1
|
Liu J, Wang J, Wu J, Gu S, Yao Y, Li J, Li Y, Ren H, Luo T. Comparison of two computed tomography perfusion post-processing software to assess infarct volume in patients with acute ischemic stroke. Front Neurosci 2023; 17:1151823. [PMID: 37179549 PMCID: PMC10166848 DOI: 10.3389/fnins.2023.1151823] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2023] [Accepted: 04/07/2023] [Indexed: 05/15/2023] Open
Abstract
Objectives We used two automated software commonly employed in clinical practice-Olea Sphere (Olea) and Shukun-PerfusionGo (PerfusionGo)-to compare the diagnostic utility and volumetric agreement of computed tomography perfusion (CTP)-predicted final infarct volume (FIV) with true FIV in patients with anterior-circulation acute ischemic stroke (AIS). Methods In all, 122 patients with anterior-circulation AIS who met the inclusion and exclusion criteria were retrospectively enrolled and divided into two groups: intervention group (n = 52) and conservative group (n = 70), according to recanalization of blood vessels and clinical outcome (NIHSS) after different treatments. Patients in both groups underwent one-stop 4D-CT angiography (CTA)/CTP, and the raw CTP data were processed on a workstation using Olea and PerfusionGo post-processing software, to calculate and obtain the ischemic core (IC) and hypoperfusion (IC plus penumbra) volumes, hypoperfusion in the conservative group and IC in the intervention group were used to define the predicted FIV. The ITK-SNAP software was used to manually outline and measure true FIV on the follow-up non-enhanced CT or MRI-DWI images. Intraclass correlation coefficients (ICC), Bland-Altman, and Kappa analysis were used to compare the differences in IC and penumbra volumes calculated by the Olea and PerfusionGo software to investigate the relationship between their predicted FIV and true FIV. Results The IC and penumbra difference between Olea and PerfusionGo within the same group (p < 0.001) was statistically significant. Olea obtained larger IC and smaller penumbra than PerfusionGo. Both software partially overestimated the infarct volume, but Olea significantly overestimated it by a larger percentage. ICC analysis showed that Olea performed better than PerfusionGo (intervention-Olea: ICC 0.633, 95%CI 0.439-0.771; intervention-PerfusionGo: ICC 0.526, 95%CI 0.299-0.696; conservative-Olea: ICC 0.623, 95%CI 0.457-0.747; conservative-PerfusionGo: ICC 0.507, 95%CI 0.312-0.662). Olea and PerfusionGo had the same capacity in accurately diagnosing and classifying patients with infarct volume <70 ml. Conclusion Both software had differences in the evaluation of the IC and penumbra. Olea's predicted FIV was more closely correlated with the true FIV than PerfusionGo's prediction. Accurate assessment of infarction on CTP post-processing software remains challenging. Our results may have important practice implications for the clinical use of perfusion post-processing software.
Collapse
Affiliation(s)
- Jiayang Liu
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Jingjie Wang
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Jiajing Wu
- Department of Radiology, Hospital of PLA Army, Chongqing, China
| | - Sirun Gu
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Yunzhuo Yao
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Jing Li
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Yongmei Li
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Huanhuan Ren
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
- Department of Radiology, Chongqing General Hospital, Chongqing, China
| | - Tianyou Luo
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| |
Collapse
|
2
|
Predicting a Favorable (mRS 0-2) or Unfavorable (mRS 3-6) Stroke Outcome by Arterial Spin Labeling and Amide Proton Transfer Imaging in Post-Thrombolysis Stroke Patients. J Pers Med 2023; 13:jpm13020248. [PMID: 36836482 PMCID: PMC9962289 DOI: 10.3390/jpm13020248] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2022] [Revised: 01/26/2023] [Accepted: 01/28/2023] [Indexed: 01/31/2023] Open
Abstract
(1) Background: The objective of this study was to determine whether arterial spin labeling (ASL), amide proton transfer (APT), or their combination could distinguish between patients with a low and high modified Rankin Scale (mRS) and forecast the effectiveness of the therapy; (2) Methods: Fifty-eight patients with subacute phase ischemic stroke were included in this study. Based on cerebral blood flow (CBF) and asymmetry magnetic transfer ratio (MTRasym) images, histogram analysis was performed on the ischemic area to acquire imaging biomarkers, and the contralateral area was used as a control. Imaging biomarkers were compared between the low (mRS 0-2) and high (mRS 3-6) mRS score groups using the Mann-Whitney U test. Receiver operating characteristic (ROC) curve analysis was used to evaluate the performance of the potential biomarkers in differentiating between the two groups; (3) Results: The rAPT 50th had an area under the ROC curve (AUC) of 0.728, with a sensitivity of 91.67% and a specificity of 61.76% for differentiating between patients with low and high mRS scores. Moreover, the AUC, sensitivity, and specificity of the rASL max were 0.926, 100%, and 82.4%, respectively. Combining the parameters with logistic regression could further improve the performance in predicting prognosis, leading to an AUC of 0.968, a sensitivity of 100%, and a specificity of 91.2%; (4) Conclusions: The combination of APT and ASL may be a potential imaging biomarker to reflect the effectiveness of thrombolytic therapy for stroke patients, assisting in guiding treatment approaches and identifying high-risk patients such as those with severe disability, paralysis, and cognitive impairment.
Collapse
|
3
|
Liu QC, Jia ZY, Zhao LB, Cao YZ, Ma G, Shi HB, Liu S. Agreement and Accuracy of Ischemic Core Volume Evaluated by Three CT Perfusion Software Packages in Acute Ischemic Stroke. J Stroke Cerebrovasc Dis 2021; 30:105872. [PMID: 34153591 DOI: 10.1016/j.jstrokecerebrovasdis.2021.105872] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/03/2020] [Revised: 04/26/2021] [Accepted: 05/02/2021] [Indexed: 10/21/2022] Open
Abstract
PURPOSE To compare the ischemic core volume estimated by CT Perfusion 4D and Vue PACS with that estimated by RAPID software in acute ischemic stroke (AIS). MATERIALS AND METHODS CT perfusion data from AIS patients were retrospectively post-processed with RAPID, CT Perfusion 4D and Vue PACS software. The Vue PACS application included three different settings: method A (Circular Singular Value Decomposition), method B (Oscillating index Singular Value Decomposition) and method C (Standard Singular Value Decomposition). Bland-Altman analysis, intraclass correlation coefficients (ICCs) and Kappa analysis were used to evaluate concordance between estimated ischemic core values. Final infarct volume (FIV) was measured by follow-up non-contrast CT or MRI 5-7 days after mechanical thrombectomy (MT) in patients with successful recanalization. RESULTS A total of 82 patients were included in the study. Concordance with RAPID ranged from good (method B: ICC 0.780; method C: ICC 0.852) to excellent (CT perfusion 4D: ICC 0.950; method A: ICC 0.954). The limits of agreement (-32.3, 41.8 mL) were the narrowest with method A. For detecting core volumes ≤ 70 ml, method A and CT perfusion 4D showed almost perfect concordance with RAPID (CT perfusion 4D, kappa=0.87; method A, kappa=0.87), whereas methods B and C showed substantial concordance with RAPID (method B, kappa=0.77; method C, kappa =0.73). Thirty-two patients had good reperfusion after MT. RAPID showed the highest accuracy for predicting FIV, followed by method A. CONCLUSION CT perfusion 4D and Vue PACS method A showed excellent concordance with RAPID for quantifying ischemic core volume, which can be considered as alternatives in selecting patients for MT in clinical practice.
Collapse
Affiliation(s)
- Qin Chen Liu
- Department of Interventional Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Zhen Yu Jia
- Department of Interventional Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Lin Bo Zhao
- Department of Interventional Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Yue Zhou Cao
- Department of Interventional Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Gao Ma
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Hai Bin Shi
- Department of Interventional Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Sheng Liu
- Department of Interventional Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
| |
Collapse
|
4
|
Shafaat O, Bernstock JD, Shafaat A, Yedavalli VS, Elsayed G, Gupta S, Sotoudeh E, Sair HI, Yousem DM, Sotoudeh H. Leveraging artificial intelligence in ischemic stroke imaging. J Neuroradiol 2021; 49:343-351. [PMID: 33984377 DOI: 10.1016/j.neurad.2021.05.001] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2021] [Revised: 05/02/2021] [Accepted: 05/03/2021] [Indexed: 11/30/2022]
Abstract
Artificial intelligence (AI) is having a disruptive and transformative effect on clinical medicine. Prompt clinical diagnosis and imaging are critical for minimizing the morbidity and mortality associated with ischemic strokes. Clinicians must understand the current strengths and limitations of AI to provide optimal patient care. Ischemic stroke is one of the medical fields that have been extensively evaluated by artificial intelligence. Presented herein is a review of artificial intelligence applied to clinical management of stroke, geared toward clinicians. In this review, we explain the basic concept of AI and machine learning. This review is without coding and mathematical details and targets the clinicians involved in stroke management without any computer or mathematics' background. Here the AI application in ischemic stroke is summarized and classified into stroke imaging (automated diagnosis of brain infarction, automated ASPECT score calculation, infarction segmentation), prognosis prediction, and patients' selection for treatment.
Collapse
Affiliation(s)
- Omid Shafaat
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 1800 Orleans St, Baltimore, MD 21287, USA.
| | - Joshua D Bernstock
- Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Hale Building, 60 Fenwood Road, Boston, MA 02115, USA.
| | - Amir Shafaat
- Department of Mechanical Engineering, Arak University of Technology, Daneshgah St, 38181-41167 Arak, Iran.
| | - Vivek S Yedavalli
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 1800 Orleans St, Baltimore, MD 21287, USA.
| | - Galal Elsayed
- Department of Neurosurgery, University of Alabama at Birmingham, 1960 6th Ave. S., Birmingham, AL 35233, USA.
| | - Saksham Gupta
- Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Hale Building, 60 Fenwood Road, Boston, MA 02115, USA.
| | - Ehsan Sotoudeh
- Department of Surgery, Iranian Hospital in Dubai, P.O.BOX: 2330, Al-Wasl Road, Dubai 2330, UAE.
| | - Haris I Sair
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 1800 Orleans St, Baltimore, MD 21287, USA; Radiology Artificial Intelligence Lab (RAIL), Malone Center for Engineering in Healthcare, Johns Hopkins University Whiting School of Engineering, 600 North Wolfe Street, Baltimore, MD 21287, USA.
| | - David M Yousem
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 1800 Orleans St, Baltimore, MD 21287, USA.
| | - Houman Sotoudeh
- Department of Radiology, University of Alabama at Birmingham, 619 19th St S, Birmingham, AL 35294, USA.
| |
Collapse
|
5
|
Benali A, Moynier M, Dargazanli C, Deverdun J, Cagnazzo F, Mourand I, Bonafe A, Arquizan C, Derraz I, Menjot de Champfleur N, Molino F, Ducros A, Le Bars E, Costalat V. Mechanical Thrombectomy in Nighttime Hours: Is There a Difference in 90-Day Clinical Outcome for Patients with Ischemic Stroke? AJNR Am J Neuroradiol 2021; 42:530-537. [PMID: 33478943 DOI: 10.3174/ajnr.a6997] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2020] [Accepted: 10/05/2020] [Indexed: 11/07/2022]
Abstract
BACKGROUND AND PURPOSE Few data are available regarding the influence of the timing of ischemic stroke management, such as daytime and nighttime hours, on the delay of mechanical thrombectomy, the effectiveness of revascularization, and clinical outcomes. We aimed to investigate whether admission during nighttime hours could impact the clinical outcome (mRS at 90 days) of patients with acute ischemic stroke treated by mechanical thrombectomy. MATERIALS AND METHODS We retrospectively analyzed 169 patients (112 treated during daytime hours and 57 treated during nighttime hours) with acute ischemic stroke in the anterior cerebral circulation. The main outcome was the rate of patients achieving functional independence at 90 days (mRS ≤2), depending on admission time. RESULTS In patients admitted during nighttime hours, the rate of mRS ≤ 2 at 90 days was significantly higher (51% versus 35%, P = .05) compared with those admitted in daytime hours. Patients in daytime and nighttime hours were comparable regarding admission and treatment characteristics. However, patients in nighttime hours tended to have a higher median NIHSS score at admission (P = .08) and to be younger (P = .08), especially among the mothership group (P = .09). The multivariate logistic regression analysis confirmed that patients in nighttime hours had better functional outcomes at 90 days than those in daytime hours (P = .018; 95% CI, 0.064-0.770; OR = 0.221). CONCLUSIONS In a highly organized stroke care network, mechanical thrombectomy is quite effective in the nighttime hours among acute ischemic stroke presentations. Unexpectedly, we found that those patients achieved favorable clinical outcomes more frequently than those treated during daytime hours. Larger series are needed to confirm these results.
Collapse
Affiliation(s)
- A Benali
- From the Departments of Neuroradiology (A.B., M.M., C.D., J.D., F.C., A.B., I.D., N.M.d.C., E.L.B., V.C.)
| | - M Moynier
- From the Departments of Neuroradiology (A.B., M.M., C.D., J.D., F.C., A.B., I.D., N.M.d.C., E.L.B., V.C.)
| | - C Dargazanli
- From the Departments of Neuroradiology (A.B., M.M., C.D., J.D., F.C., A.B., I.D., N.M.d.C., E.L.B., V.C.)
| | - J Deverdun
- From the Departments of Neuroradiology (A.B., M.M., C.D., J.D., F.C., A.B., I.D., N.M.d.C., E.L.B., V.C.)
| | - F Cagnazzo
- From the Departments of Neuroradiology (A.B., M.M., C.D., J.D., F.C., A.B., I.D., N.M.d.C., E.L.B., V.C.)
| | - I Mourand
- Neurology (I.M., C.A., A.D.), Gui de Chauliac Hospital, Montpellier, France
| | - A Bonafe
- From the Departments of Neuroradiology (A.B., M.M., C.D., J.D., F.C., A.B., I.D., N.M.d.C., E.L.B., V.C.)
| | - C Arquizan
- Neurology (I.M., C.A., A.D.), Gui de Chauliac Hospital, Montpellier, France
| | - I Derraz
- From the Departments of Neuroradiology (A.B., M.M., C.D., J.D., F.C., A.B., I.D., N.M.d.C., E.L.B., V.C.)
| | - N Menjot de Champfleur
- From the Departments of Neuroradiology (A.B., M.M., C.D., J.D., F.C., A.B., I.D., N.M.d.C., E.L.B., V.C.)
| | - F Molino
- Department of Physics (F.M.), Charles Coulomb Laboratory, Montpellier, France
| | - A Ducros
- Neurology (I.M., C.A., A.D.), Gui de Chauliac Hospital, Montpellier, France
| | - E Le Bars
- From the Departments of Neuroradiology (A.B., M.M., C.D., J.D., F.C., A.B., I.D., N.M.d.C., E.L.B., V.C.)
| | - V Costalat
- From the Departments of Neuroradiology (A.B., M.M., C.D., J.D., F.C., A.B., I.D., N.M.d.C., E.L.B., V.C.)
| |
Collapse
|