Lesion segmentation is a critical task in skin cancer analysis and detection. When developing deep learning-based segmentation methods, we need a large number of human-annotated labels to serve as ground truth for model-supervised learning. Due to the complexity of dermatological images and the subjective differences of different dermatologists in decision-making, the labels in the segmentation target boundary region are prone to produce uncertain labels or error labels. These labels may lead to unsatisfactory performance of dermoscopy segmentation. In addition, the model trained by the errored one-hot label may be overconfident, which can lead to arbitrary prediction and model overfitting. In this paper, a superpixel-oriented label distribution learning method is proposed. The superpixels formed by the simple linear iterative cluster (SLIC) algorithm combine one-hot labels constraint and define a distance function to convert it into a soft probability distribution. Referring to the model structure of knowledge distillation, after Superpixel-oriented label distribution learning, we get soft labels with structural prior information. Then the soft labels are transferred as new knowledge to the lesion segmentation network for training. Ours method on ISIC 2018 datasets achieves an Dice coefficient reaching 84%, sensitivity 79.6%, precision 80.4%, improved by 19.3%, 8.6% and 2.5% respectively in comparison with the results of U-Net. We also evaluate our method on the tasks of skin lesion segmentation via several general neural network architectures. The experiments show that ours method improves the performance of network image segmentation and can be easily integrated into most existing deep learning architectures. Full article

Despite the recent advances in immune therapies, melanoma remains one of the deadliest and most difficult skin cancers to treat. Literature reports that multifarious driver oncogenes with tumor suppressor genes are responsible for melanoma progression and its complexity can be demonstrated by alterations in expression with signaling cascades. However, a further improvement in the therapeutic outcomes of the disease is highly anticipated with the aid of humanoid assistive technologies that are nowadays touted as a superlative alternative for the clinical diagnosis of diseases. The development of the projected technology-assistive diagnostics will be based on the innovations of medical imaging, artificial intelligence, and humanoid robots. Segmentation of skin lesions in dermoscopic images is an important requisite component of such a breakthrough innovation for an accurate melanoma diagnosis. However, most of the existing segmentation methods tend to perform poorly on dermoscopic images with undesirable heterogeneous properties. Novel image segmentation methods are aimed to address these undesirable heterogeneous properties of skin lesions with the help of image preprocessing methods. Nevertheless, these methods come with the extra cost of computational complexity and their performances are highly dependent on the preprocessing methods used to alleviate the deteriorating effects of the inherent artifacts. The overarching objective of this study is to investigate the effects of image preprocessing on the performance of a saliency segmentation method for skin lesions. The resulting method from the collaboration of color histogram clustering with Otsu thresholding is applied to demonstrate that preprocessing can be abolished in the saliency segmentation of skin lesions in dermoscopic images with heterogeneous properties. The color histogram clustering is used to automatically determine the initial clusters that represent homogenous regions in an input image. Subsequently, a saliency map is computed by agglutinating color contrast, contrast ratio, spatial feature, and central prior to efficiently detect regions of skin lesions in dermoscopic images. The final stage of the segmentation process is accomplished by applying Otsu thresholding followed by morphological analysis to obliterate the undesirable artifacts that may be present at the saliency detection stage. Extensive experiments were conducted on the available benchmarking datasets to validate the performance of the segmentation method. Experimental results generally indicate that it is passable to segment skin lesions in dermoscopic images without preprocessing because the applied segmentation method is ferociously competitive with each of the numerous leading supervised and unsupervised segmentation methods investigated in this study. Full article

The early detection of skin cancer, especially through the examination of lesions with malignant characteristics, has been reported to significantly decrease the potential fatalities. Segmentation of the regions that contain the actual lesions is one of the most widely used steps for achieving an automated diagnostic process of skin lesions. However, accurate segmentation of skin lesions has proven to be a challenging task in medical imaging because of the intrinsic factors such as the existence of undesirable artifacts and the complexity surrounding the seamless acquisition of lesion images. In this paper, we have introduced a novel algorithm based on gamma correction with clustering of keypoint descriptors for accurate segmentation of lesion areas in dermoscopy images. The algorithm was tested on dermoscopy images acquired from the publicly available dataset of Pedro Hispano hospital to achieve compelling equidistant sensitivity, specificity, and accuracy scores of 87.29%, 99.54%, and 96.02%, respectively. Moreover, the validation of the algorithm on a subset of heavily noised skin lesion images collected from the public dataset of International Skin Imaging Collaboration has yielded the equidistant sensitivity, specificity, and accuracy scores of 80.59%, 100.00%, and 94.98%, respectively. The performance results are propitious when compared to those obtained with existing modern algorithms using the same standard benchmark datasets and performance evaluation indices. Full article

Melanoma is a melanocytic tumor that is responsible for the most skin cancer-related deaths. By contrast, seborrheic keratosis (SK) is a very common benign lesion with a clinical picture that may resemble melanoma. We used a multispectral imaging device to distinguish these two entities, with the use of autofluorescence imaging with 405 nm and diffuse reflectance imaging with 525 and 660 narrow-band LED illumination. We analyzed intensity descriptors of the acquired images. These included ratios of intensity values of different channels, standard deviation and minimum/maximum values of intensity of the lesions. The pattern of the lesions was also assessed with the use of particle analysis. We found significantly higher intensity values in SKs compared with melanoma, especially with the use of the autofluorescence channel. Moreover, we found a significantly higher number of particles with high fluorescence in SKs. We created a parameter, the SK index, using these values to differentiate melanoma from SK with a sensitivity of 91.9% and specificity of 57.0%. In conclusion, this imaging technique is potentially applicable to distinguish melanoma from SK based on the analysis of various quantitative parameters. For this application, multispectral imaging could be used as a screening tool by general physicians and non-experts in the everyday practice. Full article

Aim: To perform a comprehensive analysis of discordances between contrast-enhanced CT (ceCT) and ¹⁸F-FDG PET/CT in the evaluation of the extra-cerebral treatment monitoring in patients with stage IV melanoma. Materials and methods: We conducted a retrospective monocentric observational study over a 3-year period in patients referred for ¹⁸F-FDG PET/CT and ceCT in the framework of therapy monitoring of immune checkpoint (ICIs) as of January 2017. Imaging reports were analyzed by two physicians in consensus. The anatomical site responsible for discordances, as well as induced changes in treatment were noted. Results: Eighty patients were included and 195 pairs of scans analyzed. Overall, discordances occurred in 65 cases (33%). Eighty percent of the discordances (52/65) were due to ¹⁸F-FDG PET/CT scans upstaging the patient. Amongst these discordances, 17/52 (33%) led to change in patient’s management, the most frequent being radiotherapy of a progressing site. ceCT represented 13/65 (20%) of discordances and induced changes in patients’ management in 2/13 cases (15%). The most frequent anatomical site involved was subcutaneous for ¹⁸F-FDG PET/CT findings and lung or liver for ceCT. Conclusions: Treatment monitoring with ¹⁸F-FDG PET/CT is more efficient than ceCT and has a greater impact in patient’s management. Full article

Background: The use of ¹⁸F-2-Fluor-2-desoxy-D-glucose Positron Emission Tomography/Computed Tomography FDG-PET/CT in clinical routine for staging, treatment response monitoring and post treatment surveillance in metastatic melanoma patients has noticeably increased due to significant improvement of the overall survival rate in melanoma patients. However, determining the dignity of the findings with increased metabolic activity on FDG-PET/CT can be sometimes challenging and may need further investigation. Purpose: We aimed to investigate the malignancy rate of indeterminate findings on FDG-PET/CT in metastatic cutaneous melanoma patients. Methods: This single-center retrospective study included cutaneous melanoma patients who underwent FDG-PET/CT in clinical routine between 2015 and 2017 with findings reported as indeterminate and therefore requiring further evaluation. The dignity of the included findings was determined by subsequent imaging and, if required, additional histopathology. The impact of the outcome on the clinical management was also reported. Results: A total of 842 FDG-PET/CT reports of 244 metastatic cutaneous melanoma patients were reviewed. Sixty indeterminate findings were included. Almost half of all indeterminate findings were lymph nodes, lung nodules and cerebral lesions. In total, 43.3% of all included findings proved to be malignant. 81% of all malignant lesions were metastases of cutaneous melanoma, while 19% of all malignant lesions could be attributed to other primary malignancies, such as lung, breast, thyroid and colorectal cancers. Malignant findings influenced clinical management in 60% of the cases. Conclusion: Indeterminate findings on FDG-PET/CT in metastatic cutaneous melanoma patients should be further investigated. Almost one out of every two indeterminate findings on FDG-PET/CT is malignant. The majority of the findings are melanoma manifestations, however, in a significant percentage, other primary tumors are found. Upon verification, patient management is changed in most cases. Full article

Lung nodules are frequent findings in chest computed tomography (CT) in patients with metastatic melanoma. In this study, we assessed the frequency and compared morphologic differences of metastases and benign nodules. We retrospectively evaluated 85 patients with melanoma (AJCC stage III or IV). Inclusion criteria were ≤20 lung nodules and follow-up using CT ≥183 days after baseline. Lung nodules were evaluated for size and morphology. Nodules with significant growth, nodule regression in line with RECIST assessment or histologic confirmation were judged to be metastases. A total of 438 lung nodules were evaluated, of which 68% were metastases. At least one metastasis was found in 78% of patients. A 10 mm diameter cut-off (used for RECIST) showed a specificity of 95% and a sensitivity of 20% for diagnosing metastases. Central location (n = 122) was more common in metastatic nodules (p = 0.009). Subsolid morphology (n = 53) was more frequent (p < 0.001), and calcifications (n = 13) were solely found in non-metastatic lung nodules (p < 0.001). Our data show that lung nodules are prevalent in about two-thirds of melanoma patients (AJCC stage III/IV) and the majority are metastases. Even though we found a few morphologic indicators for metastatic or non-metastatic lung nodules, morphology has limited value to predict the presence of lung metastases. Full article

Segmentation of skin lesions is a challenging task because of the wide range of skin lesion shapes, sizes, colors, and texture types. In the past few years, deep learning networks such as U-Net have been successfully applied to medical image segmentation and exhibited faster and more accurate performance. In this paper, we propose an extended version of U-Net for the segmentation of skin lesions using the concept of the triple attention mechanism. We first selected regions using attention coefficients computed by the attention gate and contextual information. Second, a dual attention decoding module consisting of spatial attention and channel attention was used to capture the spatial correlation between features and improve segmentation performance. The combination of the three attentional mechanisms helped the network to focus on a more relevant field of view of the target. The proposed model was evaluated using three datasets, ISIC-2016, ISIC-2017, and PH2. The experimental results demonstrated the effectiveness of our method with strong robustness to the presence of irregular borders, lesion and skin smooth transitions, noise, and artifacts. Full article

Background. The use of teledermatology has spread over the last years, especially during the recent SARS-Cov-2 pandemic. Teledermoscopy, an extension of teledermatology, consists of consulting dermoscopic images, also transmitted through smartphones, to remotely diagnose skin tumors or other dermatological diseases. The purpose of this work was to verify the diagnostic validity of images acquired with an inexpensive smartphone microscope (Nurugo^TM), employing convolutional neural networks (CNN) to classify malignant melanoma (MM), melanocytic nevus (MN), and seborrheic keratosis (SK). Methods. The CNN, trained with 600 dermatoscopic images from the ISIC (International Skin Imaging Collaboration) archive, was tested on three test sets: ISIC images, images acquired with the Nurugo^TM, and images acquired with a conventional dermatoscope. Results. The results obtained, although with some limitations due to the smartphone device and small data set, were encouraging, showing comparable results to the clinical dermatoscope and up to 80% accuracy (out of 10 images, two were misclassified) using the Nurugo^TM demonstrating how an amateur device can be used with reasonable levels of diagnostic accuracy. Conclusion. Considering the low cost and the ease of use, the Nurugo^TM device could be a useful tool for general practitioners (GPs) to perform the first triage of skin lesions, aiding the selection of lesions that require a face-to-face consultation with dermatologists. Full article

Melanoma is a deadly disease that often exhibits relentless progression and can have both early and late metastases. Recent advances in immunotherapy and targeted therapy have dramatically increased patient survival for patients with melanoma. Similar advances in molecular targeted PET imaging can identify molecular pathways that promote disease progression and therefore offer physiological information. Thus, they can be used to assess prognosis, tumor heterogeneity, and identify instances of treatment failure. Numerous agents tested preclinically and clinically demonstrate promising results with high tumor-to-background ratios in both primary and metastatic melanoma tumors. Here, we detail the development and testing of multiple molecular targeted PET-imaging agents, including agents for general oncological imaging and those specifically for PET imaging of melanoma. Of the numerous radiopharmaceuticals evaluated for this purpose, several have made it to clinical trials and showed promising results. Ultimately, these agents may become the standard of care for melanoma imaging if they are able to demonstrate micrometastatic disease and thus provide more accurate information for staging. Furthermore, these agents provide a more accurate way to monitor response to therapy. Patients will be able to receive treatment based on tumor uptake characteristics and may be able to be treated earlier for lesions that with traditional imaging would be subclinical, overall leading to improved outcomes for patients. Full article

Mucosal melanoma is a rare tumor with aggressive biological behavior and poor prognosis. Diagnosis is often performed at an advanced stage when the lesions become symptomatic. Although dermoscopy and reflectance confocal microscopy (RCM) are widely used techniques for the diagnosis of cutaneous tumors, their use for mucosal lesions is not well established, probably because the latter are rarer. The objective of this study was to evaluate current literature on these imaging techniques for mucosal melanoma. We searched in PubMed and Cochrane databases all studies up to October 2020 dealing with dermoscopy, RCM, and mucosal melanoma. We found that the most relevant dermoscopic features were structureless pattern and/or the presence of multiple colors. RCM examination mainly showed numerous basal hyper-reflective dendritic cells and loss of normal architecture of the papillae of the lamina propria. Although diagnostic algorithms have been proposed for both techniques, the limit of these methods is the absence of large studies and of standardized and shared diagnostic criteria. Full article

(1) Background: Ciliary body uveal melanoma is a rare subtype of uveal melanoma which comprises 3–5% of melanomas, an immunogenic cancer, and can present multifaceted initial clinical manifestations, masquerading as various ocular pathologies. Chronic lymphocytic leukemia (CLL) presents immunodeficiency and risk for the development of a secondary malignancy, with Bruton’s tyrosine kinase inhibitor treatment having a mutagenic effect and a secondary anti-platelet aggregation effect. We present the case of a 65-year-old patient undergoing treatment for CLL with ibrutinib who presented with recurrent hyphema that masked an underlying, inferiorly situated, ciliary body uveal melanoma; (2) Methods: Retrospective case review; (3) Results: An ophthalmological examination together with imaging via mode B ultrasound and contrast-enhanced magnetic resonance imaging resulted in the clinical and imagistic diagnosis of a ciliary body uveal melanoma. A pathological examination of the enucleated eye confirmed the diagnosis. Postoperative tumoral reoccurrence was not detected for 1½ years, however, CLL immunosuppression worsened with admission for severe COVID-19 disease. (4) Conclusions: CLL patient screening for melanoma should also include detailed ophthalmological examinations, which could also include ultrasound ophthalmological imaging. The avoidance of uveal melanoma metastatic disease is paramount for patient survival. CLL manifests additional profound immunosuppression. Full article

Early detection of immune-related adverse events (irAEs) with immune checkpoint inhibitors (ICIs) is crucial, particularly when these are likely to mimic tumor progression, as well as sarcoid-like reactions. Here, we report the case of a 68-year woman, with a history of four primary cutaneous melanomas (thickest lesion with BRAF mutation removed from the left axilla 2 years before), who was diagnosed with BRAF V600E-mutant metastatic melanoma and treated by ICI targeting the PD-1 receptor. Follow-up whole-body positron emission tomography/computed tomography (PET/CT) using 18F-fluorodeoxyglucose ([18F]-FDG) was performed at 15 months, and FDG-avid subcutaneous nodules on her legs were detected. A biopsy from a lesion on her right leg was obtained, and histology strongly suggested erythema nodosum. Given the isolated nature of these lesions, the normal serum Angiotensin-Converting Enzyme and the context of ICI, an immune-related sarcoid-like reaction was retained as the most likely diagnosis. Recent literature in immune-oncology suggests that erythema nodosum could be directly related to ICI(s). Although erythema nodosum is a rare occurrence with imaging features overlapping with malignancy, it should be considered in the differential diagnosis of suspicious in-transit metastasis, especially when the patient is treated with ICIs and when lesions follow a bilateral distribution. In conclusion, nuclear medicine physicians should keep in mind this irAE when interpreting PET/CT scans in clinical practice in order to avoid false-positive findings. Full article