105 Machine learning and carotid artery CT radiomics identify significant differences between culprit and non-culprit lesions in patients with stroke and transient ischaemic attack
IntroductionCarotid atherosclerosis is the main cause of ischaemic stroke. Texture analysis is a radiomic approach used to quantify image heterogeneity which can predict tumour aggression in oncology. We investigated whether this method could be applied to carotid artery disease to differentiate sym...
Saved in:
Published in | Heart (British Cardiac Society) Vol. 106; no. Suppl 2; pp. A82 - A84 |
---|---|
Main Authors | , , , , , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
London
BMJ Publishing Group LTD
01.07.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | IntroductionCarotid atherosclerosis is the main cause of ischaemic stroke. Texture analysis is a radiomic approach used to quantify image heterogeneity which can predict tumour aggression in oncology. We investigated whether this method could be applied to carotid artery disease to differentiate symptomatic from asymptomatic patients and culprit from non-culprit plaques, and then whether machine learning (ML) could correctly classify plaques based on these features.MethodsCT angiography (CTA) images from symptomatic patients with carotid artery-related cerebrovascular accidents (CVAs) and from asymptomatic (ASX) patients were studied. Regions-of-interest (ROIs) were drawn on 14 consecutive carotid artery CTA slices with 3mm slice thickness. PyRadiomics was used for isotropic image (1x1x1) resampling and normalisation prior to texture feature extraction from 6 different classes (Table 1). Asymptomatic carotids were compared to culprit carotids (CC), and non-culprit (NC) carotids using the Mann Whitney U test or Wilcoxon signed-rank tests as appropriate, with a p-value <0.0005 deemed statistically significant after Bonferroni correction. Non-normally distributed variables are reported as median (interquartile range). To assess the discriminatory ability of radiomic features in multi-class classification (ASX, CC or NC), texture features were fed into a Python scikit-learn pipeline for feature selection with variance thresholding, feature scaling and dimensionality reduction incorporated within a 5-fold cross validation scheme with 5 different ML classifiers to reduce the risk of data leakage and overfitting. Mean cross validation (CV) accuracy, area under the receiver operating curve (AUC) and 95% confidence intervals (CI) are reported.Abstract 105 Table 1Different classes of texture features extracted from carotid CTA Abbreviation Feature Class Number of Features IHFirst-order Intensity Histogram Statistics18GLCMGrey Level Co-occurrence Matrix24GLRLMGrey Level Run Length Matrix16GLSZMGrey Level Size Zone Matrix16GLDMGrey Level Dependence Matrix14NGTDMNeighbouring Grey Tone Difference Matrix5ResultsThe dataset comprised 82 carotid arteries from 41 symptomatic patients (41 culprit; 41 non-culprit) and 50 carotid arteries from 25 asymptomatic patients. CC and NC carotids showed significant differences in both first- and second-order features (IH Median: CC 618 (61); NC 646 (97), p<0.005) and (GLDM Large Dependence High Grey-Level Emphasis: CC 3147 (1837), NC 4811 (2181), p<0.0001), respectively. Both CC and NC carotids had higher heterogeneity than asymptomatic carotids (GLDM Dependence Entropy: CC 6.59 (0.43), NC 6.57 (0.52), ASX 6.24 (0.26), p<0.0001). All ML classifiers performed better than a randomly guessing classifier (mean accuracy 33.3%) in this multi-class (n=3) classification task (Table 2; Figure 2), with the neural network achieving the highest accuracy of 69%, CI [61%, 77%] with AUC 0.82 CI [0.78, 0.86].Abstract 105 Table 25-fold mean cross-validation auc with 95% confidence intervals Multi-Class ML Models AUC 95% confidence interval [CI] Decision Tree0.59[0.54, 0.64]Naïve Bayes0.75[0.73, 0.77]Random Forest0.79[0.70, 0.88]Logistic Regression0.80[0.77, 0.83]Neural Network0.82[0.78, 0.86]AUC, Area under the Receiver Operating Curve (‘OneVsRest’ scheme for multi-class classification tasks); ML, machine learning; CI, confidence intervalAbstract 105 Figure 1Rest and hyperaemic coronary flow velocity in the distal left anterior descending arteryAbstract 105 Figure 2Coronary flow reserve in controls and living kidney donors. Red squares represent mean. Error bars represent 95% confidence intervalsConclusionsTextural analysis combined with machine learning on carotid CT scans reveals highly significant differences between symptomatic and asymptomatic patients, and between culprit and non-culprit carotid arteries within symptomatic patients. This approach could help identify patients at high-risk of stroke for aggressive medical therapy and surveillance.Conflict of InterestNone |
---|---|
AbstractList | IntroductionCarotid atherosclerosis is the main cause of ischaemic stroke. Texture analysis is a radiomic approach used to quantify image heterogeneity which can predict tumour aggression in oncology. We investigated whether this method could be applied to carotid artery disease to differentiate symptomatic from asymptomatic patients and culprit from non-culprit plaques, and then whether machine learning (ML) could correctly classify plaques based on these features.MethodsCT angiography (CTA) images from symptomatic patients with carotid artery-related cerebrovascular accidents (CVAs) and from asymptomatic (ASX) patients were studied. Regions-of-interest (ROIs) were drawn on 14 consecutive carotid artery CTA slices with 3mm slice thickness. PyRadiomics was used for isotropic image (1x1x1) resampling and normalisation prior to texture feature extraction from 6 different classes (Table 1). Asymptomatic carotids were compared to culprit carotids (CC), and non-culprit (NC) carotids using the Mann Whitney U test or Wilcoxon signed-rank tests as appropriate, with a p-value <0.0005 deemed statistically significant after Bonferroni correction. Non-normally distributed variables are reported as median (interquartile range). To assess the discriminatory ability of radiomic features in multi-class classification (ASX, CC or NC), texture features were fed into a Python scikit-learn pipeline for feature selection with variance thresholding, feature scaling and dimensionality reduction incorporated within a 5-fold cross validation scheme with 5 different ML classifiers to reduce the risk of data leakage and overfitting. Mean cross validation (CV) accuracy, area under the receiver operating curve (AUC) and 95% confidence intervals (CI) are reported.Abstract 105 Table 1Different classes of texture features extracted from carotid CTAAbbreviationFeature ClassNumber of FeaturesIHFirst-order Intensity Histogram Statistics18GLCMGrey Level Co-occurrence Matrix24GLRLMGrey Level Run Length Matrix16GLSZMGrey Level Size Zone Matrix16GLDMGrey Level Dependence Matrix14NGTDMNeighbouring Grey Tone Difference Matrix5ResultsThe dataset comprised 82 carotid arteries from 41 symptomatic patients (41 culprit; 41 non-culprit) and 50 carotid arteries from 25 asymptomatic patients. CC and NC carotids showed significant differences in both first- and second-order features (IH Median: CC 618 (61); NC 646 (97), p<0.005) and (GLDM Large Dependence High Grey-Level Emphasis: CC 3147 (1837), NC 4811 (2181), p<0.0001), respectively. Both CC and NC carotids had higher heterogeneity than asymptomatic carotids (GLDM Dependence Entropy: CC 6.59 (0.43), NC 6.57 (0.52), ASX 6.24 (0.26), p<0.0001). All ML classifiers performed better than a randomly guessing classifier (mean accuracy 33.3%) in this multi-class (n=3) classification task (Table 2; Figure 2), with the neural network achieving the highest accuracy of 69%, CI [61%, 77%] with AUC 0.82 CI [0.78, 0.86].Abstract 105 Table 25-fold mean cross-validation auc with 95% confidence intervalsMulti-Class ML ModelsAUC95% confidence interval [CI]Decision Tree0.59[0.54, 0.64]Naïve Bayes0.75[0.73, 0.77]Random Forest0.79[0.70, 0.88]Logistic Regression0.80[0.77, 0.83]Neural Network0.82[0.78, 0.86]AUC, Area under the Receiver Operating Curve (‘OneVsRest’ scheme for multi-class classification tasks); ML, machine learning; CI, confidence intervalAbstract 105 Figure 1Rest and hyperaemic coronary flow velocity in the distal left anterior descending artery[Figure omitted. See PDF]Abstract 105 Figure 2Coronary flow reserve in controls and living kidney donors. Red squares represent mean. Error bars represent 95% confidence intervals[Figure omitted. See PDF]ConclusionsTextural analysis combined with machine learning on carotid CT scans reveals highly significant differences between symptomatic and asymptomatic patients, and between culprit and non-culprit carotid arteries within symptomatic patients. This approach could help identify patients at high-risk of stroke for aggressive medical therapy and surveillance.Conflict of InterestNone IntroductionCarotid atherosclerosis is the main cause of ischaemic stroke. Texture analysis is a radiomic approach used to quantify image heterogeneity which can predict tumour aggression in oncology. We investigated whether this method could be applied to carotid artery disease to differentiate symptomatic from asymptomatic patients and culprit from non-culprit plaques, and then whether machine learning (ML) could correctly classify plaques based on these features.MethodsCT angiography (CTA) images from symptomatic patients with carotid artery-related cerebrovascular accidents (CVAs) and from asymptomatic (ASX) patients were studied. Regions-of-interest (ROIs) were drawn on 14 consecutive carotid artery CTA slices with 3mm slice thickness. PyRadiomics was used for isotropic image (1x1x1) resampling and normalisation prior to texture feature extraction from 6 different classes (Table 1). Asymptomatic carotids were compared to culprit carotids (CC), and non-culprit (NC) carotids using the Mann Whitney U test or Wilcoxon signed-rank tests as appropriate, with a p-value <0.0005 deemed statistically significant after Bonferroni correction. Non-normally distributed variables are reported as median (interquartile range). To assess the discriminatory ability of radiomic features in multi-class classification (ASX, CC or NC), texture features were fed into a Python scikit-learn pipeline for feature selection with variance thresholding, feature scaling and dimensionality reduction incorporated within a 5-fold cross validation scheme with 5 different ML classifiers to reduce the risk of data leakage and overfitting. Mean cross validation (CV) accuracy, area under the receiver operating curve (AUC) and 95% confidence intervals (CI) are reported.Abstract 105 Table 1Different classes of texture features extracted from carotid CTA Abbreviation Feature Class Number of Features IHFirst-order Intensity Histogram Statistics18GLCMGrey Level Co-occurrence Matrix24GLRLMGrey Level Run Length Matrix16GLSZMGrey Level Size Zone Matrix16GLDMGrey Level Dependence Matrix14NGTDMNeighbouring Grey Tone Difference Matrix5ResultsThe dataset comprised 82 carotid arteries from 41 symptomatic patients (41 culprit; 41 non-culprit) and 50 carotid arteries from 25 asymptomatic patients. CC and NC carotids showed significant differences in both first- and second-order features (IH Median: CC 618 (61); NC 646 (97), p<0.005) and (GLDM Large Dependence High Grey-Level Emphasis: CC 3147 (1837), NC 4811 (2181), p<0.0001), respectively. Both CC and NC carotids had higher heterogeneity than asymptomatic carotids (GLDM Dependence Entropy: CC 6.59 (0.43), NC 6.57 (0.52), ASX 6.24 (0.26), p<0.0001). All ML classifiers performed better than a randomly guessing classifier (mean accuracy 33.3%) in this multi-class (n=3) classification task (Table 2; Figure 2), with the neural network achieving the highest accuracy of 69%, CI [61%, 77%] with AUC 0.82 CI [0.78, 0.86].Abstract 105 Table 25-fold mean cross-validation auc with 95% confidence intervals Multi-Class ML Models AUC 95% confidence interval [CI] Decision Tree0.59[0.54, 0.64]Naïve Bayes0.75[0.73, 0.77]Random Forest0.79[0.70, 0.88]Logistic Regression0.80[0.77, 0.83]Neural Network0.82[0.78, 0.86]AUC, Area under the Receiver Operating Curve (‘OneVsRest’ scheme for multi-class classification tasks); ML, machine learning; CI, confidence intervalAbstract 105 Figure 1Rest and hyperaemic coronary flow velocity in the distal left anterior descending arteryAbstract 105 Figure 2Coronary flow reserve in controls and living kidney donors. Red squares represent mean. Error bars represent 95% confidence intervalsConclusionsTextural analysis combined with machine learning on carotid CT scans reveals highly significant differences between symptomatic and asymptomatic patients, and between culprit and non-culprit carotid arteries within symptomatic patients. This approach could help identify patients at high-risk of stroke for aggressive medical therapy and surveillance.Conflict of InterestNone |
Author | Sala, Evis Wall, Chris Tarkin, Jason Chowdhury, Mohammed Weir-McCall, Jonathan Le, Elizabeth Phuong Vi Zaccagna, Fulvio Pavey, Holly Warburton, Elizabeth Evans, Nicholas Huang, Yuan Rudd, James HF Rundo, Leonardo Schönlieb, Carola-Bibiane |
Author_xml | – sequence: 1 givenname: Elizabeth Phuong Vi surname: Le fullname: Le, Elizabeth Phuong Vi organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 2 givenname: Nicholas surname: Evans fullname: Evans, Nicholas organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 3 givenname: Jason surname: Tarkin fullname: Tarkin, Jason organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 4 givenname: Mohammed surname: Chowdhury fullname: Chowdhury, Mohammed organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 5 givenname: Fulvio surname: Zaccagna fullname: Zaccagna, Fulvio organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 6 givenname: Holly surname: Pavey fullname: Pavey, Holly organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 7 givenname: Chris surname: Wall fullname: Wall, Chris organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 8 givenname: Yuan surname: Huang fullname: Huang, Yuan organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 9 givenname: Jonathan surname: Weir-McCall fullname: Weir-McCall, Jonathan organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 10 givenname: Elizabeth surname: Warburton fullname: Warburton, Elizabeth organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 11 givenname: Leonardo surname: Rundo fullname: Rundo, Leonardo organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 12 givenname: Carola-Bibiane surname: Schönlieb fullname: Schönlieb, Carola-Bibiane organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 13 givenname: Evis surname: Sala fullname: Sala, Evis organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge – sequence: 14 givenname: James HF surname: Rudd fullname: Rudd, James HF organization: Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge |
BookMark | eNo1kUtOwzAQhi1UJNrCEZAssU6x48RJllDxkopYUCR2kWOPW7epU2xXVXdsuBIH4iS4ha7m9eubGf0D1LOdBYQuKRlRyvj1HIQLC9smKUlJcjt-HVGSn6A-zXgZe_S9F3OW5wknrDhDA-8XhJCsKnkffUfpz-fXs5BzYwG3EWWNnWFhFZbCdcEoHOngdng8xU4o062M9NgosMHoHfZmZo02UtiAldEaHFgJHjcQtgAWy027diYcgPHu5Fi34E1nI8jitQgm0jzemjDHPrhuCQd9cML6_QgbL-cC4mYsQhByeY5OtWg9XPzHIXq7v5uOH5PJy8PT-GaSNJTyPKkKJpSqQDJGgBYFl6TIszIthCiZZI3kqW7ygleZUpnWDacy101VAdWcl6xiQ3T1x1277mMDPtSLbuNsXFmnWZpxkpG0iCryp2pWizp-txJuV1NS792pj-7Ue3fq6E6c5OwX2_uMlw |
ContentType | Journal Article |
Copyright | Author(s) (or their employer(s)) 2020. No commercial re-use. See rights and permissions. Published by BMJ. 2020 Author(s) (or their employer(s)) 2020. No commercial re-use. See rights and permissions. Published by BMJ. |
Copyright_xml | – notice: Author(s) (or their employer(s)) 2020. No commercial re-use. See rights and permissions. Published by BMJ. – notice: 2020 Author(s) (or their employer(s)) 2020. No commercial re-use. See rights and permissions. Published by BMJ. |
DBID | 3V. 7X7 7XB 88E 88I 8AF 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR BTHHO CCPQU DWQXO FYUFA GHDGH GNUQQ HCIFZ K9. M0S M1P M2P PQEST PQQKQ PQUKI PRINS Q9U |
DOI | 10.1136/heartjnl-2020-BCS.105 |
DatabaseName | ProQuest Central (Corporate) ProQuest - Health & Medical Complete保健、医学与药学数据库 ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Science Database (Alumni Edition) STEM Database Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central BMJ Journals ProQuest One Community College ProQuest Central Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Central Student SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Health & Medical Complete (Alumni) Health & Medical Collection (Alumni Edition) PML(ProQuest Medical Library) Science Journals (ProQuest Database) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic |
DatabaseTitle | ProQuest Central Student ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest AP Science ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Central China ProQuest Central Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea ProQuest Medical Library (Alumni) ProQuest Science Journals (Alumni Edition) ProQuest Central Basic ProQuest Science Journals ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition BMJ Journals ProQuest One Academic ProQuest Central (Alumni) |
DatabaseTitleList | ProQuest Central Student |
Database_xml | – sequence: 1 dbid: BENPR name: AUTh Library subscriptions: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine |
EISSN | 1468-201X |
EndPage | A84 |
GroupedDBID | --- .55 .VT 0R~ 29I 2WC 354 39C 3O- 3V. 4.4 40O 53G 5GY 5RE 7X7 7~S 88E 88I 8AF 8FI 8FJ 8R4 8R5 AAFWJ AAHLL AAKAS AAOJX AAWJN AAWTL AAYEP ABAAH ABJNI ABKDF ABMQD ABOCM ABUWG ABVAJ ACGFS ACGOD ACGTL ACHTP ACMFJ ACOFX ACTZY ADBBV ADCEG ADUGQ ADZCM AEKJL AENEX AFFNX AFKRA AFWFF AHMBA AHNKE AHQMW AJYBZ AKKEP ALIPV ALMA_UNASSIGNED_HOLDINGS AOIJS AZFZN AZQEC BAWUL BCR BENPR BLC BLJBA BOMFT BPHCQ BTHHO BVXVI C1A CAG CCPQU COF CXRWF DIK DU5 DWQXO E3Z EBS EJD EX3 F5P FEDTE FYUFA GNUQQ GX1 H13 HAJ HCIFZ HMCUK HVGLF HYE HZ~ IAO IEA IHR INH INR IOF ITC J5H L7B M1P M2P N4W N9A NTWIH NXWIF O9- OK1 OVD P2P PCD PEA PQQKQ PROAC PSQYO Q2X R53 RHI RMJ RPM RV8 TEORI TR2 UKHRP UYXKK V24 VM9 WH7 WOQ WOW X7M YFH YQY ZGI ZXP 7XB 8FK K9. PQEST PQUKI PRINS Q9U |
ID | FETCH-LOGICAL-b1165-973add9ec330e1776c0754827aa83c3bc62fb57694dd4ffb61c5fb99e1f668393 |
IEDL.DBID | BENPR |
ISSN | 1355-6037 |
IngestDate | Thu Oct 10 19:53:04 EDT 2024 Wed Aug 21 03:41:18 EDT 2024 |
IsDoiOpenAccess | false |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | Suppl 2 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-b1165-973add9ec330e1776c0754827aa83c3bc62fb57694dd4ffb61c5fb99e1f668393 |
OpenAccessLink | https://heart.bmj.com/content/heartjnl/106/Suppl_2/A82.2.full.pdf |
PQID | 2424604027 |
PQPubID | 2041068 |
ParticipantIDs | proquest_journals_2424604027 bmj_primary_10_1136_heartjnl_2020_BCS_105 |
PublicationCentury | 2000 |
PublicationDate | 20200700 20200701 |
PublicationDateYYYYMMDD | 2020-07-01 |
PublicationDate_xml | – month: 07 year: 2020 text: 20200700 |
PublicationDecade | 2020 |
PublicationPlace | London |
PublicationPlace_xml | – name: London |
PublicationTitle | Heart (British Cardiac Society) |
PublicationYear | 2020 |
Publisher | BMJ Publishing Group LTD |
Publisher_xml | – name: BMJ Publishing Group LTD |
SSID | ssj0004986 |
Score | 2.3701136 |
Snippet | IntroductionCarotid atherosclerosis is the main cause of ischaemic stroke. Texture analysis is a radiomic approach used to quantify image heterogeneity which... |
SourceID | proquest bmj |
SourceType | Aggregation Database Publisher |
StartPage | A82 |
SubjectTerms | Accuracy Carotid arteries Confidence intervals Flow velocity Machine learning Neural networks Radiomics Stroke Transient ischemic attack |
Title | 105 Machine learning and carotid artery CT radiomics identify significant differences between culprit and non-culprit lesions in patients with stroke and transient ischaemic attack |
URI | http://dx.doi.org/10.1136/heartjnl-2020-BCS.105 https://www.proquest.com/docview/2424604027 |
Volume | 106 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3NTtwwELYKSIhLVQoIWrqaQy8cLDZx1t6cUFmBUKVFFSzS3qLYsVFgyS4bc-DGpa_UB-qTdMbraA9IPUaOnCgzmT9_Mx9j340zNhWV4hr1gWdSa66dNRzzNqVzl6HLpHrH-Fpe3WU_p4NpLLi1EVbZ2cRgqKu5oRr5KbUxSNS4VJ0tnjmxRtHpaqTQ2GBbaZLRMe3W-cX1r5t1Z2QeuB4T9Kpc9oWKPTyJkKdEGO0fmhnqCWZQ56NborxFD6OfHt7Z5eBsLj-xjzFKhB8rse6yD7b5zLbH8Rx8j_3BTf6-_R4HJKSFSP1wD2VTARHx-LqCANZ8hdEElmVVU_NxC3Voy3WvQLANAgnhd4WOIwUtBkTYFpiX2WJZ-7BhM294dz2zVF3DjRqIE1lboFIutH45f7Thfk_uj5agbgmTj0-G0vvSPO6zu8uLyeiKRwYGrmksD8-VQPuXWyNE3yZKSYMRBg0OLcuhMEIbmTqNGUueVVXmnJaJGTid5zZxUmLoJQ7YJr6kPWQwVK6vTSaswaQsVelw4KxEZTClHGYuL4_YCX75YrGasVGE3ETIopNSQVIqUEq4Mjhix518ivjLtcVaQb78f_kr2wkiD5jbY7bply_2G0YWXvfYhpqqXlSif7x7060 |
link.rule.ids | 315,786,790,12083,21416,27955,27956,31752,33777,43343,43838,74100,74657 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV07b9swECbaBGizBE0fSJpHb-jSgYgl0qQ1FamRwGnjLHUAb4JIkYUSR3YtZsjWpX-pP6i_JHcMhQwFOgoUKEF3uhe_u4-xj9Zbl4tac4P6wKUyhhvvLMe8TZvCS3SZVO-YXqrJlfw6H85Twa1LsMreJkZDXS8t1ciPqY1Bocbl-vPqJyfWKDpdTRQaz9mmFEKSnuu5fuqLLCLTY4Y-lauB0KmDJxPqmOiiw3W7QC3B_OnL-DsR3qJ_MbfX_1jl6GrOXrHtFCPCyaNQd9gz175mL6bpFPwN-4Ob_P31expxkA4S8cMPqNoaiIYnNDVEqOY9jGewruqGWo87aGJTrr8HAm0QRAi_KvQMKWgvIIG2wN4tVusmxA3bZcv764Wj2hpu1EKax9oBFXKhC-vljYv3B3J-tARNR4h8fDJUIVT25i27OjudjSc88S9wQ0N5eKEFWr_CWSEGLtNaWYwvaGxoVY2EFcaq3BvMVwpZ19J7ozI79KYoXOaVwsBLvGMb-JJul8FI-4GxUjiLKVmu89HQO4WqYCs1kr6o9tgn_PLl6nHCRhkzE6HKXkolSalEKeHKcI8d9PIp0w_XlU_q8f7_yx_Yy8lselFenF9-22dbUfwRfXvANsL6zh1ijBHMUVSkB0Nv1E0 |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT9wwELZ4SKiXilJQKVDm0EsPFpt11t6cEF1Y8egiJEDaWxQ7Ngos2WVjDty49C_1B_WXMGMccUDiGDlyosxkXv5mPsZ-GmdsV5SKa9QHnkqtuXbWcMzblM5cii6T6h2jc3l8nZ6Oe-OIf2oirLK1icFQl1NDNfI9amOQqHGYqrsIi7g4HO7PHjgxSNFJa6TTWGTL6CU7ROOgxuqtRzILrI8J-lcuO0LFbp5EyD2ijva39QQ1BnOp34NLIr9FX6Pvb99Z6OB2hqvsc4wX4eBVwF_Ygq3X2Moonoh_Zf9wk__Pf0cBE2khkkDcQFGXQJQ8viohwDafYHAF86KsqA25gSo06LonIAAHwYXwC0PLloK2AyKAC8zjZDavfNiwnta8vZ5YqrPhRjXE2awNUFEXGj-f3tlwvydHSEtQNYTOxydD4X1h7tbZ9fDoanDMIxcD1zSgh2dKoCXMrBGiYxOlpMFYg0aIFkVfGKGN7DqNuUuWlmXqnJaJ6TmdZTZxUmIQJjbYEr6k_cagr1xHm1RYg-lZV3X7PWclqoUpZD91WbHJfuGXz2ev0zbykKUImbdSyklKOUoJV3qbbLuVTx5_viZ_U5XvHy_vshXUofzPyfnZFvsUpB-AuNtsyc8f7Q6GG17_CHr0AshD2Hk |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=105%E2%80%85Machine+learning+and+carotid+artery+CT+radiomics+identify+significant+differences+between+culprit+and+non-culprit+lesions+in+patients+with+stroke+and+transient+ischaemic+attack&rft.jtitle=Heart+%28British+Cardiac+Society%29&rft.au=Le%2C+Elizabeth+Phuong+Vi&rft.au=Evans%2C+Nicholas&rft.au=Tarkin%2C+Jason&rft.au=Chowdhury%2C+Mohammed&rft.date=2020-07-01&rft.issn=1355-6037&rft.eissn=1468-201X&rft.volume=106&rft.issue=Suppl+2&rft.spage=A82&rft.epage=A84&rft_id=info:doi/10.1136%2Fheartjnl-2020-BCS.105&rft.externalDBID=ttps%3A%2F%2Fheart.bmj.com%2Fcontent%2F106%2FSuppl_2%2FA82.2.full.pdf |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1355-6037&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1355-6037&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1355-6037&client=summon |