OBJECTIVES: We propose a new melanoma segmentation model, SG-UNet, to enhance the precision of melanoma segmentation in dermascopy images to facilitate early melanoma detection. METHODS: We utilized a U-shaped convolutional neural network, UNet, and made improvements to its backbone, skip connections, and downsampling pooling sections. In the backbone, with reference to the structure of VGG, we increased the number of convolutions from 10 to 13 in the downsampling part of UNet to achieve a deepened network hierarchy that allowed capture of more refined feature representations. To further enhance feature extraction and detail recognition, we replaced the traditional convolution the backbone section with self-calibrated convolution to enhance the model's ability to capture both spatial and channel dimensional features. In the pooling part, the original pooling layer was replaced by Haar wavelet downsampling to achieve more effective multi-scale feature fusion and reduce the spatial resolution of the feature map. The global attention mechanism was then incorporated into the skip connections at each layer to enhance the understanding of contextual information of the image. RESULTS: The experimental results showed that the SG-UNet model achieved significantly improved segmentation accuracy on ISIC 2017 and ISIC 2018 datasets as compared with other current state-of-the-art segmentation models, with Dice reached 92.41% and 86.62% and IoU reaching 92.31% and 86.48% on the two datasets, respectively. CONCLUSIONS The proposed model is capable of effective and accurate segmentation of melanoma from dermoscopy images.
Melanoma/diagnosis* ; Humans ; Neural Networks, Computer ; Dermoscopy/methods* ; Skin Neoplasms ; Image Processing, Computer-Assisted/methods* ; Calibration ; Algorithms

Objective: To investigate the clinicopathological characteristics, immunohistochemical profiles, molecular features, and prognosis of subungual melanoma in situ (SMIS). Methods: Thirty cases of SMIS were collected in Fudan University Shanghai Cancer Center, Shanghai, China from 2018 to 2022. The clinicopathological characteristics and follow-up data were retrospectively analyzed. Histopathologic evaluation and immunohistochemical studies were carried out. By using Vysis melanoma fluorescence in situ hybridization (FISH) probe kit, combined with 9p21(CDKN2A) and 8q24(MYC) assays were performed. Results: There were 8 males and 22 females. The patients' ages ranged from 22 to 65 years (median 48 years). All patients presented with longitudinal melanonychia involving a single digit. Thumb was the most commonly affected digit (16/30, 53.3%). 56.7% (17/30) of the cases presented with Hutchinson's sign. Microscopically, melanocytes proliferated along the dermo-epithelial junction. Hyperchromatism and nuclear pleomorphism were two of the most common histological features. The melanocyte count ranged from 30 to 185. Most cases showed small to medium nuclear enlargement (29/30, 96.7%). Pagetoid spread was seen in all cases. Intra-epithelial mitoses were identified in 56.7% (17/30) of the cases. Involvement of nailfold was found in 19 cases, 4 of which were accompanied by cutaneous adnexal extension. The positive rates of SOX10, PNL2, Melan A, HMB45, S-100, and PRAME were 100.0%, 100.0%, 96.0%, 95.0%, 76.9%, and 83.3%, respectively. FISH analysis was positive in 6/9 of the cases. Follow-up data were available in 28 patients, and all of them were alive without disease. Conclusions: SMIS mainly shows small to medium-sized cells. High melanocyte count, hyperchromatism, nuclear pleomorphism, Pagetoid spreading, intra-epithelial mitosis, nailfold involvement, and cutaneous adnexal extension are important diagnostic hallmarks. Immunohistochemistry including SOX10 and PRAME, combined with FISH analysis, is valuable for the diagnosis of SMIS.
Male ; Female ; Humans ; Young Adult ; Adult ; Middle Aged ; Aged ; Skin Neoplasms/pathology* ; Prognosis ; Retrospective Studies ; In Situ Hybridization, Fluorescence ; China ; Melanoma/diagnosis* ; Nail Diseases/pathology* ; Antigens, Neoplasm

This is a report of a patient who presented with a history of what resembled a skin-tag on the plantar aspect of his left foot, which later grew in four months, causing discomfort during ambulation. Little did we know that the growth was just the tip of the iceberg of a vicious malignant melanoma (MM) lurking underneath with metastasis. Upon clinical suspicion, a biopsy was scheduled to obtain histopathological examination (HPE). Magnetic resonance imaging (MRI) reported the lesion to be a malignant melanoma and contrast enhance computed tomography of the thorax abdomen and pelvic (CECT TAP) surveillance and positron-emission tomography (PET) were requested to stage and guide the treatment modalities. A wide surgical resection was performed and wound was left to heal via secondary intention. The aim of this report is to create awareness of early suspicions and detection of MM and treatment, which could lead to a better prognosis and the acceptance of post excision allowing for wound to heal via secondary intention healing.
Melanoma ; Early Diagnosis ; Biopsy ; Prognosis

Melanocytic lesions occur on the surface of the skin, in which the malignant type is melanoma with a high fatality rate, seriously endangering human health. The histopathological analysis is the gold standard for diagnosis of melanocytic lesions. In this study, a fully automated intelligent diagnosis method based on deep learning was proposed to classify the pathological whole slide images (WSI) of melanocytic lesions. Firstly, the color normalization based on CycleGAN neural network was performed on multi-center pathological WSI; Secondly, ResNet-152 neural network-based deep convolutional network prediction model was built using 745 WSI; Then, a decision fusion model was cascaded, which calculates the average prediction probability of each WSI; Finally, the diagnostic performance of the proposed method was verified by internal and external test sets containing 182 and 54 WSI, respectively. Experimental results showed that the overall diagnostic accuracy of the proposed method reached 94.12% in the internal test set and exceeded 90% in the external test set. Furthermore, the color normalization method adopted was superior to the traditional color statistics-based and staining separation-based methods in terms of structure preservation and artifact suppression. The results demonstrate that the proposed method can achieve high precision and strong robustness in pathological WSI classification of melanocytic lesions, which has the potential in promoting the clinical application of computer-aided pathological diagnosis.
Humans ; Deep Learning ; Melanoma/pathology* ; Diagnosis, Computer-Assisted ; Neural Networks, Computer ; Skin/pathology*

Betacoronavirus ; Coronavirus Infections ; epidemiology ; Humans ; Melanoma ; diagnosis ; therapy ; Pandemics ; Pneumonia, Viral ; epidemiology ; Skin Neoplasms ; diagnosis ; therapy

Chronic burn scars often cause various skin malignancies at rates of up to 2%. These lesions are usually squamous cell carcinomas, but rarely, malignant melanoma is reported. We report a 67-year-old male with a malignant melanoma on a burn scar with regional metastasis. This patient presented an ulcerative lesion only in 2 weeks. After histopathological diagnosis, we performed only palliative surgery on patient's demand, and followed up the subsequent deterioration course. Our case reemphasizes the need for rapid diagnosis and treatment when suspect lesions are present on chronic burn scar. Also, physician should be in mind and inform the patient about malignant melanoma and its aggressive course.
Aged ; Burns ; Carcinoma, Squamous Cell ; Cicatrix ; Diagnosis ; Humans ; Male ; Melanoma ; Neoplasm Metastasis ; Palliative Care ; Skin ; Skin Neoplasms ; Ulcer

Artificial Intelligence ; Deep Learning ; Diabetic Retinopathy ; diagnosis ; Humans ; Image Processing, Computer-Assisted ; Machine Learning ; Mass Screening ; Melanoma ; diagnosis ; Referral and Consultation ; Skin Neoplasms ; diagnosis ; Triage

Angiomatoid Spitz nevus is a variant of melanocytic nevus with prominent vasculature. Due to its pathologic features, angiomatoid Spitz nevus in the vaginal wall is extremely rare. A 42-year-old woman presented to the hospital with abnormal vaginal bleeding. Vaginal examination revealed a 2×2-cm well-demarcated tumor on the posterior wall of the vagina. The mass was successfully removed by complete excision and was diagnosed as angiomatoid Spitz nevus on pathologic examination. We present the first reported case of vaginal angiomatoid Spitz nevus, which caused vaginal bleeding. Although angiomatoid Spitz nevus has many histopathological similarities with malignant melanoma, precise histopathological diagnosis is important for preventing overtreatment.
Adult ; Diagnosis ; Female ; Gynecological Examination ; Humans ; Medical Overuse ; Melanoma ; Nevus, Epithelioid and Spindle Cell ; Nevus, Pigmented ; Uterine Hemorrhage ; Vagina

OBJECTIVE: immunotherapy with immune checkpoint inhibitors has become one of the standard therapeutic modalities for patients with advanced melanoma. Melanoma of the female lower genital tract is a rare and aggressive disease, with poor long-term clinical outcomes. To date, no study evaluated the role of immunotherapy in metastatic melanoma of the lower genital tract. METHODS: Data of women with metastatic melanoma of the lower genital tract were prospectively collected. Survival outcomes over time was assessed using Kaplan-Meier model. RESULTS: Seven cases of metastatic melanoma of the lower genital tract (vulva [n=2], vagina [n=4], and uterine cervix [n=1]) treated with immune checkpoint inhibitors are reviewed. Two patients had metastatic disease at diagnosis, while 5 patients developed metastatic disease at a mean (standard deviation) time of 9.9 (±3.0) months from primary diagnosis. Four patients received an anti-cytotoxic T lymphocyte-associated antigen 4 (CTLA4) (ipilimumab) and 3 received an anti-programmed cell death 1 (PD-1) (pembrolizumab [n=2], nivolumab [n=1]) therapy. The response rate to immunotherapy was 28.5%. Patients receiving an anti-PD-1 experienced a better progression-free survival than patients treated with anti-CTLA4 (p=0.01, log-rank test). Although not reaching statistical significance, overall survival was better in patients having an anti-PD-1 therapy in comparison to anti-CTLA4 (p=0.15, log-rank test). CONCLUSION: Results from our series confirm the poor prognosis of women with metastatic melanoma of the lower genital tract, thus supporting the need of exploring new treatment modalities. Further studies are warranted to improve knowledge on the role of immunotherapy in metastatic melanoma of the lower genital tract.
Cell Death ; Cervix Uteri ; Diagnosis ; Disease-Free Survival ; Female ; Humans ; Immunotherapy ; Melanoma ; Prognosis ; Prospective Studies ; Vagina

BACKGROUND: Malignant melanoma is a cutaneous malignancy with a high mortality rate and high potential for metastases. Detailed information on the clinicopathologic characteristics and prognostic factors of cutaneous melanoma is currently limited in Korea. This study aimed to identify the epidemiological and clinicopathologic characteristics of primary cutaneous melanoma in Korean patients, and to assess which prognostic variables could influence both the development of metastases in primary cutaneous melanoma and overall survival (OS). METHODS: A total of 261 patients diagnosed with primary cutaneous melanoma in seven medical centers between 1997 and 2017 were retrospectively investigated with regard to clinical presentation, localization of the tumor, histopathologic subtype, and survival time. RESULTS: The nodular histologic subtype, ulceration, and Breslow thickness were significantly associated with the development of metastasis; and overweight and obesity (body mass index > 23) were significantly associated with increased Breslow thickness. The location of the metastases appeared to influence OS: brain metastases were associated with the highest risk of death, followed by gastrointestinal, lung, and extra-regional lymph node metastases. CONCLUSION: In this study, tumor thickness, nodular histologic subtype, and ulceration predicted metastatic spread of primary cutaneous melanoma. In addition, OS was associated with the location of metastases. Obesity was related to the prognosis of primary cutaneous melanoma. Clinicians should bear these findings in mind when forming a diagnosis because of the risk of a poor prognosis.
Brain ; Diagnosis ; Humans ; Korea ; Lung ; Lymph Nodes ; Melanoma ; Mortality ; Neoplasm Metastasis ; Obesity ; Overweight ; Prognosis ; Retrospective Studies ; Skin Neoplasms ; Ulcer