The Future of Precision Prevention for Advanced Melanoma

Precision prevention of advanced melanoma is fast becoming a realistic prospect, with personalized, holistic risk stratification allowing patients to be directed to an appropriate level of surveillance, ranging from skin self-examinations to regular total body photography with sequential digital dermoscopic imaging. This approach aims to address both underdiagnosis (a missed or delayed melanoma diagnosis) and overdiagnosis (the diagnosis and treatment of indolent lesions that would not have caused a problem). Holistic risk stratification considers several types of melanoma risk factors: clinical phenotype, comprehensive imaging-based phenotype, familial and polygenic risks. Artificial intelligence computer-aided diagnostics combines these risk factors to produce a personalized risk score, and can also assist in assessing the digital and molecular markers of individual lesions. However, to ensure uptake and efficient use of AI systems, researchers will need to carefully consider how best to incorporate privacy and standardization requirements, and above all address consumer trust concerns.

Multispectral Imaging Algorithm Predicts Breslow Thickness of Melanoma

Breslow thickness is a major prognostic factor for melanoma. It is based on histopathological evaluation, and thus it is not available to aid clinical decision making at the time of the initial melanoma diagnosis. In this work, we assessed the efficacy of multispectral imaging (MSI) to predict Breslow thickness and developed a classification algorithm to determine optimal safety margins of the melanoma excision. First, we excluded nevi from the analysis with a novel quantitative parameter. Parameter s’ could differentiate nevi from melanomas with a sensitivity of 89.60% and specificity of 88.11%. Following this step, we have categorized melanomas into three different subgroups based on Breslow thickness (≤1 mm, 1–2 mm and >2 mm) with a sensitivity of 78.00% and specificity of 89.00% and a substantial agreement (κ = 0.67; 95% CI, 0.58–0.76). We compared our results to the performance of dermatologists and dermatology residents who assessed dermoscopic and clinical images of these melanomas, and reached a sensitivity of 60.38% and specificity of 80.86% with a moderate agreement (κ = 0.41; 95% CI, 0.39–0.43). Based on our findings, this novel method may help predict the appropriate safety margins for curative melanoma excision.

Survival of Women Previously Diagnosed of Melanoma with Subsequent Pregnancy: A Systematic Review and Meta-Analysis and a Single-Center Experience

Melanoma incidence has increased over the last few decades. How the prognosis of a previously diagnosed melanoma may be affected by a woman’s subsequent pregnancy has been debated in the literature since the 1950s, and the outcomes are essential to women who are melanoma survivors in their childbearing years. The main objective of this systematic review is to improve the understanding of whether the course of melanoma in a woman may be altered by a subsequent pregnancy and to help clinicians’ diagnosis. Eligible studies for the systematic review were clinical trials, observational cohort studies and case-control studies that compared prognosis outcomes for non-pregnant patients with melanoma, or pregnant before melanoma diagnosis, versus pregnant patients after a diagnosis of melanoma. The search strategy yielded 1101 articles, of which 4 met the inclusion criteria for the systematic review. All the studies were retrospective non-randomised cohorts with patients with melanomas diagnosed before pregnancy. According to our findings, a subsequent pregnancy was not a significant influence on the outcome of a previous melanoma. However, given the small number of identified studies and the heterogeneous data included, it is recommended to approach these patients with caution, and counselling should be given by known prognostic factors. We also reviewed the medical records of 84 patients of childbearing age (35.8 ± 6.3 years, range 21–45 years) who were diagnosed with cutaneous invasive melanoma in our hospital between 2008 and 2018 (N = 724). Of these, 11 (13.1%) had a pregnancy after melanoma diagnosis (age at pregnancy: 35.6 ± 6.3 years). No statistical differences in outcome were detected.

Diagnosis of Melanoma Using Deep Learning

When compared to other types of skin cancer, melanoma is the deadliest. However, those who are diagnosed early on have a better prognosis for the purpose of providing a supplementary opinion to experts; various methods of spontaneous melanoma recognition and diagnosis have been investigated by different researchers. Because of the imbalance between classes, building models from existing information has proven difficult. Machine learning algorithms paired with imbalanced basis training approaches are being evaluated for their performance on the melanoma diagnosis challenge in this study. There were 200 dermoscopic photos in which patterns of skin lesions could be extracted using the VGG16, VGG19, Inception, and ResNet convolutional neural network architectures with the ABCD rule. After employing attribute selection with GS and training data balance using Synthetic Minority Oversampling Technique and Edited Nearest Neighbor rule, the random forest classifier had a sensitivity of nearly 93% and a kappa index ( k − index ) of 78%.

Proportion of Thick versus Thin Melanomas as a Benchmarking Tool

Background: The ratio of benign moles excised for each malignant melanoma diagnosed (number-needed-to-excise (NNE)) is a metric used to express the efficiency of diagnostic accuracy of melanoma. The literature suggests a progressive effort to reduce the NNE, thus raising concerns about missing early melanoma because the NNE does not capture the most significant outcome for melanoma prognosis, which is linked to the Breslow thickness. A lower NNE could reduce health costs related to melanoma diagnosis only if doing so does not increase the proportion of thicker melanomas. Objectives: The diagnostic performance by two tertiary referral centres using the NNE and proportion of thick (Breslow thickness > 1 mm) versus thin (Breslow thickness ≤ 1 mm) excised melanoma (thick/thin ratio: TTR) was compared to determine if a lower NNE is associated with a greater proportion of thicker melanoma. Combining TTR with NNE allows a better estimate of the effectiveness in melanoma diagnosis, assessing both the overall cost for a given pool of excised melanomas and costs due to unnecessary nevi excision at a particular dermatology centre. Methods: Demographic data and Breslow thickness of excised melanoma were extracted from patient histologic records at two referral centres for melanoma (Parma Dermatology Unit and Ravenna and Meldola Skin Cancer Unit, Istituto Scientifico Romagnolo per lo Studio e la Cura dei Tumori. IRCCS (IRST)) on all skin tumours excised between 2002 and 2011 and diagnosed as melanoma or melanocytic nevus. NNE and TTR were calculated and compared among the considered variables. Logistic regression was used to assess the contribution of each variable in predicting a higher TTR. Results: Data from 16,738 excised lesions were analysed. The IRST Unit reported a mean NNE of 4.6, whereas the Parma Unit excised 10.6 nevi for each melanoma. No statistically significant differences existed in the mean (IRST Unit, 0.56 ± 0.89 mm; Parma Unit, 1.07 ± 2.2 mm) and median (range) Breslow thickness (IRST Unit, 0.4 (9) mm; Parma Unit 0.4 (30) mm). The TTR between centres was significantly different (Parma Unit, 24%; IRST Unit, 12%; p < 0.001). Based on logistic regression, the diagnosing centre was the most powerful factor in determining a thickness of >1 mm among diagnosed melanomas (OR = 1.8; 95% CI, 1.2–2.7; p < 0.01), with all other factors being equal. The NNE decreased at both centres from younger-to-older patients, whereas the TTR increased simultaneously; however, the increase in TTR was non-significantly related to NNE reduction after adjusting for confounders (age, gender, and localization). Conclusions: A better diagnostic performance is capable of reducing the NNE and TTR, i.e., unnecessary excisions of melanocytic nevi can be reduced without increasing the risk of overlooking melanomas. The TTR, in addition to the NNE, allows stakeholders to better estimate the effectiveness in melanoma diagnosis because both overall costs for a given pool of excised melanomas and costs due for unnecessary nevi excision at a particular dermatology centre can be compared.

Acidic and Hypoxic Microenvironment in Melanoma: Impact of Tumour Exosomes on Disease Progression

The mechanisms of melanoma progression have been extensively studied in the last decade, and despite the diagnostic and therapeutic advancements pursued, malignant melanoma still accounts for 60% of skin cancer deaths. Therefore, research efforts are required to better define the intercellular molecular steps underlying the melanoma development. In an attempt to represent the complexity of the tumour microenvironment (TME), here we analysed the studies on melanoma in acidic and hypoxic microenvironments and the interactions with stromal and immune cells. Within TME, acidity and hypoxia force melanoma cells to adapt and to evolve into a malignant phenotype, through the cooperation of the tumour-surrounding stromal cells and the escape from the immune surveillance. The role of tumour exosomes in the intercellular crosstalk has been generally addressed, but less studied in acidic and hypoxic conditions. Thus, this review aims to summarize the role of acidic and hypoxic microenvironment in melanoma biology, as well as the role played by melanoma-derived exosomes (Mexo) under these conditions. We also present a perspective on the characteristics of acidic and hypoxic exosomes to disclose molecules, to be further considered as promising biomarkers for an early detection of the disease. An update on the use of exosomes in melanoma diagnosis, prognosis and response to treatment will be also provided and discussed.

An ensemble-based convolutional neural network model powered by a genetic algorithm for melanoma diagnosis

Melanoma is one of the main causes of cancer-related deaths. The development of new computational methods as an important tool for assisting doctors can lead to early diagnosis and effectively reduce mortality. In this work, we propose a convolutional neural network architecture for melanoma diagnosis inspired by ensemble learning and genetic algorithms. The architecture is designed by a genetic algorithm that finds optimal members of the ensemble. Additionally, the abstract features of all models are merged and, as a result, additional prediction capabilities are obtained. The diagnosis is achieved by combining all individual predictions. In this manner, the training process is implicitly regularized, showing better convergence, mitigating the overfitting of the model, and improving the generalization performance. The aim is to find the models that best contribute to the ensemble. The proposed approach also leverages data augmentation, transfer learning, and a segmentation algorithm. The segmentation can be performed without training and with a central processing unit, thus avoiding a significant amount of computational power, while maintaining its competitive performance. To evaluate the proposal, an extensive experimental study was conducted on sixteen skin image datasets, where state-of-the-art models were significantly outperformed. This study corroborated that genetic algorithms can be employed to effectively find suitable architectures for the diagnosis of melanoma, achieving in overall 11% and 13% better prediction performances compared to the closest model in dermoscopic and non-dermoscopic images, respectively. Finally, the proposal was implemented in a web application in order to assist dermatologists and it can be consulted at http://skinensemble.com.

Appending Global to Local features for Skin Lesion Classification on Dermoscpic Images

Skin cancer is the deadliest diseases compared with all other kinds of cancer. In this paper various pre- and post-treatments are proposed for improving automated melanoma diagnosis of dermoscopy images. At first pre-processing have done to exclude unwanted parts, a new triple-A segmentation proposes to extract lesion according to their histogram patterns. Lastly, suggest appending process with testing many factors for superior detection decision. This paper offers a novel approach with testing different detection rules: first system used fuzzy rules based on a different features, a second test has been done by modeled local colours with bag-of-features classifier. Then proposed adding lesion shape on two previous systems as their global form in the first one, while distributing it and appending with local colour patches in the second system. For each case, different features; various colour models, and many other parameters are examined to decide which settings are more discriminating. Evaluates performance of each method has carried out on (ISIC2019 Challenge) dermoscopic database. The novel processes with their a specific parameters are rising the classification accuracy to 98.26%.