Segmentation of vessels in angiograms using convolutional neural networks. (February 2018)

• Record Type: Journal Article
• Authors: Nasr-Esfahani, E.; Karimi, N.; Jafari, M.H.; Soroushmehr, S.M.R.; Samavi, S.; Nallamothu, B.K.; Najarian, K.
• Is Part Of: Biomedical signal processing and control. Volume 40(2018)
• Page Start: 240
• Page End: 251
• Publication Date: 2018-02
• Subjects: Angiograms -- Vessel segmentation -- Deep learning -- Convolutional neural networks; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2017.09.012
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Proposition of a new vessel segmentation method for angiograms using deep learning. Formation of a new segmentation probability map by combination of local and global features. Achievement of higher accuracy, sensitivity, and Dice-score measures. Abstract: Coronary artery disease (CAD) is the most common type of heart disease and it is the leading cause of death in most parts of the world. About fifty percent of all middle-aged men and thirty percent of all middle-aged women in North America develop some type of CAD. The main tool for diagnosis of CAD is the X-ray angiography. Usually these images lack high quality and they contain noise. Accurate segmentation of vessels in these images could help physicians in accurate CAD diagnosis. Many image processing techniques have been used by researchers for vessel segmentation but achieving high accuracy is still a challenge in this regard. In this paper a method for detecting vessel regions in angiography images is proposed which is based on deep learning approach using convolutional neural networks (CNN). The intended angiogram is first processed to enhance the image quality. Then a patch around each pixel is fed into a trained CNN to determine whether the pixel is of vessel or background regions. Different elements of the proposed method, including the image enhancement method, the architecture of the CNN, and the training procedure of the CNN, all lead to a highly accurate mechanism. Experiments performed on angiograms of a dataset show that the proposed algorithm has a Dice score of 81.51 and an accuracy of 97.93. Results of the proposed algorithm show its superiority in extraction of vessel regions in comparison to state of the art methods.