1
|
Sarraj A, Hassan AE, Abraham MG, Ortega-Gutierrez S, Kasner SE, Hussain MS, Chen M, Churilov L, Johns H, Sitton CW, Yogendrakumar V, Ng FC, Pujara DK, Blackburn S, Sundararajan S, Hu YC, Herial NA, Arenillas JF, Tsai JP, Budzik RF, Hicks WJ, Kozak O, Yan B, Cordato DJ, Manning NW, Parsons MW, Cheung A, Hanel RA, Aghaebrahim AN, Wu TY, Portela PC, Gandhi CD, Al-Mufti F, Pérez de la Ossa N, Schaafsma JD, Blasco J, Sangha N, Warach S, Kleinig TJ, Shaker F, Al Shaibi F, Toth G, Abdulrazzak MA, Sharma G, Ray A, Sunshine J, Opaskar A, Duncan KR, Xiong W, Samaniego EA, Maali L, Lechtenberg CG, Renú A, Vora N, Nguyen T, Fifi JT, Tjoumakaris SI, Jabbour P, Tsivgoulis G, Pereira VM, Lansberg MG, DeGeorgia M, Sila CA, Bambakidis N, Hill MD, Davis SM, Wechsler L, Grotta JC, Ribo M, Albers GW, Campbell BC. Endovascular Thrombectomy for Large Ischemic Stroke Across Ischemic Injury and Penumbra Profiles. JAMA 2024; 331:750-763. [PMID: 38324414 PMCID: PMC10851143 DOI: 10.1001/jama.2024.0572] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/28/2023] [Accepted: 01/16/2024] [Indexed: 02/09/2024]
Abstract
Importance Whether endovascular thrombectomy (EVT) efficacy for patients with acute ischemic stroke and large cores varies depending on the extent of ischemic injury is uncertain. Objective To describe the relationship between imaging estimates of irreversibly injured brain (core) and at-risk regions (mismatch) and clinical outcomes and EVT treatment effect. Design, Setting, and Participants An exploratory analysis of the SELECT2 trial, which randomized 352 adults (18-85 years) with acute ischemic stroke due to occlusion of the internal carotid or middle cerebral artery (M1 segment) and large ischemic core to EVT vs medical management (MM), across 31 global centers between October 2019 and September 2022. Intervention EVT vs MM. Main Outcomes and Measures Primary outcome was functional outcome-90-day mRS score (0, no symptoms, to 6, death) assessed by adjusted generalized OR (aGenOR; values >1 represent more favorable outcomes). Benefit of EVT vs MM was assessed across levels of ischemic injury defined by noncontrast CT using ASPECTS score and by the volume of brain with severely reduced blood flow on CT perfusion or restricted diffusion on MRI. Results Among 352 patients randomized, 336 were analyzed (median age, 67 years; 139 [41.4%] female); of these, 168 (50%) were randomized to EVT, and 2 additional crossover MM patients received EVT. In an ordinal analysis of mRS at 90 days, EVT improved functional outcomes compared with MM within ASPECTS categories of 3 (aGenOR, 1.71 [95% CI, 1.04-2.81]), 4 (aGenOR, 2.01 [95% CI, 1.19-3.40]), and 5 (aGenOR, 1.85 [95% CI, 1.22-2.79]). Across strata for CT perfusion/MRI ischemic core volumes, aGenOR for EVT vs MM was 1.63 (95% CI, 1.23-2.16) for volumes ≥70 mL, 1.41 (95% CI, 0.99-2.02) for ≥100 mL, and 1.47 (95% CI, 0.84-2.56) for ≥150 mL. In the EVT group, outcomes worsened as ASPECTS decreased (aGenOR, 0.91 [95% CI, 0.82-1.00] per 1-point decrease) and as CT perfusion/MRI ischemic core volume increased (aGenOR, 0.92 [95% CI, 0.89-0.95] per 10-mL increase). No heterogeneity of EVT treatment effect was observed with or without mismatch, although few patients without mismatch were enrolled. Conclusion and Relevance In this exploratory analysis of a randomized clinical trial of patients with extensive ischemic stroke, EVT improved clinical outcomes across a wide spectrum of infarct volumes, although enrollment of patients with minimal penumbra volume was low. In EVT-treated patients, clinical outcomes worsened as presenting ischemic injury estimates increased. Trial Registration ClinicalTrials.gov Identifier: NCT03876457.
Collapse
Affiliation(s)
- Amrou Sarraj
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | | | | | | | | | | | - Michael Chen
- Rush University Medical Center, Chicago, Illinois
| | - Leonid Churilov
- The Melbourne Brain Centre, Royal Melbourne Hospital and University of Melbourne, Melbourne, Victoria, Australia
| | - Hannah Johns
- The Melbourne Brain Centre, Royal Melbourne Hospital and University of Melbourne, Melbourne, Victoria, Australia
| | | | - Vignan Yogendrakumar
- The Melbourne Brain Centre, Royal Melbourne Hospital and University of Melbourne, Melbourne, Victoria, Australia
| | - Felix C. Ng
- The Melbourne Brain Centre, Royal Melbourne Hospital and University of Melbourne, Melbourne, Victoria, Australia
| | - Deep K. Pujara
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | | | - Sophia Sundararajan
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | - Yin C. Hu
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | - Nabeel A. Herial
- Thomas Jefferson University Hospital, Philadelphia, Pennsylvania
| | - Juan F. Arenillas
- Hospital Clínico Universitario Valladolid—University of Valladolid, Valladolid, Spain
| | | | | | | | - Osman Kozak
- Abington Jefferson Health, Abington, Pennsylvania
| | - Bernard Yan
- The Melbourne Brain Centre, Royal Melbourne Hospital and University of Melbourne, Melbourne, Victoria, Australia
| | | | | | | | - Andrew Cheung
- Liverpool Hospital, Liverpool, New South Wales, Australia
| | | | | | - Teddy Y. Wu
- Christchurch Hospital, Christchurch, New Zealand
| | | | | | - Fawaz Al-Mufti
- Westchester Medical Center, New York Medical College, Valhalla
| | | | | | | | | | - Steven Warach
- Dell Medical School at The University of Texas at Austin–Ascension Texas, Austin
| | | | - Faris Shaker
- McGovern Medical School at UTHealth, Houston, Texas
| | - Faisal Al Shaibi
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | | | | | - Gagan Sharma
- The Melbourne Brain Centre, Royal Melbourne Hospital and University of Melbourne, Melbourne, Victoria, Australia
| | - Abhishek Ray
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | - Jeffrey Sunshine
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | - Amanda Opaskar
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | - Kelsey R. Duncan
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | - Wei Xiong
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | | | - Laith Maali
- University of Kansas Medical Center, Kansas City
| | | | - Arturo Renú
- Hospital Clínic de Barcelona, Barcelona, Spain
| | - Nirav Vora
- Riverside Methodist Hospital, OhioHealth, Columbus
| | | | | | | | - Pascal Jabbour
- Thomas Jefferson University Hospital, Philadelphia, Pennsylvania
| | - Georgios Tsivgoulis
- Attikon University Hospital, National and Kapodistrian University of Athens, Athens, Greece
| | | | | | - Michael DeGeorgia
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | - Cathy A. Sila
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | - Nicholas Bambakidis
- University Hospital Cleveland Medical Center—Case Western Reserve University, Cleveland, Ohio
| | | | - Stephen M. Davis
- The Melbourne Brain Centre, Royal Melbourne Hospital and University of Melbourne, Melbourne, Victoria, Australia
| | | | | | - Marc Ribo
- Hospital Vall d’Hebrón, Barcelona, Spain
| | | | - Bruce C. Campbell
- The Melbourne Brain Centre, Royal Melbourne Hospital and University of Melbourne, Melbourne, Victoria, Australia
- Florey Institute for Neuroscience and Mental Health, Parkville, Victoria, Australia
| |
Collapse
|
2
|
Christensen S, Demeestere J, Verhaaren B, Heit JJ, Von Stein EL, Madill ES, Loube DK, Dugue R, Rengarajan S, Mlynash M, Albers GW, Lemmens R, Lansberg MG. Semiautomated Detection of Early Infarct Signs on Noncontrast CT Improves Interrater Agreement. Stroke 2023; 54:3090-3096. [PMID: 37909206 PMCID: PMC10843172 DOI: 10.1161/strokeaha.123.044058] [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: 06/05/2023] [Accepted: 10/13/2023] [Indexed: 11/02/2023]
Abstract
BACKGROUND Acute ischemic infarct identification on noncontrast computed tomography (NCCT) is highly variable between raters. A semiautomated method for segmentation of acute ischemic lesions on NCCT may improve interrater reliability. METHODS Patients with successful endovascular reperfusion from the DEFUSE 3 trial (Endovascular Therapy Following Imaging Evaluation for Ischemic Stroke) were included. We created relative NCCT (rNCCT) color-gradient overlays by comparing the density of a voxel on NCCT to the homologous region in the contralateral hemisphere. Regions with a relative hypodensity of at least 5% were visualized. We coregistered baseline and follow-up images. Two neuroradiologists and 6 nonradiologists segmented the acute ischemic lesion on the baseline scans with 2 methods: (1) manually outlining hypodense regions on the NCCT (unassisted segmentation) and (2) manually excluding areas deemed outside of the ischemic lesion on the rNCCT color map (rNCCT-assisted segmentation). Voxelwise interrater agreement was quantified using the Dice similarity coefficient and volumetric agreement between raters with the detection index (DI), defined as the true positive volume minus the false positive volume. RESULTS From a total of 92, we included 61 patients. Median age was 59 (64-77), and 57% were female. Stroke onset was known in 39%. Onset to NCCT was median, 8.5 hours (7-11) and median 10 hours (8.4-11.5) in patients with known and unknown onset, respectively. Compared with unassisted NCCT segmentation, rNCCT-assisted segmentation increased the Dice similarity coefficient by >50% for neuroradiologists (Dice similarity coefficient, 0.38 versus 0.83; P<0.001) and nonradiologists (Dice similarity coefficient, 0.14 versus 0.84; P<0.001), and improved the DI among nonradiologists (mean improvement, 5.8 mL [95% CI, 3.1-8.5] mL, P<0.001) but not among neuroradiologists. CONCLUSIONS The high variability of manual segmentations of the acute ischemic lesion on NCCT is greatly reduced using semiautomated rNCCT. The rNCCT map may therefore aid acute infarct detection and provide more reliable infarct estimates for clinicians with less experience.
Collapse
Affiliation(s)
| | - Jelle Demeestere
- KU Leuven – University of Leuven, Department of Neurosciences, Experimental Neurology, Leuven, Belgium
- University Hospitals Leuven, Department of Neurology, Leuven, Belgium
| | | | | | | | | | | | | | | | | | | | - Robin Lemmens
- KU Leuven – University of Leuven, Department of Neurosciences, Experimental Neurology, Leuven, Belgium
- University Hospitals Leuven, Department of Neurology, Leuven, Belgium
| | | |
Collapse
|
3
|
Shahrouki P, Kihira S, Tavakkol E, Qiao JX, Vagal A, Khatri P, Bahr-Hosseini M, Colby GP, Jahan R, Duckwiler G, Szeder V, Ledbetter L, Cai S, Salehi B, Doshi AH, Belani P, Fifi JT, De Leacy R, Mocco J, Saver JL, Liebeskind DS, Nael K. Automated assessment of ischemic core on non-contrast computed tomography: a multicenter comparative analysis with CT perfusion. J Neurointerv Surg 2023:jnis-2023-020954. [PMID: 37918907 DOI: 10.1136/jnis-2023-020954] [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: 08/26/2023] [Accepted: 10/13/2023] [Indexed: 11/04/2023]
Abstract
BACKGROUND Application of machine learning (ML) algorithms has shown promising results in estimating ischemic core volumes using non-contrast CT (NCCT). OBJECTIVE To assess the performance of the e-Stroke Suite software (Brainomix) in assessing ischemic core volumes on NCCT compared with CT perfusion (CTP) in patients with acute ischemic stroke. METHODS In this retrospective multicenter study, patients with anterior circulation large vessel occlusions who underwent pretreatment NCCT and CTP, successful reperfusion (modified Thrombolysis in Cerbral Infarction ≥2b), and post-treatment MRI, were included from three stroke centers. Automated calculation of ischemic core volumes was obtained on NCCT scans using ML algorithm deployed by e-Stroke Suite and from CTP using Olea software (Olea Medical). Comparative analysis was performed between estimated core volumes on NCCT and CTP and against MRI calculated final infarct volume (FIV). RESULTS A total of 111 patients were included. Estimated ischemic core volumes (mean±SD, mL) were 20.4±19.0 on NCCT and 19.9±18.6 on CTP, not significantly different (P=0.82). There was moderate (r=0.40) and significant (P<0.001) correlation between estimated core on NCCT and CTP. The mean difference between FIV and estimated core volume on NCCT and CTP was 29.9±34.6 mL and 29.6±35.0 mL, respectively (P=0.94). Correlations between FIV and estimated core volume were similar for NCCT (r=0.30, P=0.001) and CTP (r=0.36, P<0.001). CONCLUSIONS Results show that ML-based estimated ischemic core volumes on NCCT are comparable to those obtained from concurrent CTP in magnitude and in degree of correlation with MR-assessed FIV.
Collapse
Affiliation(s)
- Puja Shahrouki
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Shingo Kihira
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Elham Tavakkol
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Joe X Qiao
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Achala Vagal
- Department of Radiology, University of Cincinnati Medical Center, Cincinnati, Ohio, USA
| | - Pooja Khatri
- Department of Neurology, University of Cincinnati, Cincinnati, Ohio, USA
| | - Mersedeh Bahr-Hosseini
- Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Geoffrey P Colby
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
- Department of Neurosurgery, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Reza Jahan
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Gary Duckwiler
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Viktor Szeder
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
- Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Luke Ledbetter
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Stephen Cai
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Banafsheh Salehi
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Amish H Doshi
- Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Puneet Belani
- Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Johanna T Fifi
- Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Reade De Leacy
- Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - J Mocco
- Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Jeffrey L Saver
- Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - David S Liebeskind
- Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| | - Kambiz Nael
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA
| |
Collapse
|
4
|
Chen IE, Tsui B, Zhang H, Qiao JX, Hsu W, Nour M, Salamon N, Ledbetter L, Polson J, Arnold C, BahrHossieni M, Jahan R, Duckwiler G, Saver J, Liebeskind D, Nael K. Automated estimation of ischemic core volume on noncontrast-enhanced CT via machine learning. Interv Neuroradiol 2022:15910199221145487. [PMID: 36572984 DOI: 10.1177/15910199221145487] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/28/2022] Open
Abstract
BACKGROUND Accurate estimation of ischemic core on baseline imaging has treatment implications in patients with acute ischemic stroke (AIS). Machine learning (ML) algorithms have shown promising results in estimating ischemic core using routine noncontrast computed tomography (NCCT). OBJECTIVE We used an ML-trained algorithm to quantify ischemic core volume on NCCT in a comparative analysis to pretreatment magnetic resonance imaging (MRI) diffusion-weighted imaging (DWI) in patients with AIS. METHODS Patients with AIS who had both pretreatment NCCT and MRI were enrolled. An automatic segmentation ML approach was applied using Brainomix software (Oxford, UK) to segment the ischemic voxels and calculate ischemic core volume on NCCT. Ischemic core volume was also calculated on baseline MRI DWI. Comparative analysis was performed using Bland-Altman plots and Pearson correlation. RESULTS A total of 72 patients were included. The time-to-stroke onset time was 134.2/89.5 minutes (mean/median). The time difference between NCCT and MRI was 64.8/44.5 minutes (mean/median). In patients who presented within 1 hour from stroke onset, the ischemic core volumes were significantly (p = 0.005) underestimated by ML-NCCT. In patients presented beyond 1 hour, the ML-NCCT estimated ischemic core volumes approximated those obtained by MRI-DWI and with significant correlation (r = 0.56, p < 0.001). CONCLUSION The ischemic core volumes calculated by the described ML approach on NCCT approximate those obtained by MRI in patients with AIS who present beyond 1 hour from stroke onset.
Collapse
Affiliation(s)
- Iris E Chen
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Brian Tsui
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Haoyue Zhang
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Joe X Qiao
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - William Hsu
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - May Nour
- Department of Neurology, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Noriko Salamon
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Luke Ledbetter
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Jennifer Polson
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Corey Arnold
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Mersedeh BahrHossieni
- Department of Neurology, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Reza Jahan
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Gary Duckwiler
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Jeffrey Saver
- Department of Neurology, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - David Liebeskind
- Department of Neurology, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| | - Kambiz Nael
- Department of Radiological Sciences, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, CA, USA
| |
Collapse
|
5
|
Automated Cerebral Infarct Detection on Computed Tomography Images Based on Deep Learning. Biomedicines 2022; 10:biomedicines10010122. [PMID: 35052801 PMCID: PMC8773678 DOI: 10.3390/biomedicines10010122] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2021] [Revised: 01/02/2022] [Accepted: 01/04/2022] [Indexed: 02/01/2023] Open
Abstract
The limited accuracy of cerebral infarct detection on CT images caused by the low contrast of CT hinders the desirable application of CT as a first-line diagnostic modality for screening of cerebral infarct. This research was aimed at utilizing convolutional neural network to enhance the accuracy of automated cerebral infarct detection on CT images. The CT images underwent a series of preprocessing steps mainly to enhance the contrast inside the parenchyma, adjust the orientation, spatially normalize the images to the CT template, and create a t-score map for each patient. The input format of the convolutional neural network was the t-score matrix of a 16 × 16-pixel patch. Non-infarcted and infarcted patches were selected from the t-score maps, on which data augmentation was conducted to generate more patches for training and testing the proposed convolutional neural network. The convolutional neural network attained a 93.9% patch-wise detection accuracy in the test set. The proposed method offers prompt and accurate cerebral infarct detection on CT images. It renders a frontline detection modality of ischemic stroke on an emergent or regular basis.
Collapse
|
6
|
Inamdar MA, Raghavendra U, Gudigar A, Chakole Y, Hegde A, Menon GR, Barua P, Palmer EE, Cheong KH, Chan WY, Ciaccio EJ, Acharya UR. A Review on Computer Aided Diagnosis of Acute Brain Stroke. SENSORS (BASEL, SWITZERLAND) 2021; 21:8507. [PMID: 34960599 PMCID: PMC8707263 DOI: 10.3390/s21248507] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/04/2021] [Revised: 12/05/2021] [Accepted: 12/09/2021] [Indexed: 01/01/2023]
Abstract
Amongst the most common causes of death globally, stroke is one of top three affecting over 100 million people worldwide annually. There are two classes of stroke, namely ischemic stroke (due to impairment of blood supply, accounting for ~70% of all strokes) and hemorrhagic stroke (due to bleeding), both of which can result, if untreated, in permanently damaged brain tissue. The discovery that the affected brain tissue (i.e., 'ischemic penumbra') can be salvaged from permanent damage and the bourgeoning growth in computer aided diagnosis has led to major advances in stroke management. Abiding to the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines, we have surveyed a total of 177 research papers published between 2010 and 2021 to highlight the current status and challenges faced by computer aided diagnosis (CAD), machine learning (ML) and deep learning (DL) based techniques for CT and MRI as prime modalities for stroke detection and lesion region segmentation. This work concludes by showcasing the current requirement of this domain, the preferred modality, and prospective research areas.
Collapse
Affiliation(s)
- Mahesh Anil Inamdar
- Department of Mechatronics, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India;
| | - Udupi Raghavendra
- Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India; (A.G.); (Y.C.)
| | - Anjan Gudigar
- Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India; (A.G.); (Y.C.)
| | - Yashas Chakole
- Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India; (A.G.); (Y.C.)
| | - Ajay Hegde
- Department of Neurosurgery, Kasturba Medical College, Manipal Academy of Higher Education, Manipal 576104, India; (A.H.); (G.R.M.)
| | - Girish R. Menon
- Department of Neurosurgery, Kasturba Medical College, Manipal Academy of Higher Education, Manipal 576104, India; (A.H.); (G.R.M.)
| | - Prabal Barua
- School of Management & Enterprise, University of Southern Queensland, Toowoomba, QLD 4350, Australia;
- Faculty of Engineering and Information Technology, University of Technology, Sydney, NSW 2007, Australia
- Cogninet Brain Team, Cogninet Australia, Sydney, NSW 2010, Australia
| | - Elizabeth Emma Palmer
- School of Women’s and Children’s Health, University of New South Wales, Sydney, NSW 2052, Australia;
| | - Kang Hao Cheong
- Science, Mathematics and Technology Cluster, Singapore University of Technology and Design, Singapore 487372, Singapore;
| | - Wai Yee Chan
- Department of Biomedical Imaging, Research Imaging Centre, University of Malaya, Kuala Lumpur 59100, Malaysia;
| | - Edward J. Ciaccio
- Department of Medicine, Columbia University, New York, NY 10032, USA;
| | - U. Rajendra Acharya
- Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia;
- School of Engineering, Ngee Ann Polytechnic, Singapore 599489, Singapore
- Department of Biomedical Engineering, School of Science and Technology, SUSS University, Singapore 599491, Singapore
- Department of Biomedical Informatics and Medical Engineering, Asia University, Taichung 41354, Taiwan
| |
Collapse
|
7
|
El-Hariri H, Souto Maior Neto LA, Cimflova P, Bala F, Golan R, Sojoudi A, Duszynski C, Elebute I, Mousavi SH, Qiu W, Menon BK. Evaluating nnU-Net for early ischemic change segmentation on non-contrast computed tomography in patients with Acute Ischemic Stroke. Comput Biol Med 2021; 141:105033. [PMID: 34802712 DOI: 10.1016/j.compbiomed.2021.105033] [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: 08/09/2021] [Revised: 11/04/2021] [Accepted: 11/10/2021] [Indexed: 01/29/2023]
Abstract
Identifying the presence and extent of early ischemic changes (EIC) on Non-Contrast Computed Tomography (NCCT) is key to diagnosing and making time-sensitive treatment decisions in patients that present with Acute Ischemic Stroke (AIS). Segmenting EIC on NCCT is however a challenging task. In this study, we investigated a 3D CNN based on nnU-Net, a self-adapting CNN technique that has become the state-of-the-art in medical image segmentation, for segmenting EIC in NCCT of AIS patients. We trained and tested this model on a sizeable and heterogenous dataset of 534 patients, split into 438 for training and validation and 96 for testing. On this test set, we additionally assessed the inter-rater performance by comparing the proposed approach against two reference segmentation annotations by expert neuroradiologist readers, using this as the benchmark against which to compare our model. In terms of spatial agreement, we report median Dice Similarity Coefficients (DSCs) of 39.8% for the model vs. Reader-1, 39.4% for the model vs. Reader-2, and 55.6% for Reader-2 vs. Reader-1. In terms of lesion volume agreement, we report Intraclass Correlation Coefficients (ICCs) of 83.4% for model vs. Reader-1, 80.4% for model vs. Reader-2, and 94.8% for Reader-2 vs. Reader-1. Based on these results, we conclude that our model performs well relative to expert human performance and therefore may be useful as a decision-aid for clinicians.
Collapse
Affiliation(s)
| | | | - Petra Cimflova
- Department of Clinical Neurosciences, Foothills Medical Center, University of Calgary, Calgary, AB, Canada; Department of Medical Imaging, St. Anne's University Hospital Brno and Faculty of Medicine, Masaryk University, Brno, Czech Republic; Faculty of Medicine and University Hospital, Hradec Kralove, Czech Republic; Department of Radiology, Cumming School of Medicine, University of Calgary, Canada
| | - Fouzi Bala
- Department of Clinical Neurosciences, Foothills Medical Center, University of Calgary, Calgary, AB, Canada
| | - Rotem Golan
- Circle Neurovascular Imaging Inc, Calgary, AB, Canada
| | | | | | | | | | - Wu Qiu
- Department of Clinical Neurosciences, Foothills Medical Center, University of Calgary, Calgary, AB, Canada
| | - Bijoy K Menon
- Department of Clinical Neurosciences, Foothills Medical Center, University of Calgary, Calgary, AB, Canada; Department of Radiology, Cumming School of Medicine, University of Calgary, Canada; Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Canada; Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Canada
| |
Collapse
|
8
|
Kuang H, Menon BK, Sohn SI, Qiu W. EIS-Net: Segmenting early infarct and scoring ASPECTS simultaneously on non-contrast CT of patients with acute ischemic stroke. Med Image Anal 2021; 70:101984. [PMID: 33676101 DOI: 10.1016/j.media.2021.101984] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2020] [Revised: 12/14/2020] [Accepted: 01/25/2021] [Indexed: 11/29/2022]
Abstract
Detecting early infarct (EI) plays an essential role in patient selection for reperfusion therapy in the management of acute ischemic stroke (AIS). EI volume at acute or hyper-acute stage can be measured using advanced pre-treatment imaging, such as MRI and CT perfusion. In this study, a novel multi-task learning approach, EIS-Net, is proposed to segment EI and score Alberta Stroke Program Early CT Score (ASPECTS) simultaneously on baseline non-contrast CT (NCCT) scans of AIS patients. The EIS-Net comprises of a 3D triplet convolutional neural network (T-CNN) for EI segmentation and a multi-region classification network for ASPECTS scoring. T-CNN has triple encoders with original NCCT, mirrored NCCT, and atlas as inputs, as well as one decoder. A comparison disparity block (CDB) is designed to extract and enhance image contexts. In the decoder, a multi-level attention gate module (MAGM) is developed to recalibrate the features of the decoder for both segmentation and classification tasks. Evaluations using a high-quality dataset comprising of baseline NCCT and concomitant diffusion weighted MRI (DWI) as reference standard of 260 patients with AIS show that the proposed EIS-Net can accurately segment EI. The EIS-Net segmented EI volume strongly correlates with EI volume on DWI (r=0.919), and the mean difference between the two volumes is 8.5 mL. For ASPECTS scoring, the proposed EIS-Net achieves an intraclass correlation coefficient of 0.78 for total 10-point ASPECTS and a kappa of 0.75 for dichotomized ASPECTS (≤ 4 vs. >4). Both EI segmentation and ASPECTS scoring tasks achieve state-of-the-art performances.
Collapse
Affiliation(s)
- Hulin Kuang
- Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, China; Department of Clinical Neuroscience, the University of Calgary, Calgary, Alberta, Canada
| | - Bijoy K Menon
- Department of Clinical Neuroscience, the University of Calgary, Calgary, Alberta, Canada; Department of Radiology, the University of Calgary, Calgary, Alberta, Canada
| | - Sung Il Sohn
- Department of Neurology, Keimyung University Dongsan Medical Center, Daegu, South Korea
| | - Wu Qiu
- Department of Clinical Neuroscience, the University of Calgary, Calgary, Alberta, Canada; Department of Radiology, the University of Calgary, Calgary, Alberta, Canada.
| |
Collapse
|
9
|
Qiu W, Kuang H, Teleg E, Ospel JM, Sohn SI, Almekhlafi M, Goyal M, Hill MD, Demchuk AM, Menon BK. Machine Learning for Detecting Early Infarction in Acute Stroke with Non-Contrast-enhanced CT. Radiology 2020; 294:638-644. [PMID: 31990267 DOI: 10.1148/radiol.2020191193] [Citation(s) in RCA: 80] [Impact Index Per Article: 20.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
Background Identifying the presence and extent of infarcted brain tissue at baseline plays a crucial role in the treatment of patients with acute ischemic stroke (AIS). Patients with extensive infarction are unlikely to benefit from thrombolysis or thrombectomy procedures. Purpose To develop an automated approach to detect and quantitate infarction by using non-contrast-enhanced CT scans in patients with AIS. Materials and Methods Non-contrast-enhanced CT images in patients with AIS (<6 hours from symptom onset to CT) who also underwent diffusion-weighted (DW) MRI within 1 hour after AIS were obtained from May 2004 to July 2009 and were included in this retrospective study. Ischemic lesions manually contoured on DW MRI scans were used as the reference standard. An automatic segmentation approach involving machine learning (ML) was developed to detect infarction. Randomly selected nonenhanced CT images from 157 patients with the lesion labels manually contoured on DW MRI scans were used to train and validate the ML model; the remaining 100 patients independent of the derivation cohort were used for testing. The ML algorithm was quantitatively compared with the reference standard (DW MRI) by using Bland-Altman plots and Pearson correlation. Results In 100 patients in the testing data set (median age, 69 years; interquartile range [IQR]: 59-76 years; 59 men), baseline non-contrast-enhanced CT was performed within a median time of 48 minutes from symptom onset (IQR, 27-93 minutes); baseline MRI was performed a median of 38 minutes (IQR, 24-48 minutes) later. The algorithm-detected lesion volume correlated with the reference standard of expert-contoured lesion volume in acute DW MRI scans (r = 0.76, P < .001). The mean difference between the algorithm-segmented volume (median, 15 mL; IQR, 9-38 mL) and the DW MRI volume (median, 19 mL; IQR, 5-43 mL) was 11 mL (P = .89). Conclusion A machine learning approach for segmentation of infarction on non-contrast-enhanced CT images in patients with acute ischemic stroke showed good agreement with stroke volume on diffusion-weighted MRI scans. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Nael in this issue.
Collapse
Affiliation(s)
- Wu Qiu
- From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.)
| | - Hulin Kuang
- From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.)
| | - Ericka Teleg
- From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.)
| | - Johanna M Ospel
- From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.)
| | - Sung Il Sohn
- From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.)
| | - Mohammed Almekhlafi
- From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.)
| | - Mayank Goyal
- From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.)
| | - Michael D Hill
- From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.)
| | - Andrew M Demchuk
- From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.)
| | - Bijoy K Menon
- From the Calgary Stroke Program, Departments of Clinical Neurosciences (W.Q., H.K., E.T., J.M.O., M.G., M.D.H., A.M.D., B.K.M.), Radiology (M.G., M.D.H., A.M.D., B.K.M.), and Community Health Sciences (M.D.H., B.K.M.), University of Calgary, 239 Strathridge Pl SW, Calgary, AB, Canada T3H 4J2; Hotchkiss Brain Institute, Calgary, Alberta, Canada (M.G., M.D.H., A.M.D., B.K.M.), Department of Neurology, Keimyung University, Daegu, South Korea (S.I.S.); and Division of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel, Basel, Switzerland (J.M.O.)
| |
Collapse
|