Pigmented skin lesion segmentation based on random forest and full convolutional neural networks

Shan, Peng; Hu, Ping; Huang, Lin

doi:10.1117/12.2503941

Cited by 2 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average age was 50.27 ± 16.19 years. The inclusion criteria were: (1) All melanoma patients included met the diagnostic guidelines of CSCO melanoma expert committee[14]; (2) liver and kidney functions were normal; and (3) there were no other malignant tumors. All patients who received chemotherapy, immunotherapy, and radiotherapy before operation were excluded.…”

Section: Methodsmentioning

confidence: 99%

Expression and predictive value of miR-489 and miR-21 in melanoma metastasis

Guan

Yuan

et al. 2019

WJCC

View full text Add to dashboard Cite

BACKGROUNDMelanoma is a highly malignant skin tumour, and is one of the most rapidly growing malignant tumors in recent years. According to statistics, the morbidity of cancer increases with age, accounting for 1.6% of new cancer cases and 0.6% of deaths worldwide. Melanoma has a serious impact on society and families, thus it is of great significance to find biological markers related to the diagnosis and treatment of melanoma.AIMTo explore the expression and predictive value of mir-489 and mir-21 in melanoma metastasis.METHODSA total of 60 patients with malignant melanoma treated at our hospital from June 2017 to December 2018 were selected as a research group, while 40 healthy subjects were selected as a control group. qRT-PCR technique was used to detect miR-489 and miR-21 in serum of the two groups. ROC curve was drawn to evaluate the predictive value and diagnostic efficiency. Spearman test was used for correlation analysis. Logistic single- and multiple-factor analyses were performed to identify the risk factors related to melanoma metastasis.RESULTSThe expression of miR-489 in the research group was significantly lower than that in the control group (P < 0.001). However, the expression of miR-21 in the research group was significantly higher than that in the control group (P < 0.001). The expression of miR-489 and miR-21 was related to TNM stage and metastasis (P < 0.001). In the diagnosis of melanoma patients, the sensitivity, specificity, and AUC of miR-489 alone were 75.56%, 80.00%, and 0.852, respectively. The sensitivity, specificity, and AUC of miR-21 alone were 77.78%, 82.22%, and 0.844, respectively. MiR-489 was negatively correlated with TNM stage of melanoma (r = -0.612, P < 0.001), while miR-21 was positively correlated with TNM stage (r = 0.609, P < 0.001). Logistic single- and multiple-factor regression analyses showed that TNM stage, miR-489, and mir-21 were independent risk factors for malignant melanoma metastasis.CONCLUSIONMiR-489 and miR-21 may participate in the process of melanoma occurrence, development, and metastasis, and can be used as potential serum biomarkers for melanoma metastasis diagnosis and disease assessment.

show abstract

Section: Methodsmentioning

confidence: 99%