1
|
Kerleroux B, Hak JF, Lapergue B, Bricout N, Zhu F, Inoue M, Janot K, Dargazanli C, Kaesmacher J, Rouchaud A, Forestier G, Gortais H, Benzakoun J, Yoshimoto T, Consoli A, Ben Hassen W, Henon H, Naggara O, Boulouis G. Endovascular therapy in patients with a large ischemic volume at presentation: An aggregate patient-level analysis. Clin Neurol Neurosurg 2024; 244:108452. [PMID: 39059286 DOI: 10.1016/j.clineuro.2024.108452] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2024] [Revised: 07/03/2024] [Accepted: 07/12/2024] [Indexed: 07/28/2024]
Abstract
INTRODUCTION Recently, four randomized controlled trials (RCTs) have demonstrated the benefits of mechanical thrombectomy (MT) in patients with acute ischemic stroke (AIS) caused by anterior large vessel occlusion (LVO) and a large ischemic core at baseline (LIC). The purpose of this study was to investigate the features influencing the clinical outcome and the benefits of mechanical thrombectomy in this subgroup. METHODS We conducted a multicenter retrospective aggregate cohort study of patients with AIS-LVO and a LIC, assessed with quantitative core volume measures, treated with MT between 2012 and 2019. The data were queried through four registries, including patients with core volumes ≥50cc. Multivariable logistic regression models were employed to determine factors independently associated with clinical outcomes in patients with successful recanalization (modified-Thrombolysis-in-Cerebral-Infarction-score, mTICI=2b-3) and unsuccessful recanalization group (mTICI=0-2a). The primary endpoint was a favorable functional outcome at day-90, defined as a modified Rankin scale (mRS) of 0-3, accounting for the inherent severity of AIS with baseline LIC. Secondary outcomes included functional independence (mRS 0-2) at day-90, mortality, and symptomatic Intracranial Hemorrhage (sICH). RESULTS A total of 460 patients were included (mean age 66±14.2 years; 39.6 % females). The mean baseline NIHSS was 20±5.2, and the core volume was 103.2±54.6 ml. Overall, 39.8 % (183/460) of patients achieved a favorable outcome at day-90 (mRS 0-3). Successful recanalization was significantly associated with a more frequent favorable outcome (aOR, 4.79; 95 %CI, 2.73-8.38; P<0.01) and functional independence (P<0.01). This benefit remained significant in older patients and in patients with cores above 100cc. At 90 days, 147/460 patients (32 %) were deceased, with successful recanalization significantly associated with less frequent mortality (OR, 0.34; 95 %CI, 0.22-0.53; P<0.01). The rate of sICH was 17.4 % and did not differ significantly between groups. CONCLUSIONS In this large, pooled-cohort study of AIS-LVO patients with infarct cores over 50cc at baseline, we demonstrated that successful recanalization was associated with a better functional outcome, lower mortality, and similar rates of symptomatic intracranial hemorrhage for a wide spectrum of patients.
Collapse
Affiliation(s)
- Basile Kerleroux
- Department of Neuroradiology, CHU Marseille La Timone, Marseille, France.
| | - Jean François Hak
- Department of Neuroradiology, CHU Marseille La Timone, Marseille, France
| | | | - Nicolas Bricout
- Diagnostic and Interventional Neuroradiology, CHRU Lille, Lille, France
| | - François Zhu
- University Hospital of Nancy, Department of Diagnostic and Therapeutic Neuroradiology, INSERM U1254, IADI, Nancy F-54000, France
| | - Manabu Inoue
- Department of Cerebrovascular Medicine National Cerebral and Cardiovascular Center Suita Japan
| | - Kevin Janot
- Department of Neuroradiology, CHRU Tours, Tours, France
| | - Cyril Dargazanli
- Neuroradiology Department, CHRU Gui de Chauliac, Montpellier, France
| | - Johannes Kaesmacher
- Institute of Diagnostic, Interventional and Pediatric Radiology and Institute of Diagnostic and Interventional Neuroradiology, University Hospital Bern, Inselspital, University of Bern, Bern, Switzerland
| | - Aymeric Rouchaud
- Neuroradiology department, Dupuytren, University Hospital of Limoges, France
| | - Géraud Forestier
- Neuroradiology department, Dupuytren, University Hospital of Limoges, France
| | - Hugo Gortais
- Department of Neuroradiology, GHU Paris Psychiatrie et Neurosciences, Hospitalier Sainte Anne, Institut de Psychiatrie et Neurosciences de Paris (IPNP), UMR_S1266, INSERM, Université de Paris Centre, France
| | - Joseph Benzakoun
- Department of Neuroradiology, GHU Paris Psychiatrie et Neurosciences, Hospitalier Sainte Anne, Institut de Psychiatrie et Neurosciences de Paris (IPNP), UMR_S1266, INSERM, Université de Paris Centre, France
| | - Takeshi Yoshimoto
- Department of Neurology, National Cerebral and Cardiovascular Center Suita, Japan
| | - Arturo Consoli
- Department of Diagnostic and Interventional Neuroradiology, Foch Hospital, Suresnes, France
| | - Wagih Ben Hassen
- Department of Neuroradiology, CHU Marseille La Timone, Marseille, France
| | - Hilde Henon
- Univ. Lille, Inserm, CHU Lille, U1172 - LilNCog - Lille Neuroscience & Cognition, Lille F-59000, France
| | - Olivier Naggara
- Department of Neuroradiology, CHU Marseille La Timone, Marseille, France
| | | |
Collapse
|
2
|
Ben Alaya I, Limam H, Kraiem T. Automatic triaging of acute ischemic stroke patients for reperfusion therapies using Artificial Intelligence methods and multiple MRI features: A review. Clin Imaging 2023; 104:109992. [PMID: 37857099 DOI: 10.1016/j.clinimag.2023.109992] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2023] [Revised: 09/25/2023] [Accepted: 09/25/2023] [Indexed: 10/21/2023]
Abstract
BACKGROUND The selection of appropriate treatments for Acute Ischemic Stroke (AIS), including Intravenous (IV) tissue plasminogen activator (tPA) and Mechanical thrombectomy, is a critical aspect of clinical decision-making. Timely treatment is essential, with recommended administration of therapies within 4.5 h of symptom onset. However, patients with unknown Time Since Stroke (TSS), are often excluded from thrombolysis, even if the stroke onset exceeds 6 h. Current clinical guidelines propose using multimodal Magnetic Resonance Imaging (MRI) to assess various mismatches. METHODS The review explores the significance of automatic methods based on Artificial Intelligence (AI) algorithms that utilize multiple MRI features to identify patients who are most likely to benefit from acute reperfusion therapies. These AI methods include TSS classification and patient selection for therapies in the late time window (>6 h) using MRI images to provide detailed stroke information. RESULTS The review discusses the challenges and limitations in the existing mismatch methods, which may lead to missed opportunities for reperfusion therapy. To address these limitations, AI approaches have been developed to enhance accuracy and support clinical decision-making. These AI methods have shown promising results, outperforming traditional mismatch assessments and providing improved sensitivity and specificity in identifying patients eligible for reperfusion therapies. DISCUSSION In summary, the integration of AI algorithms utilizing multiple MRI features has the potential to enhance accuracy, improve patient outcomes, and positively influence the decision-making process in AIS. However, ongoing research and collaboration among clinicians, researchers, and technologists are vital to realize the full potential of AI in optimizing stroke management.
Collapse
Affiliation(s)
- Ines Ben Alaya
- Tunis El Manar University, Higher Institute of Medical Technology of Tunis, Laboratory of Biophysics and Medical Technology, 1006 Tunis, Tunisia.
| | - Hela Limam
- Tunis El Manar University, Higher Institute of Computer Science, Higher Institute of Management of Tunis, BestMod Laboratory, 1002 Tunis, Tunisia.
| | - Tarek Kraiem
- Tunis El Manar University, Higher Institute of Medical Technology of Tunis, Laboratory of Biophysics and Medical Technology, 1006 Tunis, Tunisia
| |
Collapse
|
3
|
Bani-Sadr A, Trintignac M, Mechtouff L, Hermier M, Cappucci M, Ameli R, de Bourguignon C, Derex L, Cho TH, Nighoghossian N, Eker OF, Berthezene Y. Is the optimal Tmax threshold identifying perfusion deficit volumes variable across MR perfusion software packages? A pilot study. MAGMA (NEW YORK, N.Y.) 2023; 36:815-822. [PMID: 36811716 DOI: 10.1007/s10334-023-01068-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/23/2022] [Revised: 02/06/2023] [Accepted: 02/07/2023] [Indexed: 02/24/2023]
Abstract
PURPOSE Accurate quantification of ischemic core and ischemic penumbra is mandatory for late-presenting acute ischemic stroke. Substantial differences between MR perfusion software packages have been reported, suggesting that the optimal Time-to-Maximum (Tmax) threshold may be variable. We performed a pilot study to assess the optimal Tmax threshold of two MR perfusion software packages (A: RAPID®; B: OleaSphere®) by comparing perfusion deficit volumes to final infarct volumes as ground truth. METHODS The HIBISCUS-STROKE cohort includes acute ischemic stroke patients treated by mechanical thrombectomy after MRI triage. Mechanical thrombectomy failure was defined as a modified thrombolysis in cerebral infarction score of 0. Admission MR perfusion were post-processed using two packages with increasing Tmax thresholds (≥ 6 s, ≥ 8 s and ≥ 10 s) and compared to final infarct volume evaluated with day-6 MRI. RESULTS Eighteen patients were included. Lengthening the threshold from ≥ 6 s to ≥ 10 s led to significantly smaller perfusion deficit volumes for both packages. For package A, Tmax ≥ 6 s and ≥ 8 s moderately overestimated final infarct volume (median absolute difference: - 9.5 mL, interquartile range (IQR) [- 17.5; 0.9] and 0.2 mL, IQR [- 8.1; 4.8], respectively). Bland-Altman analysis indicated that they were closer to final infarct volume and had narrower ranges of agreement compared with Tmax ≥ 10 s. For package B, Tmax ≥ 10 s was closer to final infarct volume (median absolute difference: - 10.1 mL, IQR: [- 17.7; - 2.9]) versus - 21.8 mL (IQR: [- 36.7; - 9.5]) for Tmax ≥ 6 s. Bland-Altman plots confirmed these findings (mean absolute difference: 2.2 mL versus 31.5 mL, respectively). CONCLUSIONS The optimal Tmax threshold for defining the ischemic penumbra appeared to be most accurate at ≥ 6 s for package A and ≥ 10 s for package B. This implies that the widely recommended Tmax threshold ≥ 6 s may not be optimal for all available MRP software package. Future validation studies are required to define the optimal Tmax threshold to use for each package.
Collapse
Affiliation(s)
- Alexandre Bani-Sadr
- Department of Neuroradiology, East Group Hospital, Hospices Civils de Lyon, 59 Bd Pinel, 69500, Bron, France.
- CREATIS Laboratory, CNRS UMR 5220, INSERM U 5220, Claude Bernard Lyon I University, 7 Avenue Jean Capelle O, 69100, Villeurbanne, France.
| | - Mathilde Trintignac
- Department of Neuroradiology, East Group Hospital, Hospices Civils de Lyon, 59 Bd Pinel, 69500, Bron, France
| | - Laura Mechtouff
- Stroke Department, East Group Hospital, Hospices Civils de Lyon, 59 Bd Pinel, 69500, Bron, France
- CarMeN Laboratory, INSERM U1060, Claude Bernard Lyon I University, 59 Bd Pinel, 69500, Bron, France
| | - Marc Hermier
- Department of Neuroradiology, East Group Hospital, Hospices Civils de Lyon, 59 Bd Pinel, 69500, Bron, France
| | - Matteo Cappucci
- Department of Neuroradiology, East Group Hospital, Hospices Civils de Lyon, 59 Bd Pinel, 69500, Bron, France
| | - Roxana Ameli
- Department of Neuroradiology, East Group Hospital, Hospices Civils de Lyon, 59 Bd Pinel, 69500, Bron, France
| | | | - Laurent Derex
- Stroke Department, East Group Hospital, Hospices Civils de Lyon, 59 Bd Pinel, 69500, Bron, France
| | - Tae-Hee Cho
- Stroke Department, East Group Hospital, Hospices Civils de Lyon, 59 Bd Pinel, 69500, Bron, France
- CarMeN Laboratory, INSERM U1060, Claude Bernard Lyon I University, 59 Bd Pinel, 69500, Bron, France
| | - Norbert Nighoghossian
- Stroke Department, East Group Hospital, Hospices Civils de Lyon, 59 Bd Pinel, 69500, Bron, France
- CarMeN Laboratory, INSERM U1060, Claude Bernard Lyon I University, 59 Bd Pinel, 69500, Bron, France
| | - Omer Faruk Eker
- Department of Neuroradiology, East Group Hospital, Hospices Civils de Lyon, 59 Bd Pinel, 69500, Bron, France
- CREATIS Laboratory, CNRS UMR 5220, INSERM U 5220, Claude Bernard Lyon I University, 7 Avenue Jean Capelle O, 69100, Villeurbanne, France
| | - Yves Berthezene
- Department of Neuroradiology, East Group Hospital, Hospices Civils de Lyon, 59 Bd Pinel, 69500, Bron, France
- CREATIS Laboratory, CNRS UMR 5220, INSERM U 5220, Claude Bernard Lyon I University, 7 Avenue Jean Capelle O, 69100, Villeurbanne, France
| |
Collapse
|
4
|
Ryu WS, Kang YR, Noh YG, Park JH, Kim D, Kim BC, Park MS, Kim BJ, Kim JT. Acute Infarct Segmentation on Diffusion-Weighted Imaging Using Deep Learning Algorithm and RAPID MRI. J Stroke 2023; 25:425-429. [PMID: 37813675 PMCID: PMC10574298 DOI: 10.5853/jos.2023.02145] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Revised: 08/07/2023] [Accepted: 08/18/2023] [Indexed: 10/11/2023] Open
Affiliation(s)
- Wi-Sun Ryu
- Artificial Intelligence Research Center, JLK Inc., Seoul, Korea
| | - You-Ri Kang
- Department of Neurology, Chonnam National University Hospital, Chonnam National University Medical School, Gwangju, Korea
| | - Yoon-Gon Noh
- Artificial Intelligence Research Center, JLK Inc., Seoul, Korea
| | - Jong-Hyeok Park
- Artificial Intelligence Research Center, JLK Inc., Seoul, Korea
| | - Dongmin Kim
- Artificial Intelligence Research Center, JLK Inc., Seoul, Korea
| | - Byeong C. Kim
- Department of Neurology, Chonnam National University Hospital, Chonnam National University Medical School, Gwangju, Korea
| | - Man-Seok Park
- Department of Neurology, Chonnam National University Hospital, Chonnam National University Medical School, Gwangju, Korea
| | - Beom Joon Kim
- Department of Neurology and Cerebrovascular Center, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam, Korea
| | - Joon-Tae Kim
- Department of Neurology, Chonnam National University Hospital, Chonnam National University Medical School, Gwangju, Korea
| |
Collapse
|
5
|
Li YH, Lin SC, Chung HW, Chang CC, Peng HH, Huang TY, Shen WC, Tsai CH, Lo YC, Lee TY, Juan CH, Juan CE, Chang HC, Liu YJ, Juan CJ. The role of input imaging combination and ADC threshold on segmentation of acute ischemic stroke lesion using U-Net. Eur Radiol 2023; 33:6157-6167. [PMID: 37095361 DOI: 10.1007/s00330-023-09622-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2022] [Revised: 02/11/2023] [Accepted: 02/17/2023] [Indexed: 04/26/2023]
Abstract
BACKGROUND To evaluate the effect of the weighting of input imaging combo and ADC threshold on the performance of the U-Net and to find an optimized input imaging combo and ADC threshold in segmenting acute ischemic stroke (AIS) lesion. METHODS This study retrospectively enrolled a total of 212 patients having AIS. Four combos, including ADC-ADC-ADC (AAA), DWI-ADC-ADC (DAA), DWI-DWI-ADC (DDA), and DWI-DWI-DWI (DDD), were used as input images, respectively. Three ADC thresholds including 0.6, 0.8 and 1.8 × 10-3 mm2/s were applied. Dice similarity coefficient (DSC) was used to evaluate the segmentation performance of U-Nets. Nonparametric Kruskal-Wallis test with Tukey-Kramer post-hoc tests were used for comparison. A p < .05 was considered statistically significant. RESULTS The DSC significantly varied among different combos of images and different ADC thresholds. Hybrid U-Nets outperformed uniform U-Nets at ADC thresholds of 0.6 × 10-3 mm2/s and 0.8 × 10-3 mm2/s (p < .001). The U-Net with imaging combo of DDD had segmentation performance similar to hybrid U-Nets at an ADC threshold of 1.8 × 10-3 mm2/s (p = .062 to 1). The U-Net using the imaging combo of DAA at the ADC threshold of 0.6 × 10-3 mm2/s achieved the highest DSC in the segmentation of AIS lesion. CONCLUSIONS The segmentation performance of U-Net for AIS varies among the input imaging combos and ADC thresholds. The U-Net is optimized by choosing the imaging combo of DAA at an ADC threshold of 0.6 × 10-3 mm2/s in segmentating AIS lesion with highest DSC. KEY POINTS • Segmentation performance of U-Net for AIS differs among input imaging combos. • Segmentation performance of U-Net for AIS differs among ADC thresholds. • U-Net is optimized using DAA with ADC = 0.6 × 10-3 mm2/s.
Collapse
Affiliation(s)
- Ya-Hui Li
- Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan, Republic of China
- Department of Medical Imaging, China Medical University Hsinchu Hospital, No. 199, Sec. 1, Xinglong Rd., Zhubei City, Hsinchu County 302, Hsinchu, Taiwan, Republic of China
| | - Shao-Chieh Lin
- Department of Medical Imaging, China Medical University Hsinchu Hospital, No. 199, Sec. 1, Xinglong Rd., Zhubei City, Hsinchu County 302, Hsinchu, Taiwan, Republic of China
- Ph.D. Program in Electrical and Communication Engineering, Feng Chia University, Taichung, Taiwan, Republic of China
| | - Hsiao-Wen Chung
- Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan, Republic of China
- Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan, Republic of China
| | - Chia-Ching Chang
- Department of Medical Imaging, China Medical University Hsinchu Hospital, No. 199, Sec. 1, Xinglong Rd., Zhubei City, Hsinchu County 302, Hsinchu, Taiwan, Republic of China
- Department of Management Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan, Republic of China
| | - Hsu-Hsia Peng
- Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu, Taiwan, Republic of China
| | - Teng-Yi Huang
- Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, Republic of China
| | - Wu-Chung Shen
- Department of Radiology, School of Medicine, College of Medicine, China Medical University, Taichung, Taiwan, Republic of China
- Department of Medical Imaging, Medical University Hospital, Taichung, Taiwan, Republic of China
| | - Chon-Haw Tsai
- Department of Neurology, China Medical University Hospital, Taichung, Taiwan, Republic of China
| | - Yu-Chien Lo
- Department of Medical Imaging, Medical University Hospital, Taichung, Taiwan, Republic of China
| | - Tung-Yang Lee
- Cheng Ching Hospital, Taichung, Taiwan, Republic of China
- Master's Program of Biomedical Informatics and Biomedical Engineering, Feng Chia University, Taichung, Taiwan, Republic of China
| | - Cheng-Hsuan Juan
- Cheng Ching Hospital, Taichung, Taiwan, Republic of China
- Master's Program of Biomedical Informatics and Biomedical Engineering, Feng Chia University, Taichung, Taiwan, Republic of China
| | - Cheng-En Juan
- Master's Program of Biomedical Informatics and Biomedical Engineering, Feng Chia University, Taichung, Taiwan, Republic of China
| | - Hing-Chiu Chang
- Department of Biomedical Engineering, The Chinese University of Hong Kong, ERB1112, 11/F, William M.W. Mong Engineering Building, Shatin, N.T, Hong Kong.
- Multi-Scale Medical Robotics Center, The Chinese University of Hong Kong, Shatin, N.T, Hong Kong.
| | - Yi-Jui Liu
- Department of Automatic Control Engineering, Feng Chia University, No. 100 Wenhwa Rd., Seatwen, 40724, Taichung, Taiwan, Republic of China.
| | - Chun-Jung Juan
- Department of Medical Imaging, China Medical University Hsinchu Hospital, No. 199, Sec. 1, Xinglong Rd., Zhubei City, Hsinchu County 302, Hsinchu, Taiwan, Republic of China.
- Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu, Taiwan, Republic of China.
- Department of Radiology, School of Medicine, College of Medicine, China Medical University, Taichung, Taiwan, Republic of China.
- Department of Medical Imaging, Medical University Hospital, Taichung, Taiwan, Republic of China.
- Department of Biomedical Engineering, National Defense Medical Center, Taipei, Taiwan, Republic of China.
- Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan, Republic of China.
| |
Collapse
|
6
|
Bani-Sadr A, Cho TH, Cappucci M, Hermier M, Ameli R, Filip A, Riva R, Derex L, De Bourguignon C, Mechtouff L, Eker OF, Nighoghossian N, Berthezene Y. Assessment of three MR perfusion software packages in predicting final infarct volume after mechanical thrombectomy. J Neurointerv Surg 2023; 15:393-398. [PMID: 35318959 DOI: 10.1136/neurintsurg-2022-018674] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2022] [Accepted: 02/28/2022] [Indexed: 11/04/2022]
Abstract
AIMS To evaluate the performance of three MR perfusion software packages (A: RAPID; B: OleaSphere; and C: Philips) in predicting final infarct volume (FIV). METHODS This cohort study included patients treated with mechanical thrombectomy following an admission MRI and undergoing a follow-up MRI. Admission MRIs were post-processed by three packages to quantify ischemic core and perfusion deficit volume (PDV). Automatic package outputs (uncorrected volumes) were collected and corrected by an expert. Successful revascularization was defined as a modified Thrombolysis in Cerebral Infarction (mTICI) score ≥2B. Uncorrected and corrected volumes were compared between each package and with FIV according to mTICI score. RESULTS Ninety-four patients were included, of whom 67 (71.28%) had a mTICI score ≥2B. In patients with successful revascularization, ischemic core volumes did not differ significantly from FIV regardless of the package used for uncorrected and corrected volumes (p>0.15). Conversely, assessment of PDV showed significant differences for uncorrected volumes. In patients with unsuccessful revascularization, the uncorrected PDV of packages A (median absolute difference -40.9 mL) and B (median absolute difference -67.0 mL) overestimated FIV to a lesser degree than package C (median absolute difference -118.7 mL; p=0.03 and p=0.12, respectively). After correction, PDV did not differ significantly from FIV for all three packages (p≥0.99). CONCLUSIONS Automated MRI perfusion software packages estimate FIV with high variability in measurement despite using the same dataset. This highlights the need for routine expert evaluation and correction of automated package output data for appropriate patient management.
Collapse
Affiliation(s)
- Alexandre Bani-Sadr
- Neuroradiology, Hospices Civils de Lyon, Bron, France .,MYRIAD, CREATIS, Villeurbanne, France
| | - Tae-Hee Cho
- Stroke Department, Hospices Civils de Lyon, Lyon, France
| | | | - Marc Hermier
- Neuroradiology, Hospices Civils de Lyon, Bron, France
| | - Roxana Ameli
- Neuroradiology, Hospices Civils de Lyon, Bron, France
| | - Andrea Filip
- Neuroradiology, Hospices Civils de Lyon, Bron, France
| | - Roberto Riva
- Neuroradiology, Hospices Civils de Lyon, Bron, France
| | - Laurent Derex
- Stroke Department, Hospices Civils de Lyon, Lyon, France
| | | | | | - Omer F Eker
- Neuroradiology, Hospices Civils de Lyon, Bron, France.,MYRIAD, CREATIS, Villeurbanne, France
| | | | - Yves Berthezene
- Neuroradiology, Hospices Civils de Lyon, Bron, France.,MYRIAD, CREATIS, Villeurbanne, France
| |
Collapse
|
7
|
Dittrich TD, Sporns PB, Kriemler LF, Rudin S, Nguyen A, Zietz A, Polymeris AA, Tränka C, Thilemann S, Wagner B, Altersberger VL, Piot I, Barinka F, Müller S, Hänsel M, Gensicke H, Engelter ST, Lyrer PA, Sutter R, Nickel CH, Katan M, Peters N, Kulcsár Z, Karwacki GM, Pileggi M, Cereda C, Wegener S, Bonati LH, Fischer U, Psychogios M, De Marchis GM. Mechanical Thrombectomy Versus Best Medical Treatment in the Late Time Window in Non-DEFUSE-Non-DAWN Patients: A Multicenter Cohort Study. Stroke 2023; 54:722-730. [PMID: 36718751 PMCID: PMC10561685 DOI: 10.1161/strokeaha.122.039793] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2022] [Accepted: 10/21/2022] [Indexed: 02/01/2023]
Abstract
BACKGROUND We assessed the efficacy and safety of mechanical thrombectomy (MT) in adult stroke patients with anterior circulation large vessel occlusion presenting in the late time window not fulfilling the DEFUSE-3 (Thrombectomy for Stroke at 6 to 16 Hours With Selection by Perfusion Imaging trial) and DAWN (Thrombectomy 6 to 24 Hours After Stroke With a Mismatch Between Deficit and Infarct trial) inclusion criteria. METHODS Cohort study of adults with anterior circulation large vessel occlusion admitted between 6 and 24 hours after last-seen-well at 5 participating Swiss stroke centers between 2014 and 2021. Mismatch was assessed by computer tomography or magnetic resonance imaging perfusion with automated software (RAPID or OLEA). We excluded patients meeting DEFUSE-3 and DAWN inclusion criteria and compared those who underwent MT with those receiving best medical treatment alone by inverse probability of treatment weighting using the propensity score. The primary efficacy end point was a favorable functional outcome at 90 days, defined as a modified Rankin Scale score shift toward lower categories. The primary safety end point was symptomatic intracranial hemorrhage within 7 days of stroke onset; the secondary was all-cause mortality within 90 days. RESULTS Among 278 patients with anterior circulation large vessel occlusion presenting in the late time window, 190 (68%) did not meet the DEFUSE-3 and DAWN inclusion criteria and thus were included in the analyses. Of those, 102 (54%) received MT. In the inverse probability of treatment weighting analysis, patients in the MT group had higher odds of favorable outcomes compared with the best medical treatment alone group (modified Rankin Scale shift: acOR, 1.46 [1.02-2.10]; P=0.04) and lower odds of all-cause mortality within 90 days (aOR, 0.59 [0.37-0.93]; P=0.02). There were no significant differences in symptomatic intracranial hemorrhage (MT versus best medical treatment alone: 5% versus 2%, P=0.63). CONCLUSIONS Two out of 3 patients with anterior circulation large vessel occlusion presenting in the late time window did not meet the DEFUSE-3 and DAWN inclusion criteria. In these patients, MT was associated with higher odds of favorable functional outcomes without increased rates of symptomatic intracranial hemorrhage. These findings support the enrollment of patients into ongoing randomized trials on MT in the late window with more permissive inclusion criteria.
Collapse
Affiliation(s)
- Tolga D Dittrich
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Peter B Sporns
- Department of Neuroradiology, University Hospital Basel, Switzerland (P.B.S., A.N., M.P.)
- Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Germany (P.B.S.)
| | - Lilian F Kriemler
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
- Clinic for Internal Medicine, Cantonal Hospital Schaffhausen, Switzerland (L.F.K.)
| | - Salome Rudin
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Anh Nguyen
- Department of Neuroradiology, University Hospital Basel, Switzerland (P.B.S., A.N., M.P.)
| | - Annaelle Zietz
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Alexandros A Polymeris
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Christopher Tränka
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Sebastian Thilemann
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Benjamin Wagner
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Valerian L Altersberger
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Ines Piot
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Filip Barinka
- Department of Neurology and Stroke Center, Hirslanden Hospital Zurich, Switzerland (F.B., N.P.)
| | - Susanne Müller
- Department of Neuroradiology, University Hospital Zurich, Switzerland (S.M.)
| | - Martin Hänsel
- Department of Neurology, University Hospital Zurich and University of Zurich, Switzerland (M.H., S.W.)
| | - Henrik Gensicke
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
- Neurology and Neurorehabilitation, University Department of Geriatric Medicine Felix Platter, Basel, Switzerland (H.G., S.T.E.)
| | - Stefan T Engelter
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
- Neurology and Neurorehabilitation, University Department of Geriatric Medicine Felix Platter, Basel, Switzerland (H.G., S.T.E.)
| | - Philippe A Lyrer
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Raoul Sutter
- Department of Intensive Care Medicine, University Hospital Basel, Switzerland (R.S.)
| | - Christian H Nickel
- Emergency Department University Hospital Basel and University of Basel, Switzerland (C.H.N.)
| | - Mira Katan
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Nils Peters
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
- Department of Neurology and Stroke Center, Hirslanden Hospital Zurich, Switzerland (F.B., N.P.)
| | - Zsolt Kulcsár
- Department of Neuroradiology, University Hospital Zurich, Switzerland (Z.K.)
| | - Grzegorz M Karwacki
- Department of Radiology and Nuclear Medicine, Cantonal Hospital of Lucerne, Switzerland (G.M.K.)
| | - Marco Pileggi
- Department of Neuroradiology, University Hospital Basel, Switzerland (P.B.S., A.N., M.P.)
| | - Carlo Cereda
- Department of Neurology and Stroke Center, EOC Neurocenter of Southern Switzerland, Lugano, Switzerland (C.C.)
| | - Susanne Wegener
- Department of Neurology, University Hospital Zurich and University of Zurich, Switzerland (M.H., S.W.)
| | - Leo H Bonati
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
- Rheinfelden Rehabilitation Clinic, Switzerland (L.H.B.)
| | - Urs Fischer
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| | - Marios Psychogios
- Department of Neuroradiology, EOC Neurocenter of Southern Switzerland, Lugano, Switzerland (M.P.)
| | - Gian Marco De Marchis
- Department of Neurology, University Hospital Basel and University of Basel, Switzerland (T.D.D., L.F.K., S.R., A.Z., A.A.P., C.T., S.T., B.W., V.L.A., I.P., H.G., S.T.E., P.A.L., M.K., N.P., L.H.B., U.F., G.M.D.M.)
| |
Collapse
|
8
|
Neurological Functional Independence After Endovascular Thrombectomy and Different Imaging Modalities for Large Infarct Core Assessment : A Systematic Review and Meta-analysis. Clin Neuroradiol 2023; 33:21-29. [PMID: 35920865 DOI: 10.1007/s00062-022-01202-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2022] [Accepted: 07/10/2022] [Indexed: 11/03/2022]
Abstract
PURPOSE To investigate the rate of neurological functional independence (NFI) at 90 days in patients with large infarct core (LIC), which was evaluated by different imaging modalities before endovascular thrombectomy (EVT). METHODS PubMed and EMBASE were searched for original studies on clinical functional outcomes at 90 days in LIC patients who received EVT treatment from inception to 28 September 2021. The pooled NFI rates were calculated using random effects model according to different imaging modalities and criteria. RESULTS We included 34 studies enrolling 2997 LIC patients. The NFI rates were 23% (95% confidence interval, CI 15-32%) and 24% (95% CI 10-38%) when LIC was defined as core volume ≥50 ml and ≥ 70 ml separately on computed tomography perfusion, 36% (95% CI 23-48%) and 21% (95% CI 17-25%) when LIC was defined as core volume ≥ 50 ml and ≥ 70 ml separately on magnetic resonance diffusion-weighted imaging (DWI), 28% (95% CI 24-32%) and 37% (95% CI 21-53%) when LIC was defined as DWI-ASPECTS ≤ 5 and ≤ 6 separately, 23% (95% CI 19-27%) and 32% (95% CI 18-46%) when LIC was defined as NCCT-ASPECTS ≤ 5 and ≤ 6 separately. CONCLUSION Similar NFI rates could be obtained after EVT in LIC patients if proper LIC criteria were select according to the imaging modality.
Collapse
|
9
|
Kossen T, Madai VI, Mutke MA, Hennemuth A, Hildebrand K, Behland J, Aslan C, Hilbert A, Sobesky J, Bendszus M, Frey D. Image-to-image generative adversarial networks for synthesizing perfusion parameter maps from DSC-MR images in cerebrovascular disease. Front Neurol 2023; 13:1051397. [PMID: 36703627 PMCID: PMC9871486 DOI: 10.3389/fneur.2022.1051397] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2022] [Accepted: 12/15/2022] [Indexed: 01/11/2023] Open
Abstract
Stroke is a major cause of death or disability. As imaging-based patient stratification improves acute stroke therapy, dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) is of major interest in image brain perfusion. However, expert-level perfusion maps require a manual or semi-manual post-processing by a medical expert making the procedure time-consuming and less-standardized. Modern machine learning methods such as generative adversarial networks (GANs) have the potential to automate the perfusion map generation on an expert level without manual validation. We propose a modified pix2pix GAN with a temporal component (temp-pix2pix-GAN) that generates perfusion maps in an end-to-end fashion. We train our model on perfusion maps infused with expert knowledge to encode it into the GANs. The performance was trained and evaluated using the structural similarity index measure (SSIM) on two datasets including patients with acute stroke and the steno-occlusive disease. Our temp-pix2pix architecture showed high performance on the acute stroke dataset for all perfusion maps (mean SSIM 0.92-0.99) and good performance on data including patients with the steno-occlusive disease (mean SSIM 0.84-0.99). While clinical validation is still necessary for future studies, our results mark an important step toward automated expert-level perfusion maps and thus fast patient stratification.
Collapse
Affiliation(s)
- Tabea Kossen
- Charité Lab for Artificial Intelligence in Medicine (CLAIM), Charité-Universitätsmedizin Berlin, Berlin, Germany,Department of Computer Engineering and Microelectronics, Computer Vision and Remote Sensing, Technical University Berlin, Berlin, Germany,*Correspondence: Tabea Kossen ✉
| | - Vince I. Madai
- Charité Lab for Artificial Intelligence in Medicine (CLAIM), Charité-Universitätsmedizin Berlin, Berlin, Germany,QUEST Center for Responsible Research, Berlin Institute of Health (BIH), Charité-Universitätsmedizin Berlin, Berlin, Germany,Faculty of Computing, Engineering and the Built Environment, School of Computing and Digital Technology, Birmingham City University, Birmingham, United Kingdom
| | - Matthias A. Mutke
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
| | - Anja Hennemuth
- Department of Computer Engineering and Microelectronics, Computer Vision and Remote Sensing, Technical University Berlin, Berlin, Germany,Institute for Imaging Science and Computational Modelling in Cardiovascular Medicine, Charité-Universitätsmedizin Berlin, Berlin, Germany,Fraunhofer MEVIS, Bremen, Germany
| | - Kristian Hildebrand
- Department of Computer Science and Media, Berlin University of Applied Sciences and Technology, Berlin, Germany
| | - Jonas Behland
- Charité Lab for Artificial Intelligence in Medicine (CLAIM), Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Cagdas Aslan
- Department of Computer Science and Media, Berlin University of Applied Sciences and Technology, Berlin, Germany
| | - Adam Hilbert
- Charité Lab for Artificial Intelligence in Medicine (CLAIM), Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Jan Sobesky
- Center for Stroke Research Berlin, Charité-Universitätsmedizin Berlin, Berlin, Germany,Johanna-Etienne-Hospital, Neuss, Germany
| | - Martin Bendszus
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
| | - Dietmar Frey
- Charité Lab for Artificial Intelligence in Medicine (CLAIM), Charité-Universitätsmedizin Berlin, Berlin, Germany
| |
Collapse
|
10
|
Xiong Y, Luo Y, Wang M, Yang ST, Shi R, Ye W, Li G, Yang K, Wang S, Li Z, Wang Y. Evaluation of Diffusion-Perfusion Mismatch in Acute Ischemic Stroke with a New Automated Perfusion-Weighted Imaging Software: A Retrospective Study. Neurol Ther 2022; 11:1777-1788. [PMID: 36201112 DOI: 10.1007/s40120-022-00409-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/02/2022] [Accepted: 09/16/2022] [Indexed: 10/10/2022] Open
Abstract
INTRODUCTION The aim of this study was to evaluate the accuracy of automated software (iStroke) on magnetic resonance (MR) apparent diffusion coefficient (ADC) and perfusion-weighted imaging (PWI) against ground truth in assessing infarct core, and compare the hypoperfusion volume and mismatch volume on iStroke with those on Food and Drug Administration-approved software (RAPID) in patients with acute ischemic stroke. METHODS We used the single-volume decomposition method to develop the iStroke (iStroke; Beijing Tiantan Hospital, Beijing, China) software. Patients with ischemic stroke were collected from two educational hospitals in China with MR-PWI performed in the emergency department within 24 h of symptom onset. Infarct core volume was defined as ADC < 620 × 10-6 mm2/s and hypoperfusion volume was defined as Tmax > 6 s. We compared the accuracy of infarct core volume using iStroke and RAPID (iSchema View Inc, Menlo Park, CA) software with ground truth. RESULTS We included 405 patients with acute ischemic stroke with MR ADC and PWI sequences. The infarct core volume on iStroke (median 2.43 ml, interquartile range [IQR] 0.60-10.32 ml) was not significantly different from the ground truth (median 2.89 ml, IQR 0.77-9.17 ml) (P = 0.07); Bland-Altman curves showed that the core volume of iStroke and RAPID software were comparable with each other on individual agreement with ground truth. The hypoperfusion volume and mismatch volume on iStroke were not statistically different from those on the RAPID software, respectively. In patients with large vessel occlusion (n = 74), the agreement between iStroke and RAPID was substantial (kappa = 0.76) according to DEFUSE 3 criteria (infarct core < 70 ml, mismatch volume ≥ 15 ml, and mismatch ratio ≥ 1.8). CONCLUSIONS The iStroke automatic processing of ADC and PWI is a reliable software for the identification of diffusion-perfusion mismatch in acute ischemic stroke.
Collapse
Affiliation(s)
- Yunyun Xiong
- Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China.,Chinese Institute for Brain Research, Beijing, China
| | - Yu Luo
- Department of Radiology, Shanghai Fourth People's Hospital Affiliated to Tongji University School of Medicine, Shanghai, 200434, China
| | - Mingming Wang
- Department of Radiology, Shanghai Fourth People's Hospital Affiliated to Tongji University School of Medicine, Shanghai, 200434, China
| | - Shih-Ting Yang
- China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Ruiqiong Shi
- China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Wanxing Ye
- China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Guangshuo Li
- Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Kaixuan Yang
- China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Shang Wang
- China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Zixiao Li
- Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China.,Chinese Institute for Brain Research, Beijing, China
| | - Yongjun Wang
- Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China. .,China National Clinical Research Center for Neurological Diseases, Beijing, China.
| |
Collapse
|
11
|
Juan CJ, Lin SC, Li YH, Chang CC, Jeng YH, Peng HH, Huang TY, Chung HW, Shen WC, Tsai CH, Chang RF, Liu YJ. Improving interobserver agreement and performance of deep learning models for segmenting acute ischemic stroke by combining DWI with optimized ADC thresholds. Eur Radiol 2022; 32:5371-5381. [PMID: 35201408 DOI: 10.1007/s00330-022-08633-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2021] [Revised: 12/26/2021] [Accepted: 01/31/2022] [Indexed: 11/28/2022]
Abstract
OBJECTIVES To examine the role of ADC threshold on agreement across observers and deep learning models (DLMs) plus segmentation performance of DLMs for acute ischemic stroke (AIS). METHODS Twelve DLMs, which were trained on DWI-ADC-ADC combination from 76 patients with AIS using 6 different ADC thresholds with ground truth manually contoured by 2 observers, were tested by additional 67 patients in the same hospital and another 78 patients in another hospital. Agreement between observers and DLMs were evaluated by Bland-Altman plot and intraclass correlation coefficient (ICC). The similarity between ground truth (GT) defined by observers and between automatic segmentation performed by DLMs was evaluated by Dice similarity coefficient (DSC). Group comparison was performed using the Mann-Whitney U test. The relationship between the DSC and ADC threshold as well as AIS lesion size was evaluated by linear regression analysis. A p < .05 was considered statistically significant. RESULTS Excellent interobserver agreement and intraobserver repeatability in the manual segmentation (all ICC > 0.98, p < .001) were achieved. The 95% limit of agreement was reduced from 11.23 cm2 for GT on DWI to 0.59 cm2 for prediction at an ADC threshold of 0.6 × 10-3 mm2/s combined with DWI. The segmentation performance of DLMs was improved with an overall DSC from 0.738 ± 0.214 on DWI to 0.971 ± 0.021 on an ADC threshold of 0.6 × 10-3 mm2/s combined with DWI. CONCLUSIONS Combining an ADC threshold of 0.6 × 10-3 mm2/s with DWI reduces interobserver and inter-DLM difference and achieves best segmentation performance of AIS lesions using DLMs. KEY POINTS • Higher Dice similarity coefficient (DSC) in predicting acute ischemic stroke lesions was achieved by ADC thresholds combined with DWI than by DWI alone (all p < .05). • DSC had a negative association with the ADC threshold in most sizes, both hospitals, and both observers (most p < .05) and a positive association with the stroke size in all ADC thresholds, both hospitals, and both observers (all p < .001). • An ADC threshold of 0.6 × 10-3 mm2/s eliminated the difference of DSC at any stroke size between observers or between hospitals (p = .07 to > .99).
Collapse
Affiliation(s)
- Chun-Jung Juan
- Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan, Republic of China
- Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu, Taiwan, Republic of China
- Department of Radiology, School of Medicine, College of Medicine, China Medical University, Taichung, Taiwan, Republic of China
- Department of Medical Imaging, China Medical University Hospital, Taichung, Taiwan, Republic of China
- Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu, Taiwan, Republic of China
| | - Shao-Chieh Lin
- Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu, Taiwan, Republic of China
- Ph.D. Program in Electrical and Communication Engineering, Feng Chia University, Taichung, Taiwan, Republic of China
| | - Ya-Hui Li
- Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu, Taiwan, Republic of China
- Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan, Republic of China
| | - Chia-Ching Chang
- Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu, Taiwan, Republic of China
- Department of Management Science, National Chiao-Tung University, Hsinchu, Taiwan, Republic of China
| | - Yi-Hung Jeng
- Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu, Taiwan, Republic of China
- Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu, Taiwan, Republic of China
| | - Hsu-Hsia Peng
- Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu, Taiwan, Republic of China
| | - Teng-Yi Huang
- Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, Republic of China
| | - Hsiao-Wen Chung
- Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan, Republic of China
- Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan, Republic of China
| | - Wu-Chung Shen
- Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu, Taiwan, Republic of China
- Department of Radiology, School of Medicine, College of Medicine, China Medical University, Taichung, Taiwan, Republic of China
| | - Chon-Haw Tsai
- Department of Neurology, China Medical University Hospital, Taichung, Taiwan, Republic of China
| | - Ruey-Feng Chang
- Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan, Republic of China.
- Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan, Republic of China.
| | - Yi-Jui Liu
- Department of Automatic Control Engineering, Feng Chia University, No. 100 Wenhwa Rd., Seatwen, 40724, Taichung, Taiwan, Republic of China.
| |
Collapse
|
12
|
Lakatos L, Bolognese M, Müller M, Österreich M, von Hessling A. Automated Supra- and Infratentorial Brain Infarct Volume Estimation on Diffusion Weighted Imaging Using the RAPID Software. Front Neurol 2022; 13:907151. [PMID: 35873774 PMCID: PMC9304979 DOI: 10.3389/fneur.2022.907151] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2022] [Accepted: 06/14/2022] [Indexed: 11/13/2022] Open
Abstract
PurposeThe present computerized techniques have limits to estimate the ischemic lesion volume especially in vertebrobasilar ischemia (VBI) automatically. We investigated the ability of the RAPID AI (RAPID) software on diffusion-weighted imaging (DWI) to estimate the infarct size in VBI in comparison to supratentorial ischemia (STI).MethodsAmong 123 stroke patients (39 women, 84 men, mean age 66 ± 11 years) having undergone DWI, 41 had had a VBI and 82 a STI. The infarct volume calculation by RAPID was compared to volume calculations by 2 neurologists using the ABC/2 method. For inter-reader and between-method analysis intraclass correlation coefficient (ICC), area under the curve (AUC) estimations, and Bland–Altman plots were used.ResultsICC between the two neurologists and each neurologist and RAPID were >0.946 (largest 95% CI boundaries 0.917–0.988) in the STI group, and > 0.757 (95% CI boundaries between 0.544 and 0.982) in the VBI group. In the STI group, AUC values ranged between 0.982 and 0.999 (95% CI 0.971–1) between the 2 neurologists and between 0.875 and 1 (95% CI 0.787–1) between the neurologists and RAPID; in the VBI group, they ranged between 0.925 and 0.965 (95% CI 0.801–1) between the neurologists, and between 0.788 and 0.931 (95% CI 0.663–1) between RAPID and the neurologists. Compared to the visual DWI interpretation by the neurologists, RAPID did not recognize a substantial number of infarct volumes of ≤ 2 ml.ConclusionThe ability of the RAPID software to depict strokes in the vertebrobasilar artery system seems close to its ability in the supratentorial brain tissue. However, small lesion volumes ≤ 2 ml remain still undetected in both brain areas.
Collapse
Affiliation(s)
- Lehel Lakatos
- Department of Neurology and Neurorehabilitation, Lucerne Kantonsspital, Lucerne, Switzerland
| | - Manuel Bolognese
- Department of Neurology and Neurorehabilitation, Lucerne Kantonsspital, Lucerne, Switzerland
| | - Martin Müller
- Department of Neurology and Neurorehabilitation, Lucerne Kantonsspital, Lucerne, Switzerland
- *Correspondence: Martin Müller
| | - Mareike Österreich
- Department of Neurology and Neurorehabilitation, Lucerne Kantonsspital, Lucerne, Switzerland
| | - Alexander von Hessling
- Department of Radiology (Section Neuroradiology), Lucerne Kantonsspital, Lucerne, Switzerland
| |
Collapse
|
13
|
Mangesius S, Haider L, Lenhart L, Steiger R, Prados Carrasco F, Scherfler C, Gizewski ER. Qualitative and Quantitative Comparison of Hippocampal Volumetric Software Applications: Do All Roads Lead to Rome? Biomedicines 2022; 10:biomedicines10020432. [PMID: 35203641 PMCID: PMC8962257 DOI: 10.3390/biomedicines10020432] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2021] [Revised: 01/30/2022] [Accepted: 02/10/2022] [Indexed: 02/06/2023] Open
Abstract
Brain volumetric software is increasingly suggested for clinical routine. The present study quantifies the agreement across different software applications. Ten cases with and ten gender- and age-adjusted healthy controls without hippocampal atrophy (median age: 70; 25–75% range: 64–77 years and 74; 66–78 years) were retrospectively selected from a previously published cohort of Alzheimer’s dementia patients and normal ageing controls. Hippocampal volumes were computed based on 3 Tesla T1-MPRAGE-sequences with FreeSurfer (FS), Statistical-Parametric-Mapping (SPM; Neuromorphometrics and Hammers atlases), Geodesic-Information-Flows (GIF), Similarity-and-Truth-Estimation-for-Propagated-Segmentations (STEPS), and Quantib™. MTA (medial temporal lobe atrophy) scores were manually rated. Volumetric measures of each individual were compared against the mean of all applications with intraclass correlation coefficients (ICC) and Bland–Altman plots. Comparing against the mean of all methods, moderate to low agreement was present considering categorization of hippocampal volumes into quartiles. ICCs ranged noticeably between applications (left hippocampus (LH): from 0.42 (STEPS) to 0.88 (FS); right hippocampus (RH): from 0.36 (Quantib™) to 0.86 (FS). Mean differences between individual methods and the mean of all methods [mm3] were considerable (LH: FS −209, SPM-Neuromorphometrics −820; SPM-Hammers −1474; Quantib™ −680; GIF 891; STEPS 2218; RH: FS −232, SPM-Neuromorphometrics −745; SPM-Hammers −1547; Quantib™ −723; GIF 982; STEPS 2188). In this clinically relevant sample size with large spread in data ranging from normal aging to severe atrophy, hippocampal volumes derived by well-accepted applications were quantitatively different. Thus, interchangeable use is not recommended.
Collapse
Affiliation(s)
- Stephanie Mangesius
- Department of Neuroradiology, Medical University of Innsbruck, Anichstrasse 35, 6020 Innsbruck, Austria; (S.M.); (L.L.); (R.S.); (E.R.G.)
- Neuroimaging Core Facility, Medical University of Innsbruck, Anichstrasse 35, 6020 Innsbruck, Austria
| | - Lukas Haider
- NMR Research Unit, Queen Square Multiple Sclerosis Centre, University College London Institute of Neurology, Russell Square House, Russell Square 10-12, London WC1B 5EH, UK;
- Department of Biomedical Imaging and Image Guided Therapy, Medical University of Vienna, Währinger Gürtel 18-20, 1090 Vienna, Austria
- Correspondence:
| | - Lukas Lenhart
- Department of Neuroradiology, Medical University of Innsbruck, Anichstrasse 35, 6020 Innsbruck, Austria; (S.M.); (L.L.); (R.S.); (E.R.G.)
- Neuroimaging Core Facility, Medical University of Innsbruck, Anichstrasse 35, 6020 Innsbruck, Austria
| | - Ruth Steiger
- Department of Neuroradiology, Medical University of Innsbruck, Anichstrasse 35, 6020 Innsbruck, Austria; (S.M.); (L.L.); (R.S.); (E.R.G.)
- Neuroimaging Core Facility, Medical University of Innsbruck, Anichstrasse 35, 6020 Innsbruck, Austria
| | - Ferran Prados Carrasco
- NMR Research Unit, Queen Square Multiple Sclerosis Centre, University College London Institute of Neurology, Russell Square House, Russell Square 10-12, London WC1B 5EH, UK;
- Centre for Medical Image Computing (CMIC), Department of Medical Physics and Biomedical Engineering, University College London, Malet Place Engineering Building, Gower Street, London WC1E 6BT, UK
- e-Health Centre, Universitat Oberta de Catalunya, Rambla del Poblenou 156, 08018 Barcelona, Spain
| | - Christoph Scherfler
- Department of Neurology, Medical University of Innsbruck, Anichstrasse 35, 6020 Innsbruck, Austria;
| | - Elke R. Gizewski
- Department of Neuroradiology, Medical University of Innsbruck, Anichstrasse 35, 6020 Innsbruck, Austria; (S.M.); (L.L.); (R.S.); (E.R.G.)
- Neuroimaging Core Facility, Medical University of Innsbruck, Anichstrasse 35, 6020 Innsbruck, Austria
| |
Collapse
|
14
|
Kim YC, Seo WK, Baek IY, Lee JE, Song HN, Chung JW, Kim CK, Oh K, Suh SI, Bang OY, Kim GM, Saver JL, Liebeskind DS. Diffusion-Weighted Imaging-Alone Endovascular Thrombectomy Triage in Acute Stroke: Simulating Diffusion-Perfusion Mismatch Using Machine Learning. J Stroke 2022; 24:148-151. [PMID: 35135068 PMCID: PMC8829488 DOI: 10.5853/jos.2021.02817] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2021] [Accepted: 11/01/2021] [Indexed: 11/26/2022] Open
Affiliation(s)
- Yoon-Chul Kim
- Research Institute for Future Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
| | - Woo-Keun Seo
- Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
- Department of Digital Health, Samsung Advanced Institute for Health Sciences & Technology, Sungkyunkwan University, Seoul, Korea
- Correspondence: Woo-Keun Seo Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul 06351, Korea Tel: +82-2-3410-0799 Fax: +82-2-3410-0630 E-mail:
| | - In-Young Baek
- Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
| | - Ji-Eun Lee
- Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
| | - Ha-Na Song
- Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
| | - Jong-Won Chung
- Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
| | - Chi Kyung Kim
- Department of Neurology, Korea University College of Medicine, Seoul, Korea
| | - Kyungmi Oh
- Department of Neurology, Korea University College of Medicine, Seoul, Korea
| | - Sang-il Suh
- Department of Radiology, Korea University College of Medicine, Seoul, Korea
| | - Oh Young Bang
- Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
| | - Gyeong-Moon Kim
- Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
| | - Jeffrey L. Saver
- Department of Neurology, University of California in Los Angeles, Los Angeles, CA, USA
| | - David S. Liebeskind
- Department of Neurology, University of California in Los Angeles, Los Angeles, CA, USA
| |
Collapse
|
15
|
Ben Alaya I, Limam H, Kraiem T. Applications of artificial intelligence for DWI and PWI data processing in acute ischemic stroke: Current practices and future directions. Clin Imaging 2021; 81:79-86. [PMID: 34649081 DOI: 10.1016/j.clinimag.2021.09.015] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2021] [Revised: 09/05/2021] [Accepted: 09/22/2021] [Indexed: 11/03/2022]
Abstract
Multimodal Magnetic Resonance Imaging (MRI) techniques of Perfusion-Weighted Imaging (PWI) and Diffusion-Weighted Imaging (DWI) data are integral parts of the diagnostic workup in the acute stroke setting. The visual interpretation of PWI/DWI data is the most likely procedure to triage Acute Ischemic Stroke (AIS) patients who will access reperfusion therapy, especially in those exceeding 6 h of stroke onset. In fact, this process defines two classes of tissue: the ischemic core, which is presumed to be irreversibly damaged, visualized on DWI data and the penumbra which is the reversibly injured brain tissue around the ischemic tissue, visualized on PWI data. AIS patients with a large ischemic penumbra and limited infarction core have a high probability of benefiting from endovascular treatment. However, it is a tedious and time-consuming procedure. Consequently, it is subject to high inter- and intra-observer variability. Thus, the assessment of the potential risks and benefits of endovascular treatment is uncertain. Fast, accurate and automatic post-processing of PWI and DWI data is important for clinical diagnosis and is necessary to help the decision making for therapy. Therefore, an automated procedure that identifies stroke slices, stroke hemisphere, segments stroke regions in DWI, and measures hypoperfused tissue in PWI enhances considerably the reproducibility and the accuracy of stroke assessment. In this work, we draw an overview of several applications of Artificial Intelligence (AI) for the automation processing and their potential contributions in clinical practices. We compare the current approaches among each other's with respect to some key requirements.
Collapse
Affiliation(s)
- Ines Ben Alaya
- Tunis El Manar University, Higher Institute of Medical Technology of Tunis, Laboratory of Biophysics and Medical Technology, 1006 Tunis, Tunisia.
| | - Hela Limam
- Université de Tunis El Manar, Institut Supérieur d'Informatique, Institut Supérieur de Gestion de Tunis, Laboratoire BestMod, 1002 Tunis, Tunisie.
| | - Tarek Kraiem
- Tunis El Manar University, Higher Institute of Medical Technology of Tunis, Laboratory of Biophysics and Medical Technology, 1006 Tunis, Tunisia.
| |
Collapse
|
16
|
Jiang L, Zhou L, Yong W, Cui J, Geng W, Chen H, Zou J, Chen Y, Yin X, Chen YC. A deep learning-based model for prediction of hemorrhagic transformation after stroke. Brain Pathol 2021; 33:e13023. [PMID: 34608705 PMCID: PMC10041160 DOI: 10.1111/bpa.13023] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2021] [Revised: 08/26/2021] [Accepted: 09/20/2021] [Indexed: 12/29/2022] Open
Abstract
Hemorrhagic transformation (HT) is one of the most serious complications after endovascular thrombectomy (EVT) in acute ischemic stroke (AIS) patients. The purpose of this study is to develop and validate deep-learning (DL) models based on multiparametric magnetic resonance imaging (MRI) to automatically predict HT in AIS patients. Multiparametric MRI and clinical data of AIS patients with EVT from two centers (data set 1 for training and testing: n = 338; data set 2 for validating: n = 54) were used in the DL models. The acute infarction area of diffusion-weighted imaging (DWI) and hypoperfusion of perfusion-weighted imaging (PWI) was labeled manually. Two forms of data sets (volume of interest [VOI] data sets and slice data sets) were analyzed, respectively. The models based on single parameter and multiparameter models were developed and validated to predict HT in AIS patients after EVT. Performance was evaluated by area under the receiver-operating characteristic curve (AUC), accuracy (ACC), sensitivity, specificity, negative predictive value, and positive predictive value. The results showed that the performance of single parameter model based on MTT (VOI data set: AUC = 0.933, ACC = 0.843; slice data set: AUC = 0.945, ACC = 0.833) and TTP (VOI data set: AUC = 0.916, ACC = 0.873; slice data set: AUC = 0.889, ACC = 0.818) were better than the other single parameter model. The multiparameter model based on DWI & MTT & TTP & Clinical (DMTC) had the best performance for predicting HT (VOI data set: AUC = 0.948, ACC = 0.892; slice data set: AUC = 0.932, ACC = 0.873). The DMTC model in the external validation set achieved similar performance with the testing set (VOI data set: AUC = 0.939, ACC = 0.884; slice data set: AUC = 0.927, ACC = 0.871) (p > 0.05). The proposed clinical, DWI, and PWI multiparameter DL model has great potential for assisting the periprocedural management in the early prediction HT of the AIS patients with EVT.
Collapse
Affiliation(s)
- Liang Jiang
- Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Leilei Zhou
- Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Wei Yong
- Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Jinluan Cui
- Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Wen Geng
- Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Huiyou Chen
- Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Jianjun Zou
- Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Yang Chen
- Laboratory of Image Science and Technology, School of Computer Science and Engineering, Southeast University, Nanjing, China
| | - Xindao Yin
- Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Yu-Chen Chen
- Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| |
Collapse
|
17
|
Gwak DS, Choi W, Shim DH, Kim YW, Kang DH, Son W, Hwang YH. Role of Apparent Diffusion Coefficient Gradient Within Diffusion Lesions in Outcomes of Large Stroke After Thrombectomy. Stroke 2021; 53:921-929. [PMID: 34583532 DOI: 10.1161/strokeaha.121.035615] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
BACKGROUND AND PURPOSE The outcome of endovascular treatment in stroke patients with a large ischemic core is not always satisfactory. We evaluated whether the severity of baseline diffusion-weighted imaging abnormalities, as assessed by different apparent diffusion coefficient (ADC) thresholds, correlates with the clinical outcome in these patients after successful endovascular treatment. METHODS In 82 consecutive patients with a large vessel occlusion in the anterior circulation admitted ≤24 hours after onset, a baseline diffusion lesion volume (ADC ≤620×10-6 mm2/s [ADC620]) ≥50 mL and successful recanalization by endovascular treatment were retrospectively investigated. Lesion volumes of 3 ADC thresholds (ADC620, ADC ≤520×10-6 mm2/s [ADC520], and ADC ≤540×10-6 mm2/s [ADC540]) were measured using an automated Olea software program. The performance of the ADC520/ADC620 and ADC540/ADC620 ratios in predicting the functional outcome was assessed by receiver operating characteristic curve analysis. The ADC ratio with optimal threshold showing better receiver operating characteristic performance was dichotomized at its median value into low versus high subgroup and its association with the outcome subsequently evaluated in a multivariable logistic regression model. RESULTS The median baseline diffusion lesion volume was 80.8 mL (interquartile range, 64.4-105.4). A good functional outcome (modified Rankin Scale score, ≤2) was achieved in 35 patients (42.7%). The optimal threshold for predicting the functional outcome was identified as ADC540/ADC620 (area under the curve, 0.833) and dichotomized at 0.674. After adjusting for age, baseline National Institutes of Health Stroke Scale score, intravenous tissue-type plasminogen activator, baseline diffusion lesion volume, and onset-to-recanalization time, a low ADC540/ADC620 was independently associated with a good functional outcome (adjusted odds ratio, 10.72 [95% CI, 3.06-37.50]; P<0.001). CONCLUSIONS A low ADC540/ADC620, which may reflect less severe ischemic stress inside a diffusion lesion, may help to identify patients who would benefit from endovascular treatment despite having a large ischemic core.
Collapse
Affiliation(s)
- Dong-Seok Gwak
- Department of Neurology, Kyungpook National University Hospital, Daegu, Republic of Korea (D.-S.G., W.C.C., D.-H.S., Y.-W.K., Y.-H.H.)
| | - WooChan Choi
- Department of Neurology, Kyungpook National University Hospital, Daegu, Republic of Korea (D.-S.G., W.C.C., D.-H.S., Y.-W.K., Y.-H.H.)
| | - Dong-Hyun Shim
- Department of Neurology, Kyungpook National University Hospital, Daegu, Republic of Korea (D.-S.G., W.C.C., D.-H.S., Y.-W.K., Y.-H.H.)
| | - Yong-Won Kim
- Department of Neurology, Kyungpook National University Hospital, Daegu, Republic of Korea (D.-S.G., W.C.C., D.-H.S., Y.-W.K., Y.-H.H.).,Department of Neurology, School of Medicine, Kyungpook National University, Daegu, Republic of Korea. (Y.-W.K., Y.-H.H.)
| | - Dong-Hun Kang
- Department of Radiology, School of Medicine, Kyungpook National University, Daegu, Republic of Korea. (D.-H.K., W.S.).,Department of Neurosurgery, School of Medicine, Kyungpook National University, Daegu, Republic of Korea. (D.-H.K., W.S.)
| | - Wonsoo Son
- Department of Radiology, School of Medicine, Kyungpook National University, Daegu, Republic of Korea. (D.-H.K., W.S.).,Department of Neurosurgery, School of Medicine, Kyungpook National University, Daegu, Republic of Korea. (D.-H.K., W.S.)
| | - Yang-Ha Hwang
- Department of Neurology, Kyungpook National University Hospital, Daegu, Republic of Korea (D.-S.G., W.C.C., D.-H.S., Y.-W.K., Y.-H.H.).,Department of Neurology, School of Medicine, Kyungpook National University, Daegu, Republic of Korea. (Y.-W.K., Y.-H.H.)
| |
Collapse
|
18
|
Krusche C, Rio Bartulos C, Abu-Mugheisib M, Haimerl M, Wiggermann P. Dynamic perfusion analysis in acute ischemic stroke: A comparative study of two different softwares. Clin Hemorheol Microcirc 2021; 79:55-63. [PMID: 34420946 DOI: 10.3233/ch-219106] [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] [Indexed: 12/26/2022]
Abstract
BACKGROUND In clinical practice, decisions often must be made rapidly; therefore, automated software is useful for diagnostic support. Perfusion computed tomography and follow-up evaluation of perfusion data are valuable tools for selecting the optimal recanalization therapy in patients with acute ischemic stroke. OBJECTIVE This study aimed to compare commercially available software used to evaluate stroke patients prior to thrombectomy. METHODS The performance of Olea Sphere (OlS) software vs. CT Neuro Perfusion from Syngo (Sy), as well as the electronic Alberta Stroke Program Early Computed Tomography Score (e-ASPECTS) software vs. an experienced radiologist, were compared using descriptive statistics including significance analysis, Spearman's correlation, and the Bland-Altman agreement analysis. For this purpose, 43 data sets of patients with stroke symptoms related to the middle cerebral artery territory were retrospectively post-processed with both tools and analyzed. RESULTS The automatic e-ASPECTS showed high agreement with an expert rater assessment of the ASPECTS. Using OlS and Sy, we compared the parameters for the ischemic core (relative cerebral blood flow), Time to maximum (Tmax) for the penumbra, and the relative mismatch between these two values. Overall, both software tools achieved good agreement, and their respective values correlated well with each other. However, OlS predicted significantly smaller infarct core volumes compared with Sy. CONCLUSIONS Although the absolute values have a certain degree of variation, both software programs have good agreement with each other.
Collapse
Affiliation(s)
- Cornelius Krusche
- Institut für Röntgendiagnostik und Nuklearmedizin, Städtisches Klinikum Braunschweig gGmbH, Salzdahlumer str. 90, Braunschweig, Germany
| | - Carolina Rio Bartulos
- Institut für Röntgendiagnostik und Nuklearmedizin, Städtisches Klinikum Braunschweig gGmbH, Salzdahlumer str. 90, Braunschweig, Germany
| | - Mazen Abu-Mugheisib
- Klinik für Neurologie, Städtisches Klinikum Braunschweig gGmbH, Braunschweig, Germany
| | - Michael Haimerl
- Institut für Röntgendiagnostik, Universtitätsklinikum Regensburg, Regensburg, Germany
| | - Philipp Wiggermann
- Institut für Röntgendiagnostik und Nuklearmedizin, Städtisches Klinikum Braunschweig gGmbH, Salzdahlumer str. 90, Braunschweig, Germany
| |
Collapse
|
19
|
MRI software for diffusion-perfusion mismatch analysis may impact on patients' selection and clinical outcome. Eur Radiol 2021; 32:1144-1153. [PMID: 34350507 PMCID: PMC8794935 DOI: 10.1007/s00330-021-08211-2] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2021] [Revised: 06/18/2021] [Accepted: 07/09/2021] [Indexed: 11/25/2022]
Abstract
Objective Impact of different MR perfusion software on selection and outcome of patients with acute ischemic stroke (AIS) and large vessel occlusion (LVO) treated by endovascular thrombectomy (EVT) is unclear. We aimed at comparing two commercial MRI software, semi-automated with unadjusted (method A) and adjusted mask (method B), and fully automated (method C) in this setting. Methods MRI from 144 consecutive AIS patients with anterior circulation LVO was retrospectively analysed. All diffusion- and perfusion-weighted images (DWI-PWI) were post-processed with the three methods using standard thresholds. Concordance for core and hypoperfusion volumes was assessed with Lin’s test. Clinical outcome was compared between groups in patients who underwent successful EVT in the early and late time window. Results Mean core volume was higher and mean hypoperfusion volume was lower in method C than in methods A and B. In the early time window, methods A and B found fewer patients with a mismatch ratio ≤ 1.2 than method C (1/67 [1.5%] vs. 12/67 [17.9%], p = 0.0013). In the late time window, methods A and B found fewer patients with a mismatch ratio < 1.8 than method C (3/46 [6.5%] and 2/46 [4.3%] vs. 18/46 [39.1%], p ≤ 0.0002). More patients with functional independence at 3 months would not have been treated using method C versus methods A and B in the early (p = 0.0063) and late (p ≤ 0.011) time window. Conclusions MRI software for DWI-PWI analysis may influence patients’ selection before EVT and clinical outcome. Key Points • Method C detects fewer patients with favourable mismatch profile. • Method C might underselect more patients with functional independence at 3 months. • Software used before thrombectomy may influence patients’ outcome.
Collapse
|
20
|
Muddasani V, de Havenon A, McNally JS, Baradaran H, Alexander MD. MR Perfusion in the Evaluation of Mechanical Thrombectomy Candidacy. Top Magn Reson Imaging 2021; 30:197-204. [PMID: 34397969 PMCID: PMC8371677 DOI: 10.1097/rmr.0000000000000277] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
ABSTRACT Stroke is a leading cause of disability and mortality, and the incidence of ischemic stroke is projected to continue to rise in coming decades. These projections emphasize the need for improved imaging techniques for accurate diagnosis allowing effective treatments for ischemic stroke. Ischemic stroke is commonly evaluated with computed tomography (CT) or magnetic resonance imaging (MRI). Noncontrast CT is typically used within 4.5 hours of symptom onset to identify candidates for thrombolysis. Beyond this time window, thrombolytic therapy may lead to poor outcomes if patients are not optimally selected using appropriate imaging. MRI provides an accurate method for the earliest identification of core infarct, and MR perfusion can identify salvageable hypoperfused penumbra. The prognostic value for a better outcome in these patients lies in the ability to distinguish between core infarct and salvageable brain at risk-the ischemic penumbra-which is a function of the degree of ischemia and time. Many centers underutilize MRI for acute evaluation of ischemic stroke. This review will illustrate how perfusion-diffusion mismatch calculated from diffusion-weighted MRI and MR perfusion is a reliable approach for patient selection for stroke therapy and can be performed in timeframes that are comparable to CT-based algorithms while providing potentially superior diagnostic information.
Collapse
Affiliation(s)
| | - Adam de Havenon
- Department of Neurology, University of Utah, Salt Lake City, UT
| | - J Scott McNally
- Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, UT
| | - Hediyeh Baradaran
- Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, UT
| | - Matthew D Alexander
- Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, UT
- Department of Neurosurgery, University of Utah, Salt Lake City, UT
| |
Collapse
|