دورية أكاديمية
أعرض في EDS

Residual-Attention UNet++: A Nested Residual-Attention U-Net for Medical Image Segmentation

التفاصيل البيبلوغرافية
العنوان: Residual-Attention UNet++: A Nested Residual-Attention U-Net for Medical Image Segmentation
المؤلفون: Zan Li, Hong Zhang, Zhengzhen Li, Zuyue Ren
المصدر: Applied Sciences, Vol 12, Iss 14, p 7149 (2022)
بيانات النشر: MDPI AG, 2022.
سنة النشر: 2022
المجموعة: LCC:Technology
LCC:Engineering (General). Civil engineering (General)
LCC:Biology (General)
LCC:Physics
LCC:Chemistry
مصطلحات موضوعية: residual unit, attention mechanism, UNet++, medical image segmentation, Technology, Engineering (General). Civil engineering (General), TA1-2040, Biology (General), QH301-705.5, Physics, QC1-999, Chemistry, QD1-999
الوصف: Image segmentation is a basic technology in the field of image processing and computer vision. Medical image segmentation is an important application field of image segmentation and plays an increasingly important role in clinical diagnosis and treatment. Deep learning has made great progress in medical image segmentation. In this paper, we proposed Residual-Attention UNet++, which is an extension of the UNet++ model with a residual unit and attention mechanism. Firstly, the residual unit improves the degradation problem. Secondly, the attention mechanism can increase the weight of the target area and suppress the background area irrelevant to the segmentation task. Three medical image datasets such as skin cancer, cell nuclei, and coronary artery in angiography were used to validate the proposed model. The results showed that the Residual-Attention UNet++ achieved superior evaluation scores with an Intersection over Union (IoU) of 82.32%, and a dice coefficient of 88.59% with the skin cancer dataset, a dice coefficient of 85.91%, and an IoU of 87.74% with the cell nuclei dataset and a dice coefficient of 72.48%, and an IoU of 66.57% with the angiography dataset.
نوع الوثيقة: article
وصف الملف: electronic resource
اللغة: English
تدمد: 2076-3417
Relation: https://www.mdpi.com/2076-3417/12/14/7149; https://doaj.org/toc/2076-3417
DOI: 10.3390/app12147149
URL الوصول: https://doaj.org/article/ab3ce6b457474e93b9404c4bb2dc35df
رقم الأكسشن: edsdoj.b3ce6b457474e93b9404c4bb2dc35df
قاعدة البيانات: Directory of Open Access Journals
الوصف
تدمد:20763417
DOI:10.3390/app12147149