کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
6863696 1439518 2018 26 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Retinal vessel segmentation of color fundus images using multiscale convolutional neural network with an improved cross-entropy loss function
ترجمه فارسی عنوان
تقسیم عروق شبکیه تصاویر فوندوس رنگ با استفاده از شبکه عصبی کانولوشن چند بعدی با عملکرد بهبود یافته بین آنتروپی انتروپی
کلمات کلیدی
تقسیم عروق شبکیه، شبکه عصبی متقاطع، چند منظوره، عملکرد تلفات عبور انتروپی، زمینه تصادفی محض،
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
چکیده انگلیسی
Retinal vessel analysis of fundus images is an indispensable method for the screening and diagnosis of related diseases. In this paper, we propose a novel retinal vessel segmentation method of the fundus images based on convolutional neural network (CNN) and fully connected conditional random fields (CRFs). The segmentation process is mainly divided into two steps. Firstly, a multiscale CNN architecture with an improved cross-entropy loss function is proposed to produce the probability map from image to image. We construct the multiscale network by combining the feature map of each middle layer to learn more detail information of the retinal vessels. Meanwhile, our proposed cross-entropy loss function ignores the slightest loss of relatively easy samples in order to take more attention to learn the hard examples. Secondly, CRFs is applied to get the final binary segmentation result which makes use of more spatial context information by taking into account the interactions among all of the pixels in the fundus images. The effectiveness of the proposed method has been evaluated on two public datasets, i.g., DRIVE and STARE with comparisons against eleven state-of-the-art approaches including five deep learning based methods. Results show that our method allows for detection of more tiny blood vessels and more precise locating of the edges.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neurocomputing - Volume 309, 2 October 2018, Pages 179-191
نویسندگان
, , , , , , ,