Yin Xie
Shibiao Xu
ABSTRACT
Retinal image vessel segmentation or artery/vein segmentation tasks have been investigated for a long time, and hypertension prediction based on statistical data or body indicators has been learned well. However, the gap between retinal image segmentation and retinal image hypertension prediction still exists. In this paper, we bridge the gap by introducing a model-agnostic cross attention module in segmentation part and a semantic image fusion module in hypertension prediction part thus to form a novel segmentation-based pipeline for hypertension prediction. Specifically, the cross attention module adopts cross multiplication to attend encoder and decoder features, which enhances the artery/vein segmentation ability in uncertain region and border region in retinal image. Then we design a semantic image fusion module to fuse segmented artery/vein vessel image and original image as the classifier input to predict hypertension. The experimental results demonstrate that our model can efficiently predict hypertension, and we achieve 94.87% accuracy, 94.74% specificity, 95.00% sensitivity respectively on 393 retinal images from Kaggle ODiR5k dataset at : https://www.kaggle.com/ocular-disease-recognition-odir5k.
- Arun, Govindaiah, Roland, Theodore, Smith, Alauddin, and Bhuiyan. 2018. A New and Improved Method for Automated Screening of Age-Related Macular Degeneration Using Ensemble Deep Neural Networks.Conference proceedings: IEEE Engineering in Medicine and Biology Society. Annual Conference (2018).Google Scholar
- Erkang Cheng, Liang Du, Yi Wu, Ying J. Zhu, Vasileios Megalooikonomou, and Haibin Ling. 2014. Discriminative vessel segmentation in retinal images by fusing context-aware hybrid features. Machine Vision and Applications(2014).Google Scholar
- C. Y. Cheung, T. T. Wan, P. Mitchell, J. W. Jie, and Tien Y Wong. 2011. Quantitative and qualitative retinal microvascular characteristics and blood pressure. Journal of Hypertension 29, 7 (2011), 1380.Google ScholarCross Ref
- Copetti, Dario, Zhang, Jianwei, El Baidouri, Moaine, Gao, Dongying, Wang, and Jun. 2015. RiTE database: a resource database for genus-wide rice genomics and evolutionary biology. BMC Genomics (2015).Google Scholar
- Guangzheng Dai, Wei He, Ling Xu, Eric E. Pazo, and Chenguang Zhang. 2020. Exploring the effect of hypertension on retinal microvasculature using deep learning on East Asian population. PLoS ONE (2020).Google Scholar
- Siying Dai, Leiting Chen, Ting Lei, Chuan Zhou, and Yang Wen. 2020. Automatic Detection Of Pathological Myopia And High Myopia On Fundus Images. In 2020 IEEE International Conference on Multimedia and Expo (ICME).Google Scholar
- Behdad Dashtbozorg, Ana Maria Mendonca, and Aurelio Campilho. 2014. An Automatic Graph-Based Approach for Artery/Vein Classification in Retinal Images. IEEE Transactions on Image Processing(2014).Google ScholarDigital Library
- Jia Deng, Wei Dong, Richard Socher, Li Jia Li, and Fei Fei Li. 2009. ImageNet: A large-scale hierarchical image database. In IEEE Conference on Computer Vision and Pattern Recognition.Google ScholarCross Ref
- Rolando Estrada, Michael Allingham, Priyatham Mettu, Scott Cousins, Carlo Tomasi, and Sina Farsiu. 2015. Retinal Artery-Vein Classification via Topology Estimation. IEEE Transactions on Medical Imaging(2015).Google Scholar
- López-Martínez Fernando, Schwarcz. Aron, Nú?ez-Valdez Edward Rolando, and García-Díaz Vicente. 2018. Machine Learning Classification Analysis for a Hypertensive Population as a Function of Several Risk Factors. Expert Systems with Applications(2018).Google Scholar
- Adrian Galdran, M. Meyer, P. Costa, MendonCa, and A. Campilho. 2019. Uncertainty-Aware Artery/Vein Classification on Retinal Images. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI).Google Scholar
- B. Gopinath, J. J. Wang, A. Kifley, A. G. Tan, T. Y. Wong, and P. Mitchell. 2013. Influence of blood pressure and body mass index on retinal vascular caliber in preschool-aged children. Journal of Human Hypertension 27, 9 (2013), 523–528.Google ScholarCross Ref
- Zaiwang Gu, Jun Cheng, Huazhu Fu, Kang Zhou, Huaying Hao, Yitian Zhao, Tianyang Zhang, Shenghua Gao, and Jiang Liu. 2019. CE-Net: Context Encoder Network for 2D Medical Image Segmentation. IEEE Transactions on Medical Imaging(2019).Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google ScholarCross Ref
- L. D. Hubbard, R. J. Brothers, W. N. King, L. X. Clegg, R. Klein, L. S. Cooper, A. R. Sharrett, MD Davis, and J. Cai. 1999. Methods for evaluation of retinal microvascular abnormalities associated with hypertension/sclerosis in the Atherosclerosis Risk in Communities Study.Ophthalmology 106, 12 (1999), 2269–2280.Google Scholar
- Jessica Y. Islam, Zaman M. Mostafa, Haq Syed Atiqul, Ahmed Shamim, and Al Quadir Zahid. 2018. Epidemiology of hypertension among Bangladeshi adults using the 2017 ACC/AHA Hypertension Clinical Practice Guidelines and Joint National Committee 7 Guidelines. Journal of Human Hypertension(2018).Google Scholar
- Liangzhi Li, Manisha Verma, Yuta Nakashima, Ryo Kawasaki, and Hajime Nagahara. 2020. Joint Learning of Vessel Segmentation and Artery/Vein Classification with Post-processing. (2020).Google Scholar
- L. Li, M. Verma, Y. Nakashima, H. Nagahara, and R. Kawasaki. 2020. IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks. In 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).Google Scholar
- Xiaomeng Li, Xiaowei Hu, Lequan Yu, Lei Zhu, Chi Wing Fu, and Pheng Ann Heng. 2019. CANet: Cross-disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading. (2019).Google Scholar
- Y. Luo, Y. Li, Y. Lu, S. Lin, and X. Liu. 2018. The Prediction of Hypertension Based on Convolution Neural Network. In 2018 IEEE 4th International Conference on Computer and Communications (ICCC).Google Scholar
- F Milletari, N. Navab, and S. A. Ahmadi. 2016. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. In 2016 Fourth International Conference on 3D Vision (3DV).Google Scholar
- M. Niemeijer, X. Xu, A. V. Dumitrescu, P. Gupta, B. Van Ginneken, J. C. Folk, and MD Abramoff. 2011. Automated Measurement of the Arteriolar-to-Venular Width Ratio in Digital Color Fundus Photographs. IEEE Transactions on Medical Imaging(2011).Google ScholarCross Ref
- I. Parikh Nisha, J. Pencina Michael, J. Wang Thomas, and J. Benjamin Emelia. 2008. A Risk Score for Predicting Near-Term Incidence of Hypertension: The Framingham Heart Study. Annals of Internal Medicine 148, 2 (2008), 102–110.Google ScholarCross Ref
- Ozan Oktay, Jo Schlemper, Loic Le Folgoc, Matthew Lee, Mattias Heinrich, Kazunari Misawa, Kensaku Mori, Steven Mcdonagh, Nils Y Hammerla, and Bernhard and Kainz. 2018. Attention U-Net: Learning Where to Look for the Pancreas. (2018).Google Scholar
- José Ignacio Orlando, Joo Barbosa Breda, Karel Van Keer, Matthew B. Blaschko, Pablo J. Blanco, and Carlos A. Bulant. 2018. Towards a glaucoma risk index based on simulated hemodynamics from fundus images.Google Scholar
- Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. (2015).Google Scholar
- Sohini Roychowdhury, Dara D Koozekanani, and Keshab K Parhi. 2015. Iterative Vessel Segmentation of Fundus Images. IEEE Transactions on Biomedical Engineering(2015).Google ScholarCross Ref
- Frank M. Sacks, Laura P. Svetkey, William M. Vollmer, Lawrence J. Appel, and P H Lin. 2001. Effects on blood pressure of reduced dietary sodium and the Dietary Approaches to Stop Hypertension (DASH) diet. DASH-Sodium Collaborative Research Group. New England Journal of Medicine(2001).Google ScholarCross Ref
- S. Sherif, E. Radwa, A. Amjad, W. T. Qureshi, B. Clinton, K. Steven, M. J. Blaha, M. H. Al-Mallah, and X. Li. 2018. Using machine learning on cardiorespiratory fitness data for predicting hypertension: The Henry Ford ExercIse Testing (FIT) Project. PLoS ONE 13, 4 (2018), e0195344.Google Scholar
- W. Smith, J. J. Wang, T. Y. Wong, E. Rochtchina, R. Klein, S. R. Leeder, and P. Mitchell. 2004. Retinal arteriolar narrowing is associated with 5-year incident severe hypertension: the Blue Mountains Eye Study.Hypertension 44, 4 (2004), 442–447.Google Scholar
- Y. Tanabe, R. Kawasaki, J. J. Wang, T. Y. Wong, P. Mitchell, M. Daimon, T. Oizumi, T. Kato, S. Kawata, and T. Kayama. 2010. Retinal Arteriolar Narrowing Predicts 5-Year Risk of Hypertension in Japanese People: The Funagata Study. Microcirculation (2010).Google Scholar
- Mevlut Ture, Imran Kurt, A. Turhan Kurum, and Kazim Ozdamar. 2005. Comparing classification techniques for predicting essential hypertension. Expert Systems with Applications An International Journal (2005).Google Scholar
- Jie Jin Wang, Elena Rochtchina, Gerald Liew, Ava G. Tan, Tien Yin Wong, Stephen R. Leeder, Wayne Smith, Anoop Shankar, and Paul Mitchell. 2008. The long-term relation among retinal arteriolar narrowing, blood pressure, and incident severe hypertension.American Journal of Epidemiology 168, 1 (2008), 80–88.Google Scholar
- H. W. Xie and L. L. Lin. 2012. Research on Extracting Classification Rules for Hypertension with C4.5 Algorithm. Computer Development & Applications(2012).Google Scholar
- Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, and Kaiming He. 2017. Aggregated Residual Transformations for Deep Neural Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google ScholarCross Ref
- J. Zhang, B. Dashtbozorg, E. Bekkers, J. P. W. Pluim, R. Duits, and B. M. ter Haar Romeny. 2016. Robust Retinal Vessel Segmentation via Locally Adaptive Derivative Frames in Orientation Scores. IEEE Transactions on Medical Imaging(2016).Google Scholar
- Shihao Zhang, Huazhu Fu, Yuguang Yan, Yubing Zhang, Qingyao Wu, Ming Yang, Mingkui Tan, and Yanwu Xu. 2019. Attention Guided Network for Retinal Image Segmentation. (2019).Google Scholar
- Huanhuan Zhao, Zuchang Ma, and Yining Sun. 2019. A Hypertension Risk Prediction Model Based on BP Neural Network. In 2019 International Conference on Networking and Network Applications (NaNA).Google ScholarCross Ref
- Yitian Zhao, Jianyang Xie, Pan Su, Yalin Zheng, and Jiang Liu. 2018. Retinal Artery and Vein Classification via Dominant Sets Clustering-Based Vascular Topology Estimation. (2018).Google Scholar
- Jianwei Zhou, Liu Fang, and Renjian Huang. 2012. Status quo of quality of life of empty-nesters with hypertension and analysis on its influencing factors in Yueyang Region. Chinese Nursing Research(2012).Google Scholar
Recommendations
Retinal Vessel Segmentation of Non-Proliferative Diabetic Retinopathy
Diabetic retinopathy is a disease in diabetic patients that affects the eye. It happens due to damage in the blood vessels of the light-sensitive tissues at the retina. In non-proliferative diabetic retinopathy, tiny changes occur in the blood vessels ...
Artery vein classification in fundus images using serially connected U-Nets
Highlights- Retinal vessels can provide valuable information on the retina and other organ systems.
AbstractBackground and objective: Retinal vessels provide valuable information when diagnosing or monitoring various diseases affecting the retina and disorders affecting the cardiovascular or central nervous systems. Automated ...
Comments