1
|
Evaluation of Ischemic Penumbra in Stroke Patients Based on Deep Learning and Multimodal CT. JOURNAL OF HEALTHCARE ENGINEERING 2021. [DOI: 10.1155/2021/3215107] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
In order to investigate the value of multimodal CT for quantitative assessment of collateral circulation, ischemic semidark zone, core infarct volume in patients with acute ischemic stroke (AIS), and prognosis assessment in intravenous thrombolytic therapy, segmentation model which is based on the self-attention mechanism is prone to generate attention coefficient maps with incorrect regions of interest. Moreover, the stroke lesion is not clearly characterized, and lesion boundary is poorly differentiated from normal brain tissue, thus affecting the segmentation performance. To address this problem, a primary and secondary path attention compensation network structure is proposed, which is based on the improved global attention upsampling U-Net model. The main path network is responsible for performing accurate lesion segmentation and outputting segmentation results. Likewise, the auxiliary path network generates loose auxiliary attention compensation coefficients, which compensate for possible attention coefficient errors in the main path network. Two hybrid loss functions are proposed to realize the respective functions of main and auxiliary path networks. It is experimentally demonstrated that both the improved global attention upsampling U-Net and the proposed primary and secondary path attention compensation networks show significant improvement in segmentation performance. Moreover, patients with good collateral circulation have a small final infarct area volume and a good clinical prognosis after intravenous thrombolysis. Quantitative assessment of collateral circulation and ischemic semidark zone by multimodal CT can better predict the clinical prognosis of intravenous thrombolysis.
Collapse
|
3
|
Sheth SA, Lopez-Rivera V, Barman A, Grotta JC, Yoo AJ, Lee S, Inam ME, Savitz SI, Giancardo L. Machine Learning-Enabled Automated Determination of Acute Ischemic Core From Computed Tomography Angiography. Stroke 2019; 50:3093-3100. [PMID: 31547796 DOI: 10.1161/strokeaha.119.026189] [Citation(s) in RCA: 58] [Impact Index Per Article: 11.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Background and Purpose- The availability of and expertise to interpret advanced neuroimaging recommended in the guideline-based endovascular stroke therapy (EST) evaluation are limited. Here, we develop and validate an automated machine learning-based method that evaluates for large vessel occlusion (LVO) and ischemic core volume in patients using a widely available modality, computed tomography angiogram (CTA). Methods- From our prospectively maintained stroke registry and electronic medical record, we identified patients with acute ischemic stroke and stroke mimics with contemporaneous CTA and computed tomography perfusion (CTP) with RAPID (IschemaView) post-processing as a part of the emergent stroke workup. A novel convolutional neural network named DeepSymNet was created and trained to identify LVO as well as infarct core from CTA source images, against CTP-RAPID definitions. Model performance was measured using 10-fold cross validation and receiver-operative curve area under the curve (AUC) statistics. Results- Among the 297 included patients, 224 (75%) had acute ischemic stroke of which 179 (60%) had LVO. Mean CTP-RAPID ischemic core volume was 23±42 mL. LVO locations included internal carotid artery (13%), M1 (44%), and M2 (21%). The DeepSymNet algorithm autonomously learned to identify the intracerebral vasculature on CTA and detected LVO with AUC 0.88. The method was also able to determine infarct core as defined by CTP-RAPID from the CTA source images with AUC 0.88 and 0.90 (ischemic core ≤30 mL and ≤50 mL). These findings were maintained in patients presenting in early (0-6 hours) and late (6-24 hours) time windows (AUCs 0.90 and 0.91, ischemic core ≤50 mL). DeepSymNet probabilities from CTA images corresponded with CTP-RAPID ischemic core volumes as a continuous variable with r=0.7 (Pearson correlation, P<0.001). Conclusions- These results demonstrate that the information needed to perform the neuroimaging evaluation for endovascular therapy with comparable accuracy to advanced imaging modalities may be present in CTA, and the ability of machine learning to automate the analysis.
Collapse
Affiliation(s)
- Sunil A Sheth
- From the Departments of Neurology (S.A.S., V.L.-R., S.L., S.I.S.), UTHealth McGovern Medical School, Houston, TX.,Institute for Stroke and Cerebrovascular Diseases (S.I.S., S.A.S., A.B., L.G.), UTHealth McGovern Medical School, Houston, TX
| | - Victor Lopez-Rivera
- From the Departments of Neurology (S.A.S., V.L.-R., S.L., S.I.S.), UTHealth McGovern Medical School, Houston, TX
| | - Arko Barman
- Institute for Stroke and Cerebrovascular Diseases (S.I.S., S.A.S., A.B., L.G.), UTHealth McGovern Medical School, Houston, TX.,Center for Precision Health, UTHealth School of Biomedical Informatics, Houston, TX (A.B., L.G.)
| | - James C Grotta
- Clinical Innovation and Research Institute, Memorial Hermann Hospital, Texas Medical Center, Houston (J.C.G.)
| | - Albert J Yoo
- Texas Stroke Institute, Dallas-Fort Worth (A.J.Y.)
| | - Songmi Lee
- From the Departments of Neurology (S.A.S., V.L.-R., S.L., S.I.S.), UTHealth McGovern Medical School, Houston, TX
| | - Mehmet E Inam
- Neurosurgery (M.E.I.), UTHealth McGovern Medical School, Houston, TX
| | - Sean I Savitz
- From the Departments of Neurology (S.A.S., V.L.-R., S.L., S.I.S.), UTHealth McGovern Medical School, Houston, TX.,Institute for Stroke and Cerebrovascular Diseases (S.I.S., S.A.S., A.B., L.G.), UTHealth McGovern Medical School, Houston, TX
| | - Luca Giancardo
- Diagnostic and Interventional Imaging (L.G.), UTHealth McGovern Medical School, Houston, TX.,Institute for Stroke and Cerebrovascular Diseases (S.I.S., S.A.S., A.B., L.G.), UTHealth McGovern Medical School, Houston, TX.,Center for Precision Health, UTHealth School of Biomedical Informatics, Houston, TX (A.B., L.G.)
| |
Collapse
|
4
|
Hoving JW, Marquering HA, Majoie CBLM, Yassi N, Sharma G, Liebeskind DS, van der Lugt A, Roos YB, van Zwam W, van Oostenbrugge RJ, Goyal M, Saver JL, Jovin TG, Albers GW, Davalos A, Hill MD, Demchuk AM, Bracard S, Guillemin F, Muir KW, White P, Mitchell PJ, Donnan GA, Davis SM, Campbell BCV. Volumetric and Spatial Accuracy of Computed Tomography Perfusion Estimated Ischemic Core Volume in Patients With Acute Ischemic Stroke. Stroke 2019; 49:2368-2375. [PMID: 30355095 DOI: 10.1161/strokeaha.118.020846] [Citation(s) in RCA: 64] [Impact Index Per Article: 12.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
Background and Purpose- The volume of estimated ischemic core using computed tomography perfusion (CTP) imaging can identify ischemic stroke patients who are likely to benefit from reperfusion, particularly beyond standard time windows. We assessed the accuracy of pretreatment CTP estimated ischemic core in patients with successful endovascular reperfusion. Methods- Patients from the HERMES (Highly Effective Reperfusion Evaluated in Multiple Endovascular Stroke Trials) and EXTEND-IA TNK (Tenecteplase Versus Alteplase Before Endovascular Therapy for Ischemic Stroke) databases who had pretreatment CTP, >50% angiographic reperfusion, and follow-up magnetic resonance imaging at 24 hours were included. Ischemic core volume on baseline CTP data was estimated using relative cerebral blood flow <30% (RAPID, iSchemaView). Follow-up diffusion magnetic resonance imaging was registered to CTP, and the diffusion lesion was outlined using a semiautomated algorithm. Volumetric and spatial agreement (using Dice similarity coefficient, average Hausdorff distance, and precision) was assessed, and expert visual assessment of quality was performed. Results- In 120 patients, median CTP estimated ischemic core volume was 7.8 mL (IQR, 1.8-19.9 mL), and median diffusion lesion volume at 24 hours was 30.8 mL (IQR, 14.9-67.6 mL). Median volumetric difference was 4.4 mL (IQR, 1.2-12.0 mL). Dice similarity coefficient was low (median, 0.24; IQR, 0.15-0.37). The median precision (positive predictive value) of 0.68 (IQR, 0.40-0.88) and average Hausdorff distance (median, 3.1; IQR, 1.8-5.7 mm) indicated reasonable spatial agreement for regions estimated as ischemic core at baseline. Overestimation of total ischemic core volume by CTP was uncommon. Expert visual review revealed overestimation predominantly in white matter regions. Conclusions- CTP estimated ischemic core volumes were substantially smaller than follow-up diffusion-weighted imaging lesions at 24 hours despite endovascular reperfusion within 2 hours of imaging. This may be partly because of infarct growth. Volumetric CTP core overestimation was uncommon and not related to imaging-to-reperfusion time. Core overestimation in white matter should be a focus of future efforts to improve CTP accuracy.
Collapse
Affiliation(s)
- Jan W Hoving
- From the Department of Medicine and Neurology, Melbourne Brain Centre at the Royal Melbourne Hospital (J.W.H., N.Y., G.S., S.M.D., B.C.V.C.), University of Melbourne, Parkville, Australia.,Department of Radiology and Nuclear Medicine (J.W.H., H.A.M., C.B.L.M.M.), Amsterdam UMC (Universitair Medische Centra), University of Amsterdam, the Netherlands
| | - Henk A Marquering
- Department of Radiology and Nuclear Medicine (J.W.H., H.A.M., C.B.L.M.M.), Amsterdam UMC (Universitair Medische Centra), University of Amsterdam, the Netherlands.,Department of Biomedical Engineering and Physics (H.A.M.), Amsterdam UMC (Universitair Medische Centra), University of Amsterdam, the Netherlands
| | - Charles B L M Majoie
- Department of Radiology and Nuclear Medicine (J.W.H., H.A.M., C.B.L.M.M.), Amsterdam UMC (Universitair Medische Centra), University of Amsterdam, the Netherlands
| | - Nawaf Yassi
- From the Department of Medicine and Neurology, Melbourne Brain Centre at the Royal Melbourne Hospital (J.W.H., N.Y., G.S., S.M.D., B.C.V.C.), University of Melbourne, Parkville, Australia.,The Florey Institute of Neuroscience and Mental Health (N.Y., G.A.D.), University of Melbourne, Parkville, Australia
| | - Gagan Sharma
- From the Department of Medicine and Neurology, Melbourne Brain Centre at the Royal Melbourne Hospital (J.W.H., N.Y., G.S., S.M.D., B.C.V.C.), University of Melbourne, Parkville, Australia
| | - David S Liebeskind
- Neurovascular Imaging Research Core, Department of Neurology (D.S.L.), University of California at Los Angeles
| | - Aad van der Lugt
- Department of Radiology and Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, the Netherlands (A.v.d.L.)
| | - Yvo B Roos
- Department of Neurology (Y.B.R.), Amsterdam UMC (Universitair Medische Centra), University of Amsterdam, the Netherlands
| | - Wim van Zwam
- Department of Radiology (W.v.Z.), Cardiovascular Research Institute (CARIM), Maastricht University Medical Center, the Netherlands
| | - Robert J van Oostenbrugge
- Department of Neurology (R.J.v.O.), Cardiovascular Research Institute (CARIM), Maastricht University Medical Center, the Netherlands
| | - Mayank Goyal
- Department of Radiology, University of Calgary, Foothills Hospital, AB, Canada (M.G.)
| | - Jeffrey L Saver
- Department of Neurology (J.L.S.), University of California at Los Angeles
| | - Tudor G Jovin
- Department of Neurology, Stroke Institute, University of Pittsburgh Medical Center, CA (T.G.J.)
| | | | - Antoni Davalos
- Department of Neuroscience, Hospital Germans Trias i Pujol, Universitat Autònoma de Barcelona, Spain (A.D.)
| | - Michael D Hill
- Department of Clinical Neurosciences, Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Foothills Hospital, AB, Canada (M.D.H., A.M.D.)
| | - Andrew M Demchuk
- Department of Clinical Neurosciences, Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Foothills Hospital, AB, Canada (M.D.H., A.M.D.)
| | - Serge Bracard
- Department of Diagnostic and Interventional Neuroradiology, INSERM U 947 (S.B.), University of Lorraine and University Hospital of Nancy, France
| | - Francis Guillemin
- INSERM CIC-EC 1433 Clinical Epidemiology (F.G.), University of Lorraine and University Hospital of Nancy, France
| | - Keith W Muir
- Institute of Neuroscience and Psychology, University of Glasgow, Queen Elizabeth University Hospital, Scotland, United Kingdom (K.W.M.)
| | - Philip White
- Institute of Neuroscience, Newcastle University (P.W.), Newcastle upon Tyne Hospitals NHS Foundation Trust, United Kingdom.,Department of Neuroradiology (P.W.), Newcastle upon Tyne Hospitals NHS Foundation Trust, United Kingdom
| | - Peter J Mitchell
- Department of Radiology, Royal Melbourne Hospital, University of Melbourne, Australia (P.J.M.)
| | - Geoffrey A Donnan
- The Florey Institute of Neuroscience and Mental Health (N.Y., G.A.D.), University of Melbourne, Parkville, Australia
| | - Stephen M Davis
- From the Department of Medicine and Neurology, Melbourne Brain Centre at the Royal Melbourne Hospital (J.W.H., N.Y., G.S., S.M.D., B.C.V.C.), University of Melbourne, Parkville, Australia
| | - Bruce C V Campbell
- From the Department of Medicine and Neurology, Melbourne Brain Centre at the Royal Melbourne Hospital (J.W.H., N.Y., G.S., S.M.D., B.C.V.C.), University of Melbourne, Parkville, Australia
| |
Collapse
|
5
|
Fahmi F, Nasution TH, Anggreiny A. Smart cloud system with image processing server in diagnosing brain diseases dedicated for hospitals with limited resources. Technol Health Care 2017; 25:607-610. [PMID: 28128774 DOI: 10.3233/thc-171298] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
The use of medical imaging in diagnosing brain disease is growing. The challenges are related to the big size of data and complexity of the image processing. High standard of hardware and software are demanded, which can only be provided in big hospitals. Our purpose was to provide a smart cloud system to help diagnosing brain diseases for hospital with limited infrastructure. The expertise of neurologists was first implanted in cloud server to conduct an automatic diagnosis in real time using image processing technique developed based on ITK library and web service. Users upload images through website and the result, in this case the size of tumor was sent back immediately. A specific image compression technique was developed for this purpose. The smart cloud system was able to measure the area and location of tumors, with average size of 19.91 ± 2.38 cm2 and an average response time 7.0 ± 0.3 s. The capability of the server decreased when multiple clients accessed the system simultaneously: 14 ± 0 s (5 parallel clients) and 27 ± 0.2 s (10 parallel clients). The cloud system was successfully developed to process and analyze medical images for diagnosing brain diseases in this case for tumor.
Collapse
Affiliation(s)
- Fahmi Fahmi
- Department of Electrical Engineering, University of Sumatera Utara (USU), Medan, Indonesia
| | - Tigor H Nasution
- Department of Electrical Engineering, University of Sumatera Utara (USU), Medan, Indonesia
| | - Anggreiny Anggreiny
- Department of Radiology, Faculty of Medicine, University of Sumatera Utara (USU), Medan, Indonesia
| |
Collapse
|
6
|
Zhang Y, Zhang L, Sun Y. Rigid motion artifact reduction in CT using frequency domain analysis. JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY 2017; 25:721-736. [PMID: 28506020 DOI: 10.3233/xst-16193] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/07/2023]
Abstract
BACKGROUND It is often unrealistic to assume that the subject remains stationary during a computed tomography (CT) imaging scan. A patient rigid motion can be decomposed into a translation and a rotation around an origin. How to minimize the motion impact on image quality is important. OBJECTIVE To eliminate artifacts caused by patient rigid motion during a CT scan, this study investigated a new method based on frequency domain analysis to estimate and compensate motion impact. METHODS Motion parameters was first determined by the magnitude correlation of projections in frequency domain. Then, the estimated parameters were applied to compensate for the motion effects in the reconstruction process. Finally, this method was extended to helical CT. RESULTS In fan-beam CT experiments, the simulation results showed that the proposed method was more accurate and faster on the performance of motion estimation than using Helgason-Ludwig consistency condition method (HLCC). Furthermore, the reconstructed images on both simulated and human head experiments indicated that the proposed method yielded superior results in artifact reduction. CONCLUSIONS The proposed method is a new tool for patient motion compensation, with a potential for practical application. It is not only applicable to motion correction in fan-beam CT imaging, but also to helical CT.
Collapse
Affiliation(s)
- Yuan Zhang
- School of Electronic Information Engineering, Tianjin University, Tianjin, China
| | - Liyi Zhang
- School of Electronic Information Engineering, Tianjin University, Tianjin, China
- School of Information Engineering, Tianjin University of Commerce, Tianjin, China
| | - Yunshan Sun
- School of Information Engineering, Tianjin University of Commerce, Tianjin, China
| |
Collapse
|