Minh Nguyen Nhat To1, Hyun Jeong Kim2, Hong Gee Roh3, Yoon-Sik Cho4, Jin Tae Kwak5. 1. Department of Computer Science and Engineering, Sejong University, Seoul, 05006, South Korea. 2. Daejeon St. Mary's Hospital, Catholic University, Daejeon, 34943, South Korea. 3. Konkuk University Medical Center, Seoul, 05029, South Korea. 4. Department of Data Science, Sejong University, Seoul, 05006, South Korea. 5. Department of Computer Science and Engineering, Sejong University, Seoul, 05006, South Korea. jkwak@sejong.ac.kr.
Abstract
PURPOSE: Acute ischemic stroke is one of the primary causes of death worldwide. Recent studies have shown that the assessment of collateral status could aid in improving the treatment for patients with acute ischemic stroke. We present a 3D deep regression neural network to automatically generate the collateral images from dynamic susceptibility contrast-enhanced magnetic resonance perfusion (DSC-MRP) in acute ischemic stroke. METHODS: This retrospective study includes 144 subjects with acute ischemic stroke (stroke cases) and 201 subjects without acute ischemic stroke (controls). DSC-MRP images of these subjects were manually inspected for collateral assessment in arterial, capillary, early and late venous, and delay phases. The proposed network was trained on 205 subjects, and the optimal model was chosen using the validation set of 64 subjects. The predictive power of the network was assessed on the test set of 76 subjects using the squared correlation coefficient (R-squared), mean absolute error (MAE), Tanimoto measure (TM), and structural similarity index (SSIM). RESULTS: The proposed network was able to predict the five phase maps with high accuracy. On average, 0.897 R-squared, 0.581 × 10-1 MAE, 0.946 TM, and 0.846 SSIM were achieved for the five phase maps. No statistically significant difference was, in general, found between controls and stroke cases. The performance of the proposed network was lower in the arterial and venous phases than the other three phases. CONCLUSION: The results suggested that the proposed network performs equally well for both control and acute ischemic stroke groups. The proposed network could help automate the assessment of collateral status in an efficient and effective manner and improve the quality and yield of diagnosis of acute ischemic stroke. The follow-up study will entail the clinical evaluation of the collateral images that are generated by the proposed network.
PURPOSE:Acute ischemic stroke is one of the primary causes of death worldwide. Recent studies have shown that the assessment of collateral status could aid in improving the treatment for patients with acute ischemic stroke. We present a 3D deep regression neural network to automatically generate the collateral images from dynamic susceptibility contrast-enhanced magnetic resonance perfusion (DSC-MRP) in acute ischemic stroke. METHODS: This retrospective study includes 144 subjects with acute ischemic stroke (stroke cases) and 201 subjects without acute ischemic stroke (controls). DSC-MRP images of these subjects were manually inspected for collateral assessment in arterial, capillary, early and late venous, and delay phases. The proposed network was trained on 205 subjects, and the optimal model was chosen using the validation set of 64 subjects. The predictive power of the network was assessed on the test set of 76 subjects using the squared correlation coefficient (R-squared), mean absolute error (MAE), Tanimoto measure (TM), and structural similarity index (SSIM). RESULTS: The proposed network was able to predict the five phase maps with high accuracy. On average, 0.897 R-squared, 0.581 × 10-1 MAE, 0.946 TM, and 0.846 SSIM were achieved for the five phase maps. No statistically significant difference was, in general, found between controls and stroke cases. The performance of the proposed network was lower in the arterial and venous phases than the other three phases. CONCLUSION: The results suggested that the proposed network performs equally well for both control and acute ischemic stroke groups. The proposed network could help automate the assessment of collateral status in an efficient and effective manner and improve the quality and yield of diagnosis of acute ischemic stroke. The follow-up study will entail the clinical evaluation of the collateral images that are generated by the proposed network.
Entities:
Keywords:
Acute ischemic stroke; Collateral phase maps; Deep learning; Encoder–decoder; Magnetic resonance imaging
Authors: Yabo Fu; Thomas R Mazur; Xue Wu; Shi Liu; Xiao Chang; Yonggang Lu; H Harold Li; Hyun Kim; Michael C Roach; Lauren Henke; Deshan Yang Journal: Med Phys Date: 2018-10-28 Impact factor: 4.071
Authors: Mayank Goyal; Andrew M Demchuk; Bijoy K Menon; Muneer Eesa; Jeremy L Rempel; John Thornton; Daniel Roy; Tudor G Jovin; Robert A Willinsky; Biggya L Sapkota; Dar Dowlatshahi; Donald F Frei; Noreen R Kamal; Walter J Montanera; Alexandre Y Poppe; Karla J Ryckborst; Frank L Silver; Ashfaq Shuaib; Donatella Tampieri; David Williams; Oh Young Bang; Blaise W Baxter; Paul A Burns; Hana Choe; Ji-Hoe Heo; Christine A Holmstedt; Brian Jankowitz; Michael Kelly; Guillermo Linares; Jennifer L Mandzia; Jai Shankar; Sung-Il Sohn; Richard H Swartz; Philip A Barber; Shelagh B Coutts; Eric E Smith; William F Morrish; Alain Weill; Suresh Subramaniam; Alim P Mitha; John H Wong; Mark W Lowerison; Tolulope T Sajobi; Michael D Hill Journal: N Engl J Med Date: 2015-02-11 Impact factor: 91.245
Authors: Adriano Pinto; Richard Mckinley; Victor Alves; Roland Wiest; Carlos A Silva; Mauricio Reyes Journal: Front Neurol Date: 2018-12-05 Impact factor: 4.003
Authors: Christian Lucas; André Kemmling; Nassim Bouteldja; Linda F Aulmann; Amir Madany Mamlouk; Mattias P Heinrich Journal: Front Neurol Date: 2018-11-26 Impact factor: 4.003
Authors: Yoon-Chul Kim; Jong-Won Chung; Oh Young Bang; Mihee Hong; Woo-Keun Seo; Gyeong-Moon Kim; Eung Yeop Kim; Jin Soo Lee; Ji Man Hong; David S Liebeskind; Jeffrey L Saver Journal: Transl Stroke Res Date: 2022-05-21 Impact factor: 6.829