Yufeng Gao1,2, Yu Song1,2, Xiangrui Yin1,2, Weiwen Wu3, Lu Zhang4, Yang Chen5,6, Wanyin Shi7. 1. Laboratory of Image Science and Technology, Southeast University, Nanjing, 210096, China. 2. Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, Nanjing, 210096, China. 3. Key Lab of Optoelectronic Technology and Systems, Ministry of Education, Chongqing University, Chongqing, 400044, China. 4. INSA de Rennes, 35000, Rennes, France. 5. Laboratory of Image Science and Technology, Southeast University, Nanjing, 210096, China. chenyang.list@seu.edu.cn. 6. Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, Nanjing, 210096, China. chenyang.list@seu.edu.cn. 7. Department of Radiology, The First Affiliated Hospital of Anhui Medical University, No. 218 Jixi Road, Hefei, 230022, China. shwy110@163.com.
Abstract
PURPOSE: Digital subtraction angiography (DSA) is a powerful technique for diagnosing cardiovascular disease. In order to avoid image artifacts caused by patient movement during imaging, we take deep learning-based methods to generate DSA image from single live image without the mask image. METHODS: Conventional clinical DSA datasets are acquired with a standard injection protocol. More than 600 sequences obtained from more than 100 subjects were used for head and leg experiments. Here, the residual dense block (RDB) is adopted to generate DSA image from single live image directly, and RDBs can extract high-level features by dense connected layers. To obtain better vessel details, a supervised generative adversarial network strategy is also used in the training stage. RESULTS: The human head and leg experiments show that the deep learning methods can generate DSA image from single live image, and our method can do better than other models. Specifically, the DSA image generating with our method contains less artifact and is suitable for diagnosis. We use metrics including PSNR, SSIM and FSIM, which can reach 23.731, 0.877 and 0.8946 on the head dataset and 26.555, 0.870 and 0.9284 on the leg dataset. CONCLUSIONS: The experiment results show the model can extract the vessels from the single live image, thus avoiding the image artifacts obtained by subtracting the live image and the mask image. And our method has a better performance than other methods we have tried on this task.
PURPOSE: Digital subtraction angiography (DSA) is a powerful technique for diagnosing cardiovascular disease. In order to avoid image artifacts caused by patient movement during imaging, we take deep learning-based methods to generate DSA image from single live image without the mask image. METHODS: Conventional clinical DSA datasets are acquired with a standard injection protocol. More than 600 sequences obtained from more than 100 subjects were used for head and leg experiments. Here, the residual dense block (RDB) is adopted to generate DSA image from single live image directly, and RDBs can extract high-level features by dense connected layers. To obtain better vessel details, a supervised generative adversarial network strategy is also used in the training stage. RESULTS: The human head and leg experiments show that the deep learning methods can generate DSA image from single live image, and our method can do better than other models. Specifically, the DSA image generating with our method contains less artifact and is suitable for diagnosis. We use metrics including PSNR, SSIM and FSIM, which can reach 23.731, 0.877 and 0.8946 on the head dataset and 26.555, 0.870 and 0.9284 on the leg dataset. CONCLUSIONS: The experiment results show the model can extract the vessels from the single live image, thus avoiding the image artifacts obtained by subtracting the live image and the mask image. And our method has a better performance than other methods we have tried on this task.
Authors: John H Hipwell; Graeme P Penney; Robert A McLaughlin; Kawal Rhode; Paul Summers; Tim C Cox; James V Byrne; J Alison Noble; David J Hawkes Journal: IEEE Trans Med Imaging Date: 2003-11 Impact factor: 10.048
Authors: Derek E Hyde; Allan J Fox; Irene Gulka; Paul Kalapos; Don H Lee; David M Pelz; David W Holdsworth Journal: Stroke Date: 2004-10-28 Impact factor: 7.914
Authors: Stefan Klein; Marius Staring; Keelin Murphy; Max A Viergever; Josien P W Pluim Journal: IEEE Trans Med Imaging Date: 2009-11-17 Impact factor: 10.048
Authors: Geert Litjens; Thijs Kooi; Babak Ehteshami Bejnordi; Arnaud Arindra Adiyoso Setio; Francesco Ciompi; Mohsen Ghafoorian; Jeroen A W M van der Laak; Bram van Ginneken; Clara I Sánchez Journal: Med Image Anal Date: 2017-07-26 Impact factor: 8.545
Authors: Dong Nie; Roger Trullo; Jun Lian; Li Wang; Caroline Petitjean; Su Ruan; Qian Wang; Dinggang Shen Journal: IEEE Trans Biomed Eng Date: 2018-03-09 Impact factor: 4.538