Background. Atypical vascular pattern is one of the most important features by differentiating between benign and malignant\npigmented skin lesions. Detection and analysis of vascular structures is a necessary initial step for skin mole assessment; it is a\nprerequisite step to provide an accurate outcomefor thewidely used 7-point checklist diagnostic algorithm. Methods. In this research\nwe present a fully automated machine learning approach for segmenting vascular structures in dermoscopy colour images.The UNet\narchitecture is based on convolutional networks and designed for fast and precise segmentation of images. After preprocessing\nthe images are randomly divided into 146516 patches of 64 Ã? 64 pixels each. Results. On the independent validation dataset\nincluding 74 images our implemented method showed high segmentation accuracy. For the U-Net convolutional neural network,\nan average DSC of 0.84, sensitivity 0.85, and specificity 0.81 has been achieved. Conclusion. Vascular structures due to small size\nand similarity to other local structures create enormous difficulties during the segmentation and assessment process. The use of\nadvanced segmentation methods like deep learning, especially convolutional neural networks, has the potential to improve the\naccuracy of advanced local structure detection.
Loading....