利用加速鲁棒特征的眼底硬性渗出物转诊系统
Hard exudates referral system in eye fundus utilizing speeded up robust features.
作者信息
Naqvi Syed Ali Gohar, Zafar Hafiz Muhammad Faisal, Haq Ihsanul
机构信息
International Islamic University (IIUI), H-10, Islamabad, Pakistan.
出版信息
Int J Ophthalmol. 2017 Jul 18;10(7):1171-1174. doi: 10.18240/ijo.2017.07.24. eCollection 2017.
Abstract
In the paper a referral system to assist the medical experts in the screening/referral of diabetic retinopathy is suggested. The system has been developed by a sequential use of different existing mathematical techniques. These techniques involve speeded up robust features (SURF), K-means clustering and visual dictionaries (VD). Three databases are mixed to test the working of the system when the sources are dissimilar. When experiments were performed an area under the curve (AUC) of 0.9343 was attained. The results acquired from the system are promising.
摘要
本文提出了一种转诊系统，以协助医学专家对糖尿病性视网膜病变进行筛查/转诊。该系统是通过依次使用不同的现有数学技术开发而成的。这些技术包括加速稳健特征（SURF）、K均值聚类和视觉词典（VD）。混合使用三个数据库来测试该系统在数据源不同时的运行情况。进行实验时，获得了0.9343的曲线下面积（AUC）。从该系统获得的结果很有前景。
相似文献
1
Hard exudates referral system in eye fundus utilizing speeded up robust features.利用加速鲁棒特征的眼底硬性渗出物转诊系统
Int J Ophthalmol. 2017 Jul 18;10(7):1171-1174. doi: 10.18240/ijo.2017.07.24. eCollection 2017.
2
Referral system for hard exudates in eye fundus.眼底硬性渗出物转诊系统。
Comput Biol Med. 2015 Sep;64:217-35. doi: 10.1016/j.compbiomed.2015.07.003. Epub 2015 Jul 14.
3
Automated System for Referral of Cotton-Wool Spots.棉絮斑转诊自动化系统
Curr Diabetes Rev. 2018;14(2):168-174. doi: 10.2174/1573399812666161201114309.
4
Detection of Hard Exudates in Colour Fundus Images Using Fuzzy Support Vector Machine-Based Expert System.基于模糊支持向量机专家系统的彩色眼底图像中硬性渗出物的检测
J Digit Imaging. 2015 Dec;28(6):761-8. doi: 10.1007/s10278-015-9793-5.
5
Neonatal Fundus Image Registration and Mosaic Using Improved Speeded Up Robust Features Based on Shannon Entropy.基于香农熵的改进快速鲁棒特征的新生儿眼底图像配准与拼接。
Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:3004-3007. doi: 10.1109/EMBC46164.2021.9630593.
6
Retinal images benchmark for the detection of diabetic retinopathy and clinically significant macular edema (CSME).用于检测糖尿病视网膜病变和临床显著性黄斑水肿（CSME）的视网膜图像基准。
Biomed Tech (Berl). 2019 May 27;64(3):297-307. doi: 10.1515/bmt-2018-0098.
7
Points of interest and visual dictionaries for automatic retinal lesion detection.用于自动视网膜病变检测的兴趣点和视觉词典。
IEEE Trans Biomed Eng. 2012 Aug;59(8):2244-53. doi: 10.1109/TBME.2012.2201717. Epub 2012 May 30.
8
Tsallis entropy and sparse reconstructive dictionary learning for exudate detection in diabetic retinopathy.用于糖尿病视网膜病变中渗出物检测的Tsallis熵与稀疏重建字典学习
J Med Imaging (Bellingham). 2017 Apr;4(2):024002. doi: 10.1117/1.JMI.4.2.024002. Epub 2017 Apr 19.
9
Semi-automated quantification of hard exudates in colour fundus photographs diagnosed with diabetic retinopathy.糖尿病视网膜病变彩色眼底照片中硬性渗出物的半自动定量分析。
BMC Ophthalmol. 2017 Sep 20;17(1):172. doi: 10.1186/s12886-017-0563-7.
10
Decision support system for the detection and grading of hard exudates from color fundus photographs.眼底彩色照片中硬性渗出物的检测和分级决策支持系统。
J Biomed Opt. 2011 Nov;16(11):116001. doi: 10.1117/1.3643719.
引用本文的文献
1
Machine Vision Methods, Natural Language Processing, and Machine Learning Algorithms for Automated Dispersion Plot Analysis and Chemical Identification from Complex Mixtures.机器视觉方法、自然语言处理和机器学习算法在复杂混合物的自动散布图分析和化学识别中的应用。
Anal Chem. 2019 Aug 20;91(16):10509-10517. doi: 10.1021/acs.analchem.9b01428. Epub 2019 Jul 29.
本文引用的文献
1
Referral system for hard exudates in eye fundus.眼底硬性渗出物转诊系统。
Comput Biol Med. 2015 Sep;64:217-35. doi: 10.1016/j.compbiomed.2015.07.003. Epub 2015 Jul 14.
2
Comparison of logistic regression and neural network classifiers in the detection of hard exudates in retinal images.视网膜图像中硬性渗出物检测中逻辑回归与神经网络分类器的比较。
Annu Int Conf IEEE Eng Med Biol Soc. 2013;2013:5891-4. doi: 10.1109/EMBC.2013.6610892.
3
Automatic Exudate Detection from Non-dilated Diabetic Retinopathy Retinal Images Using Fuzzy C-means Clustering.基于模糊 C-均值聚类的非扩张性糖尿病视网膜病变视网膜图像自动渗出物检测。
Sensors (Basel). 2009;9(3):2148-61. doi: 10.3390/s90302148. Epub 2009 Mar 24.
4
A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features.基于灰度和矩不变量特征的视网膜图像血管分割新的有监督方法。
IEEE Trans Med Imaging. 2011 Jan;30(1):146-58. doi: 10.1109/TMI.2010.2064333. Epub 2010 Aug 9.
5
General retinal vessel segmentation using regularization-based multiconcavity modeling.基于正则化多凹模型的视网膜血管整体分割。
IEEE Trans Med Imaging. 2010 Jul;29(7):1369-81. doi: 10.1109/TMI.2010.2043259. Epub 2010 Mar 18.
6
Evaluation of automated fundus photograph analysis algorithms for detecting microaneurysms, haemorrhages and exudates, and of a computer-assisted diagnostic system for grading diabetic retinopathy.评价用于检测微动脉瘤、出血和渗出物的自动眼底照相分析算法，以及用于糖尿病性视网膜病变分级的计算机辅助诊断系统。
Diabetes Metab. 2010 Jun;36(3):213-20. doi: 10.1016/j.diabet.2010.01.002. Epub 2010 Mar 10.
7
A coarse-to-fine strategy for automatically detecting exudates in color eye fundus images.一种用于自动检测彩色眼底图像中渗出物的粗到精策略。
Comput Med Imaging Graph. 2010 Apr;34(3):228-35. doi: 10.1016/j.compmedimag.2009.10.001. Epub 2009 Dec 1.
8
Retinal image analysis based on mixture models to detect hard exudates.基于混合模型的视网膜图像分析以检测硬性渗出物。
Med Image Anal. 2009 Aug;13(4):650-8. doi: 10.1016/j.media.2009.05.005. Epub 2009 May 28.
9
An active contour model for segmenting and measuring retinal vessels.一种用于分割和测量视网膜血管的活动轮廓模型。
IEEE Trans Med Imaging. 2009 Sep;28(9):1488-97. doi: 10.1109/TMI.2009.2017941. Epub 2009 Mar 24.
10
Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods.使用数学形态学方法从非散瞳视网膜图像中自动检测糖尿病视网膜病变渗出物。
Comput Med Imaging Graph. 2008 Dec;32(8):720-7. doi: 10.1016/j.compmedimag.2008.08.009. Epub 2008 Oct 18.
Zotero 插件