Dermatologist versus artificial intelligence confidence in dermoscopy diagnosis: Complementary information that may affect decision-making.

In dermatology, deep learning may be applied for skin lesion classification. However, for a given input image, a neural network only outputs a label, obtained using the class probabilities, which do not model uncertainty. Our group developed a novel method to quantify uncertainty in stochastic neural networks. In this study, we aimed to train such network for skin lesion classification and evaluate its diagnostic performance and uncertainty, and compare the results to the assessments by a group of dermatologists. By passing duplicates of an image through such a stochastic neural network, we obtained distributions per class, rather than a single probability value. We interpreted the overlap between these distributions as the output uncertainty, where a high overlap indicated a high uncertainty, and vice versa. We had 29 dermatologists diagnose a series of skin lesions and rate their confidence. We compared these results to those of the network. The network achieved a sensitivity and specificity of 50% and 88%, comparable to the average dermatologist (respectively 68% and 73%). Higher confidence/less uncertainty was associated with better diagnostic performance both in the neural network and in dermatologists. We found no correlation between the uncertainty of the neural network and the confidence of dermatologists (R = -0.06, p = 0.77). Dermatologists should not blindly trust the output of a neural network, especially when its uncertainty is high. The addition of an uncertainty score may stimulate the human-computer interaction.

A critical re-evaluation of Mohs micrographic surgery for a facial basal cell carcinoma in older adults: Should we waive this treatment in certain patients?

BACKGROUND: Skin cancer incidences are increasing. Treatment for basal cell carcinomas (BCCs) can be questioned in certain patients. Treatment options are various, but Mohs micrographic surgery (MMS) has the highest cure rate. It is, however, time-consuming and results in high logistical burden and treatment costs for both patients and society. OBJECTIVES: This study critically re-evaluates MMS for facial BCCs in older adults. The main objective is to examine all clinical, tumour and patient characteristics in relation to safety and survival to detect a subgroup in which MMS was not the best choice. The overall aim is to identify characteristics that support clinical decision-making in daily practice. METHODS: Patients that received MMS between November 1998 and December 2012 were included. Only patients >75 years with a facial BCC were withheld for analysis. This is a retrospective cohort study, since evaluating the outcome of MMS in accordance with life expectancy is the main objective. Patient charts were evaluated towards comorbidities, complications and survival. RESULTS: This cohort comprises 207 patients. Median survival was 7.85 years. The age-adjusted Charlson comorbidity index (aCCI) was divided into low/medium scores (aCCI < 6) and high scores (aCCI ≥ 6). Median survival was 11.58 years in the low aCCI group and 3.60 years in the high aCCI group (p < 0.001). There was a very strong association between high aCCI and survival (HR, 6.25; 95% CI, 3.83-10.21). Other characteristics were not associated with survival. CONCLUSIONS: Clinicians should assess the aCCI in older patients presenting with a facial BCC before deciding if MMS is an eligible treatment option. High aCCI has shown to be an indicator for low median survival, even in MMS patients with usually high functional status. MMS should be waived as treatment in older patients with high aCCI scores in favour of other, less intensive and less expensive treatment options.

The therapeutic dilemma of basal cell carcinoma in older adults: A review of the current literature.

Skin cancer is known to be a significant health care threat due to the massively increasing numbers of diagnoses. In 2019, 4 million basal cell carcinoma (BCC) cases were diagnosed globally, making BCC the most frequent of all cancers worldwide in fair skinned populations. Given the increasing life-expectancy for all countries worldwide (by 2050, the world's population of people aged 60 years and older will have doubled), the incidence of BCC is expected to keep increasing in the future. Management of BCCs is challenging, especially among older adults, as mortality due to BCCs is extremely rare, whereas locally destructive growth can cause significant morbidity in certain cases. Therapeutic management in this population is further hampered because of the presence of comorbidities, frailty, and the heterogeneity of these aspects in older patients, leading to treatment dilemmas. A literature review was conducted to identify relevant patient, tumour, and treatment related factors that should be considered in the decision making for BCC treatment in older adults. This narrative review synthesizes all aspects concerning BCC treatment in older adults and aims to make some specific suggestions considering BCC treatment in older adults that can be used in daily practice. We found that nodular BCC was found to be the most common subtype in older adults, most frequently located in the head and neck region. In non-facial BCCs, current literature has shown no significant impact on the quality of life (QoL) in older patients. Besides comorbidity scores, functional status should guide clinicians in treatment decisions. Taking all aspects into account when making treatment decisions is of great importance. When treating superficial BCCs on difficult-to-reach lesions in older adults, a clinician-administered treatment should be suggested because of possible impaired mobility in these patients. Based on current literature, we recommend assessing the comorbidities, the functional status, and frailty in older patients with BCC to evaluate life expectancy. In patients with low-risk BCCs and a limited life expectancy (LLE), an active surveillance or watchful waiting strategy can be suggested.

Can Multispectral Dermoscopy Help In Distinguishing Blue Color?

INTRODUCTION: The interpretation of colors is essential in the dermoscopic evaluation of skin lesions. The same blue color on white dermoscopy may indicate blood or pigment deep in the dermis. Contrary to white dermoscopy, multispectral dermoscopy uses different wavelengths of light to illuminate a lesion and is able to decompose the dermoscopic image into individual maps that allow to more clearly visualize specific skin structures such as pigment distribution (pigment map) and vasculature (blood map). These maps are called skin parameter maps. OBJECTIVES: The aim of this research is to investigate whether skin parameter maps can be used to objectively identify and distinguish the presence of pigment and blood, by using blue naevi and angiomas as models for respectively pigment and blood. METHODS: We retrospectively analyzed 24 blue naevi and 79 angiomas. The skin parameter maps of each of the lesions were independently reviewed by 3 expert dermoscopists, in the absence of the regular white-light dermoscopic image. RESULTS: All the observers provided high levels of diagnostic accuracy for blue naevus and angioma based on skin parameter maps alone, and the dermoscopic diagnosis was considered substantially reliable because of the 79% of diagnostic K agreement. Percentages of blue naevi and angiomas that showed respectively deep pigment and blood were very high at 95.8% and 97.5%. There was a percentage of lesions that counterintuitively showed blood in blue naevi (37.5%) and deep pigment in angiomas (28.8%). CONCLUSIONS: Skin parameter maps based on multispectral images can help to objectify the presence of deep pigment or blood in blue naevi and angiomas. The application of these skin parameter maps could help in the differential diagnosis between pigmented and vascular lesions.

Angiosarcoma Mimicking Rhinophyma.

This case report describes a man in his 60s who was referred to the department of dermatology for further evaluation of a lesion on the nose.

Preoperative assessment of cutaneous melanoma thickness by multispectral dermoscopy.

Preoperative assessment of Breslow thickness by means of sonography and clinical and dermoscopic criteria in white light dermoscopy has been reported, but up until now, the use of multispectral dermoscopy has not been investigated. Aim of this research is to determine whether multispectral dermoscopy and more specifically pigment maps can be used as a predictive marker for Breslow thickness in melanoma. Pigment maps are generated in real time from multispectral dermoscopic images and help to visualize the presence of pigment in a lesion. Multispectral images of 110 melanomas were collected, using a digital handheld multispectral dermatoscope, and assessed independently by five observers for the presence or absence of deep pigment compared with the surrounding skin. According to histopathological examination, the mean Breslow thickness of all 110 melanomas was 1.04 mm (ranging from 0.1 to 14 mm). The group of melanomas where deep pigment was visualized on the multispectral image (n = 78) had a significantly higher Breslow thickness (1.19 mm) than the group where no deep pigment was observed (n = 32, mean Breslow 0.68 mm) (P = 0.025). This study is unique in preoperative assessment of tumour thickness by means of multispectral dermoscopy. Our data indicate that the presence of deep pigment as visualized in digital dermoscopic skin parameter maps identifies a group of thicker melanomas. Further prospective research is needed to validate these pigment maps, generated by multispectral dermoscopy as a measure to predict invasiveness in melanoma.

Study protocol of the BASINEL Study: a pragmatic randomised controlled trial investigating treatment versus no treatment of low-risk basal cell carcinomas in older persons.

INTRODUCTION: Basal cell carcinomas (BCCs) represent 70% of all skin cancers. These tumours do not metastasise but are locally invasive if left untreated. There is a high incidence of BCC in the elderly, and clinicians frequently face important treatment dilemmas. The approach to BCC in the elderly should be investigated thoroughly. METHODS AND ANALYSIS: Data on health-related quality of life (HrQoL), survival and complication rate will be examined in a treatment and a non-treatment arm (1:1 allocation). In the non-treatment arm, in vivo biological behaviour of low-risk BCCs in elderly patients will be examined. The main objective is to combine tumour characteristics with demographic data, in order to determine whether treatment will positively affect the patients' HrQoL within a predetermined time frame. A monocentric randomised controlled trial (RCT) was designed at the Ghent University Hospital. The study population consists of patients with the minimum age of 75 years and a new diagnosis of (a) low-risk BCC(s). Patients in the treatment arm will receive standard care. Patients in the non-treatment arm will be closely monitored: the tumour will be intensively evaluated using multispectral dermoscopy, reflectance confocal microscopy and high-definition optical coherence tomography. All patients will be asked to fill in a questionnaire concerning their HrQoL at consecutive time points. Patient-reported side effects will be evaluated via an additional questionnaire.Primary outcomes will include the difference in HrQoL and the difference in complication risks (treatment vs non-treatment) at different time points of the study. Secondary endpoints are the evolution of the BCCs in the non-treatment arm and the long-term survival in both study arms. Tertiary endpoint is the treatment effectiveness in the treatment arm. The sample size calculation was performed and resulted in a target sample size of 272 patients in this study with a 1:1 allocation. ETHICS AND DISSEMINATION: Subjects can withdraw from participating in this study at any time for any reason without any consequences. Approval for this study was received from the Ethics Committee of the Ghent University Hospital on 26 August 2021.The results of this RCT will be submitted for publication in one or more international, peer-reviewed medical journals, regardless of the nature of the study results. TRIAL REGISTRATION NUMBER: ClinicalTrials.gov (NCT05110924).

Enhanced visualization of blood and pigment in multispectral skin dermoscopy.

BACKGROUND AND OBJECTIVES: Dermoscopy has proven its value in the diagnosis of skin cancer and, therefore, is well established in daily dermatology practice. Up until now, analogue white light dermoscopy is the standard. Multispectral dermoscopy is based on illumination of the skin with narrowband light sources with different wavelengths. Each of these wavelengths is differently absorbed by skin chromophores, such as pigment or (de)oxygenated blood. Multispectral dermoscopy could be a way to enhance the visualization of vasculature and pigment. We illustrate possible additional information by such "skin parameter maps" in some cases of basal cell carcinoma and Bowen's disease. METHODS: Using a new digital multispectral dermatoscope, skin images at multiple wavelengths are collected from different types of skin lesions. These particular images together with the knowledge on skin absorption properties, result in so called "skin parameter maps". RESULTS: A "pigment contrast map," which shows the relative concentration of primarily pigment, and a "blood contrast map" which shows the relative concentration of primarily blood were created. Especially, the latter is of importance in diagnosing keratinocyte skin cancer hence vascular structures are a characteristic feature, as further illustrated in the study. CONCLUSIONS: Skin parameter maps based on multispectral images can give better insight in the inner structures of lesions, especially in lesions with characteristic blood vessels such as Bowen's disease and basal cell carcinoma. Skin parameter maps can be used complementary to regular dermoscopy and could potentially facilitate diagnosing skin lesions.

Fractional Carbon Dioxide Laser of Recent Surgical Scars in the Head and Neck Region: A Split-Scar, Evaluator-Blinded Study.

BACKGROUND: Postoperative scarring is a common cause of patient dissatisfaction. Several strategies have been developed to improve its clinical aspects. OBJECTIVE: To assess efficacy and safety of the 10,600 nm ablative fractional carbon dioxide (CO2) laser in the treatment of recent surgical scars in the head and neck region. METHODS AND MATERIALS: A prospective, randomized, single-blind intrapatient controlled study was conducted on 9 postoperative scars in the head and neck region. On half of the scar, 3 treatment sessions were performed. Physician/Patient Global Assessment (PhGA/PGA) and Patient and Observer Scar Assessment Scales (POSAS) were used to evaluate treatment efficacy. Safety was evaluated by registration of pain and adverse events. RESULTS: No statistically significant differences were noted in terms of PhGA or POSAS (observer). Patient Global Assessment (p = 0.058) and POSAS (patient) (p = 0.091) showed a trend toward better improvement of the treated half. Itch score (p = 0.046) and global end evaluation (patient) (p = 0.026) demonstrated a statistically significant difference in favor of the treated part. Adverse events were minor, and no long-term side effects were noted. CONCLUSION: The use of CO2 fractional laser is safe and is associated with high patient satisfaction. However, objective measurements could not confirm its efficacy in the treatment of recent surgical scars.

Short- and long-term clinical skin effects of testosterone treatment in trans men.

INTRODUCTION: Our knowledge concerning the effects of testosterone (T) therapy on the skin of trans men (female-to-male transsexuals) is scarce. AIM: The aim of this study was to evaluate the short- and long-term clinical effects of T treatment on the skin of trans men. METHODS: We conducted a prospective intervention study in 20 hormone naive trans men and a cross-sectional study in 50 trans men with an average of 10 years on T therapy. MAIN OUTCOME MEASURES: Acne lesions were assessed using the Gradual Acne Grading Scale, hair patterns using the Ferriman and Gallwey classification (F&G), and androgenetic alopecia using the Norwood Hamilton Scale. RESULTS: T treatment increased facial and body hair growth. The F&G score increased progressively from a median value of 0.5 at baseline to a value of 12 after 12 months of T administration. After long-term T treatment, all but one trans man achieved an F&G score indicative of hirsutism in women, with a median value of 24. Only one trans man acquired mild frontotemporal hair loss during the first year of T treatment, whereas 32.7% of trans men had mild frontotemporal hair loss and 31% had moderate to severe androgenetic alopecia after long-term T therapy. The presence and severity of acne increased during the first year of T therapy, and peaked at 6 months. After long-term T treatment, most participants had no or mild acne lesions (93.9%). Dermatological outcome was not demonstrably related to individual serum T or dihydrotestosterone levels. CONCLUSIONS: T treatment increased facial and body hair in a time-dependent manner. The prevalence and severity of acne in the majority of trans men peaked 6 months after beginning T therapy. Severe skin problems were absent after short- and long-term T treatment.

Nonablative fractional laser resurfacing for the treatment of hypertrophic scars: a randomized controlled trial.

BACKGROUND: Nonablative fractional laser (NAFL) therapy is a noninvasive procedure that has been suggested as a treatment option for hypertrophic scars. OBJECTIVES: To evaluate the efficacy and safety of 1540-nm NAFL therapy in the treatment of hypertrophic scars. MATERIALS AND METHODS: An intraindividual randomized controlled trial (RCT) with split lesion design and single-blinded outcome evaluations. Patients received four NAFL treatments at monthly intervals. Primary endpoint was a blinded on-site visual and palpable Physician Global Assessment (PhGA). Adverse event registration and pain evaluation were used to evaluate safety. Patient global assessment (PGA) was a secondary endpoint to additionally evaluate efficacy. RESULTS: The PhGA did not find a statistically significant difference between the treated and untreated control side of 18 patients, although there was significant difference on the PGA 1 (p = .006) and 3 (p = .02) months after last treatment (Wilcoxon signed rank test). Patients experienced moderate pain during treatment and mild adverse events. CONCLUSION: In this trial, blinded PhGA could not confirm the clinical efficacy of 1540-nm nonablative fractional laser in the treatment of hypertrophic scars, but the treatment is safe, and patients judged that the treated part had a better global appearance.

Photodynamic therapy using methyl aminolevulinate in the management of primary superficial basal cell carcinoma: clinical and health economic outcomes.

BACKGROUND: Basal cell carcinoma (BCC) is the most common form of skin cancer worldwide. Different treatment options exist. The efficacy of photodynamic therapy with methyl aminolevulinate (MAL-PDT) has been established in several randomized controlled trials (RCTs). Real life data can differ greatly from data derived from randomized controlled trials (RCTs). OBJECTIVES: To describe the results of a Belgian observational study concerning superficial BCC (sBCC) vis-a-vis clinical and health economic outcomes in order to evaluate the real-life practice of MAL-PDT. METHODS: This study was a prospective, single-arm, open study conducted at eight dermatological institutions during six months after the first MAL-PDT treatment. Eligible patients had to present with lesions, suitable for MAL-PDT according to Belgian reimbursement criteria. Resource use was collected during the study period. Clinical Response (CR) and Cosmetic Outcome (CO), as well as cost of care were evaluated. A subset analysis of patients with sBCC only was conducted. RESULTS: Ninety patients were identified for the analysis (mean age 65 years; 61% female). The mean number of lesions per patient was 1.6, mostly located on the face, the back and the chest. For the entire period, the mean number of visits to a dermatologist was 4 per patient including two MAL-PDT sessions. The average, cumulative amount of MAL used per treatment was 1,256 mg. Two patients experienced adverse events at the application site, none of them serious; all resolved completely. The CR rate was 89% at the end of the study. The CO was "excellent" or "good" in 96% of the patients. Total cost of care was Euro 289 ($414 U.S.) per patient. Cost per lesion was Euro 195 ($280 U.S.). CONCLUSION: The results from the real-life practice study confirm the efficacy found in prior, prospective randomized trials. About four visits and less than one tube of MAL are needed for the full treatment of sBCC in one patient.

Real-life practice study of the clinical outcome and cost-effectiveness of photodynamic therapy using methyl aminolevulinate (MAL-PDT) in the management of actinic keratosis and basal cell carcinoma.

Clinical trials have shown that photodynamic therapy using methyl aminolevulinate (MAL-PDT) is an effective treatment for actinic keratosis (AK), and nodular and superficial basal cell carcinoma (nBCC and sBCC) unsuitable for other available therapies. Economic evaluation models have shown that it is a cost effective intervention as well. The objectives of this prospective, observational, one arm study were (i) to verify in a real-life practice study the results obtained in previous clinical trials with MAL-PDT in the treatment of AK, nBCC and sBCC; (ii) to calculate the real-life cost of treatment and validate predictions from an economic evaluation model. Patients with AK and/or BCC were selected according to Belgian reimbursement criteria for treatment with MAL-PDT. Clinical response, cosmetic outcome and tolerability were assessed. MAL-PDT cost was calculated and compared to published model cost data. Data were collected from 247 patients (117 AK, 130 BCC). A complete clinical response was obtained for 83% of AK (85/102) and BCC (97/116) patients. A good or excellent cosmetic outcome was obtained for 95% of AK patients and 93% of BCC patients. Tolerability was good: only 2 patients withdrew for adverse events. Clinical results were similar to previous studies. Total cost of care per patient was euro 381 for AK, euro 318 for nBCC, and euro 298 for sBCC. Total cost per lesion was euro 58 for AK (identical to model prediction), euro 316 for nBCC and euro 178 for sBCC (both within 20% of model prediction). The clinical results of MAL-PDT in this real-life practice study confirm those demonstrated in previous clinical trials. Costs calculated from this study confirm predicted cost-effectiveness in the original model for MAL-PDT in the management of AK and BCC.

Inter-observer variation in the histopathological diagnosis of clinically suspicious pigmented skin lesions.

When a biopsy is taken of a suspicious pigmented skin lesion, histological examination is expected to establish the definitive diagnosis. This study evaluated the inter-observer variation of 20 pathologists in the histological diagnosis of a randomly selected set of suspicious pigmented skin lesions (PSLs), by comparing their diagnoses to a reference diagnosis. Overall sensitivity for melanoma was 87%, ranging from 55% to 100% between the observers. Sensitivity was significantly lower for thin (Breslow thickness <1 mm) than for thick melanomas (83% versus 97%, p=0.005). Overall melanoma specificity was 94%, ranging from 83% to 100% between observers. Dysplastic naevus was the most important source of false-positive diagnoses, mainly in situ melanomas. Positive and negative predictive values in the given test set were 75% and 97%, respectively. In the case of melanoma, there was quite some variation in measured Breslow thickness. This would have led to a different therapeutic approach in 12% of the readings. Some of the variation seemed to be due to a different interpretation of the presence of a co-existent naevus. In 9% (3/35) of the readings, participants did not agree on the presence of ulceration. These results reflect a tendency to overdiagnose mainly thin melanomas in general histopathological practice. They also demonstrate variation in the assessment of major prognostic factors of melanoma.