carriers are at high risks to develop multiple primary melanomas and other cancers, in particular pancreatic cancer. In this study, the CDKN2A testing, carried out in Sweden in the years 2015-2020, was evaluated.Materials and methods: Included families had (1) three or more cases of melanoma and/or pancreatic cancer, (2) two melanomas in first-degree relatives, the youngest case <55 years or (3) individuals with three or more multiple primary melanomas, the first before the age of 55 years, and no other affected family members. The included families had at least one affected member that had been tested for CDKN2A PVs.Results: In total, 403 families were included, whereof 913 family members had been diagnosed with cutaneous melanoma and 129 with pancreatic cancer, 33 (8.2%) were found to have PVs in CDKN2A. Frequencies ranged from 0.9% in families with only two melanomas to 43.2% in families with three or more melanoma cases and pancreatic cancer (p < 0.001). The frequency of PVs ranged from 2.1% to 16.5% in families where the youngest case was ≥55 years or <35 years (p = 0.040). In families with or without CDKN2A PVs, 37.6% and 10.0% had melanoma cases that had died from melanoma, respectively (p < 0.001).Discussion: Significant differences were seen in the frequencies of CDKN2A PVs, dependent on numbers or age at diagnosis of melanomas and diagnoses of pancreatic cancers in the family. Further, melanoma cases belonging to families that tested positive for CDKN2A PVs had a significantly higher mortality. To summarize, the current evaluation shows that, with adequately selected criteria to guide genetic testing, CDKN2A PVs are identified at significant frequencies. Identification of carrier families is of importance to ensure that members are enrolled in a preventive surveillance program.

Clinical performance of a novel hyperspectral imaging device for cutaneous melanoma and pigmented skin lesions in Caucasian skin.

BACKGROUND: The quest for diagnostic tools for the detection of cutaneous malignant melanoma (cMM) is ongoing. A challenge in cMM care is not overlooking cMM at an early stage, while simultaneously avoiding unnecessary biopsies or excisions of benign pigmented skin lesions (PSLs). A novel hyperspectral imaging (HSI) device is shown to have potential for differentiating equivocal PSLs in Asian skin types. Our objective was to assess the accuracy of the HSI device in distinguishing between cMM and benign PSLs in patients with Caucasian skin types. METHODS: Patients with Caucasian skin types (Fitzpatrick I-II), enrolled for excisional biopsies of PSLs were included and examined using the HSI device. The discrimination index (DI) was used to demonstrate the sensitivity (SE) and specificity (SP) in comparison with the re-evaluated histopathology diagnoses. RESULTS: In 186 patients, 202 pigmented skin lesions were included. The sensitivity to detect cMM was 96.7% (87/90), and the specificity for benign lesions was 42.1% (45/107). The AUC was 0.800 (95% confidence interval (CI): 0.740-0.861). CONCLUSIONS: Our novel HSI device showed a high sensitivity in detecting malignant lesions in patients with Caucasian skin types. Compared with analogous technologies, as multispectral imaging or electrical impedance spectroscopy, our device showed similar or better accuracy in differentiating cMM from benign PSLs. Therefore, it might be a useful clinical tool in skin types I-IV and where further triage of pigmented skin lesions is important.

Participation in a Prospective Cohort Study on Melanoma did not Affect the Incidence and Mortality of the Studied Disease.

Prospective observational studies have shown previously that study participants have lower morbidity and mortality than non-participants. The aim of the current study was to determine whether participants in a prospective cohort study on melanoma have a different incidence and mortality of melanoma compared with non-participants and the background population. Information was collected from Swedish National Registers on participants (n = 30,501) and non-participants (n = 10,499) in the "Melanoma In Southern Sweden" (MISS) study and the background population (n = 243,032). Hazard ratios were calculated for overall incidence of cancer and melanoma, and all-cause and melanoma-specific mortality, using Cox regression. Participants had a lower overall incidence of cancer and all-cause mortality than non-participants and the background population. There was no difference in incidence of melanoma or melanoma-specific characteristics between participants and the background population. In conclusion, participants in the MISS study have a slightly better general health, but are a representative sample of the population with regard to studies of melanoma risk factors.

Automatic diagnosis of melanoma using hyperspectral data and GoogLeNet.

BACKGROUND: Melanoma is a type of superficial tumor. As advanced melanoma has a poor prognosis, early detection and therapy are essential to reduce melanoma-related deaths. To that end, there is a need to develop a quantitative method for diagnosing melanoma. This paper reports the development of such a diagnostic system using hyperspectral data (HSD) and a convolutional neural network, which is a type of machine learning. MATERIALS AND METHODS: HSD were acquired using a hyperspectral imager, which is a type of spectrometer that can simultaneously capture information about wavelength and position. GoogLeNet pre-trained with Imagenet was used to model the convolutional neural network. As many CNNs (including GoogLeNet) have three input channels, the HSD (involving 84 channels) could not be input directly. For that reason, a "Mini Network" layer was added to reduce the number of channels from 84 to 3 just before the GoogLeNet input layer. In total, 619 lesions (including 278 melanoma lesions and 341 non-melanoma lesions) were used for training and evaluation of the network. RESULTS AND CONCLUSION: The system was evaluated by 5-fold cross-validation, and the results indicate sensitivity, specificity, and accuracy of 69.1%, 75.7%, and 72.7% without data augmentation, 72.3%, 81.2%, and 77.2% with data augmentation, respectively. In future work, it is intended to improve the Mini Network and to increase the number of lesions.

Natural disease course of Crohn's disease during the first 5 years after diagnosis in a European population-based inception cohort: an Epi-IBD study.

OBJECTIVE: The Epi-IBD cohort is a prospective population-based inception cohort of unselected patients with inflammatory bowel disease from 29 European centres covering a background population of almost 10 million people. The aim of this study was to assess the 5-year outcome and disease course of patients with Crohn's disease (CD). DESIGN: Patients were followed up prospectively from the time of diagnosis, including collection of their clinical data, demographics, disease activity, medical therapy, surgery, cancers and deaths. Associations between outcomes and multiple covariates were analysed by Cox regression analysis. RESULTS: In total, 488 patients were included in the study. During follow-up, 107 (22%) patients received surgery, while 176 (36%) patients were hospitalised because of CD. A total of 49 (14%) patients diagnosed with non-stricturing, non-penetrating disease progressed to either stricturing and/or penetrating disease. These rates did not differ between patients from Western and Eastern Europe. However, significant geographic differences were noted regarding treatment: more patients in Western Europe received biological therapy (33%) and immunomodulators (66%) than did those in Eastern Europe (14% and 54%, respectively, P<0.01), while more Eastern European patients received 5-aminosalicylates (90% vs 56%, P<0.05). Treatment with immunomodulators reduced the risk of surgery (HR: 0.4, 95% CI 0.2 to 0.6) and hospitalisation (HR: 0.3, 95% CI 0.2 to 0.5). CONCLUSION: Despite patients being treated early and frequently with immunomodulators and biological therapy in Western Europe, 5-year outcomes including surgery and phenotype progression in this cohort were comparable across Western and Eastern Europe. Differences in treatment strategies between Western and Eastern European centres did not affect the disease course. Treatment with immunomodulators reduced the risk of surgery and hospitalisation.

Sex-Based Differences in Incidence of Inflammatory Bowel Diseases-Pooled Analysis of Population-Based Studies From Western Countries.

BACKGROUND & AIMS: Although the incidence of inflammatory bowel diseases (IBDs) varies with age, few studies have examined variations between the sexes. We therefore used population data from established cohorts to analyze sex differences in IBD incidence according to age at diagnosis. METHODS: We identified population-based cohorts of patients with IBD for which incidence and age data were available (17 distinct cohorts from 16 regions of Europe, North America, Australia, and New Zealand). We collected data through December 2016 on 95,605 incident cases of Crohn's disease (CD) (42,831 male and 52,774 female) and 112,004 incident cases of ulcerative colitis (UC) (61,672 male and 50,332 female). We pooled incidence rate ratios of CD and UC for the combined cohort and compared differences according to sex using random effects meta-analysis. RESULTS: Female patients had a lower risk of CD during childhood, until the age range of 10-14 years (incidence rate ratio, 0.70; 95% CI, 0.53-0.93), but they had a higher risk of CD thereafter, which was statistically significant for the age groups of 25-29 years and older than 35 years. The incidence of UC did not differ significantly for female vs male patients (except for the age group of 5-9 years) until age 45 years; thereafter, men had a significantly higher incidence of ulcerative colitis than women. CONCLUSIONS: In a pooled analysis of population-based studies, we found age at IBD onset to vary with sex. Further studies are needed to investigate mechanisms of sex differences in IBD incidence.

Disease course of inflammatory bowel disease unclassified in a European population-based inception cohort: An Epi-IBD study.

BACKGROUND AND AIM: A definitive diagnosis of Crohn's disease (CD) or ulcerative colitis (UC) is not always possible, and a proportion of patients will be diagnosed as inflammatory bowel disease unclassified (IBDU). The aim of the study was to investigate the prognosis of patients initially diagnosed with IBDU and the disease course during the following 5 years. METHODS: The Epi-IBD study is a prospective population-based cohort of 1289 IBD patients diagnosed in centers across Europe. Clinical data were captured prospectively throughout the follow-up period. RESULTS: Overall, 476 (37%) patients were initially diagnosed with CD, 701 (54%) with UC, and 112 (9%) with IBDU. During follow-up, 28 (25%) IBDU patients were changed diagnoses to either UC (n = 20, 71%) or CD (n = 8, 29%) after a median of 6 months (interquartile range: 4-12), while 84 (7% of the total cohort) remained IBDU. A total of 17 (15%) IBDU patients were hospitalized for their IBD during follow-up, while 8 (7%) patients underwent surgery. Most surgeries (n = 6, 75%) were performed on patients whose diagnosis was later changed to UC; three of these colectomies led to a definitive diagnosis of UC. Most patients (n = 107, 96%) received 5-aminosalicylic acid, while 11 (10%) patients received biologicals, of whom five remained classified as IBDU. CONCLUSIONS: In a population-based inception cohort, 7% of IBD patients were not given a definitive diagnosis of IBD after 5 years of follow-up. One in four patients with IBDU eventually was classified as CD or UC. Overall, the disease course and medication burden in IBDU patients were mild.

Sunbed Use Increases Cutaneous Squamous Cell Carcinoma Risk in Women: A Large-scale, Prospective Study in Sweden.

The incidence of cutaneous squamous cell carcinoma has increased rapidly in Sweden in the past decades. Here, we present a prospective study of the Melanoma in Southern Sweden (MISS)-cohort, with 29,460 participating women in southern Sweden that investigates the risk factors for cutaneous squamous cell carcinoma. Data on the host and skin cancer risk factors were collected through questionnaires and then matched with the National Cancer Registry. Statistical analyses were based on uni- and multivariable Cox proportional hazards models, using age as the time-scale. We found that sunbed use (hazard ratio (HR) 1.2, 95% CI: 1.1-1.4), red and light blond hair (HR 1.6, 95% CI: 1.1-2.3), freckles (HR 1.4, 95% CI: 1.1-1.8) and immunosuppressive medications (HR 2.1, 95% CI: 1.3-4.5) were independent risk factors. Furthermore, we observed a dose-dependent relationship between sunbed use and the development of cutaneous squamous cell carcinoma. Our findings support the idea of integrating dermatological follow-up examinations for immunosuppressed patients and banning the use of sunbeds in order to prevent cutaneous squamous cell carcinoma.

Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists.

Background: Deep learning convolutional neural networks (CNN) may facilitate melanoma detection, but data comparing a CNN's diagnostic performance to larger groups of dermatologists are lacking. Methods: Google's Inception v4 CNN architecture was trained and validated using dermoscopic images and corresponding diagnoses. In a comparative cross-sectional reader study a 100-image test-set was used (level-I: dermoscopy only; level-II: dermoscopy plus clinical information and images). Main outcome measures were sensitivity, specificity and area under the curve (AUC) of receiver operating characteristics (ROC) for diagnostic classification (dichotomous) of lesions by the CNN versus an international group of 58 dermatologists during level-I or -II of the reader study. Secondary end points included the dermatologists' diagnostic performance in their management decisions and differences in the diagnostic performance of dermatologists during level-I and -II of the reader study. Additionally, the CNN's performance was compared with the top-five algorithms of the 2016 International Symposium on Biomedical Imaging (ISBI) challenge. Results: In level-I dermatologists achieved a mean (±standard deviation) sensitivity and specificity for lesion classification of 86.6% (±9.3%) and 71.3% (±11.2%), respectively. More clinical information (level-II) improved the sensitivity to 88.9% (±9.6%, P = 0.19) and specificity to 75.7% (±11.7%, P < 0.05). The CNN ROC curve revealed a higher specificity of 82.5% when compared with dermatologists in level-I (71.3%, P < 0.01) and level-II (75.7%, P < 0.01) at their sensitivities of 86.6% and 88.9%, respectively. The CNN ROC AUC was greater than the mean ROC area of dermatologists (0.86 versus 0.79, P < 0.01). The CNN scored results close to the top three algorithms of the ISBI 2016 challenge. Conclusions: For the first time we compared a CNN's diagnostic performance with a large international group of 58 dermatologists, including 30 experts. Most dermatologists were outperformed by the CNN. Irrespective of any physicians' experience, they may benefit from assistance by a CNN's image classification. Clinical trial number: This study was registered at the German Clinical Trial Register (DRKS-Study-ID: DRKS00013570; https://www.drks.de/drks_web/).

Sentinel lymph node biopsy in patients with thin melanomas: Frequency and predictors of metastasis based on analysis of two large international cohorts.

BACKGROUND: Sentinel lymph node (SLN) metastasis in patients with thin melanomas (≤1 mm) is uncommon but adverse prognostic factors may indicate an increased risk. We sought to determine how often SLN biopsy (SLNB) was performed in patients with thin melanomas, establish the frequency of SLN metastasis and evaluate the predictive value of ulceration, tumor mitotic rate, and thickness for SLN involvement. METHODS: Melanoma patients with a Breslow thickness greater than or equal to 0.5 to less than or equal to 1 mm, diagnosed 2009-2016, were identified in the Swedish Melanoma Register (SMR) and the Melanoma Institute Australia (MIA) Database. RESULTS: In total 8165 patients were included from the SMR and 1603 from MIA. SLNB was performed in 9.5% and 16.2% of patients, respectively. Corresponding figures for T1b (American Joint Committee on Cancer [AJCC] 7th Edition) were 19.5% and 24.6%. The SLN positivity rate were 4.4% (Sweden) and 5.8% (MIA). SLN metastasis was more frequent in tumors with ulceration, mitoses, and Breslow thickness greater than or equal to 0.9 mm but none were statistically significant. Younger age was identified as a significant risk factor for SLN positivity at MIA. CONCLUSIONS: A minority of patients with thin melanomas had SLNB performed and the SLN positivity rate was low. This study did not confirm tumor ulceration, mitoses, or thickness as statistically significant predictors for SLN metastasis.