دورية أكاديمية
Radiomics-Based Prediction of Collateral Status from CT Angiography of Patients Following a Large Vessel Occlusion Stroke.
العنوان: | Radiomics-Based Prediction of Collateral Status from CT Angiography of Patients Following a Large Vessel Occlusion Stroke. |
---|---|
المؤلفون: | Avery EW; Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USA., Abou-Karam A; Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USA., Abi-Fadel S; Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USA., Behland J; Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USA.; CLAIM-Charité Lab for Artificial Intelligence in Medicine, Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany., Mak A; Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USA.; CLAIM-Charité Lab for Artificial Intelligence in Medicine, Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany., Haider SP; Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USA.; Department of Otorhinolaryngology, University Hospital of Ludwig Maximilians Universität München, 81377 Munich, Germany., Zeevi T; Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USA., Sanelli PC; Section of Neuroradiology, Department of Radiology, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell Health, Manhasset, NY 11030, USA., Filippi CG; Section of Neuroradiology, Department of Radiology, Tufts School of Medicine, Boston, MA 02111, USA., Malhotra A; Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USA., Matouk CC; Division of Neurovascular Surgery, Department of Neurosurgery, Yale School of Medicine, New Haven, CT 06520, USA., Falcone GJ; Division of Neurocritical Care and Emergency Neurology, Department of Neurology, Yale School of Medicine, New Haven, CT 06520, USA., Petersen N; Division of Neurocritical Care and Emergency Neurology, Department of Neurology, Yale School of Medicine, New Haven, CT 06520, USA., Sansing LH; Division of Stroke and Vascular Neurology, Department of Neurology, Yale School of Medicine, New Haven, CT 06520, USA., Sheth KN; Division of Neurocritical Care and Emergency Neurology, Department of Neurology, Yale School of Medicine, New Haven, CT 06520, USA., Payabvash S; Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USA. |
المصدر: | Diagnostics (Basel, Switzerland) [Diagnostics (Basel)] 2024 Feb 23; Vol. 14 (5). Date of Electronic Publication: 2024 Feb 23. |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: MDPI AG Country of Publication: Switzerland NLM ID: 101658402 Publication Model: Electronic Cited Medium: Print ISSN: 2075-4418 (Print) Linking ISSN: 20754418 NLM ISO Abbreviation: Diagnostics (Basel) Subsets: PubMed not MEDLINE |
أسماء مطبوعة: | Original Publication: Basel, Switzerland : MDPI AG, [2011]- |
مستخلص: | Background: A major driver of individual variation in long-term outcomes following a large vessel occlusion (LVO) stroke is the degree of collateral arterial circulation. We aimed to develop and evaluate machine-learning models that quantify LVO collateral status using admission computed tomography angiography (CTA) radiomics. Methods: We extracted 1116 radiomic features from the anterior circulation territories from admission CTAs of 600 patients experiencing an acute LVO stroke. We trained and validated multiple machine-learning models for the prediction of collateral status based on consensus from two neuroradiologists as ground truth. Models were first trained to predict (1) good vs. intermediate or poor, or (2) good vs. intermediate or poor collateral status. Then, model predictions were combined to determine a three-tier collateral score (good, intermediate, or poor). We used the receiver operating characteristics area under the curve (AUC) to evaluate prediction accuracy. Results: We included 499 patients in training and 101 in an independent test cohort. The best-performing models achieved an averaged cross-validation AUC of 0.80 ± 0.05 for poor vs. intermediate/good collateral and 0.69 ± 0.05 for good vs. intermediate/poor, and AUC = 0.77 (0.67-0.87) and AUC = 0.78 (0.70-0.90) in the independent test cohort, respectively. The collateral scores predicted by the radiomics model were correlated with (rho = 0.45, p = 0.002) and were independent predictors of 3-month clinical outcome ( p = 0.018) in the independent test cohort. Conclusions: Automated tools for the assessment of collateral status from admission CTA-such as the radiomics models described here-can generate clinically relevant and reproducible collateral scores to facilitate a timely treatment triage in patients experiencing an acute LVO stroke. |
References: | Bioinformatics. 2013 Sep 15;29(18):2365-8. (PMID: 23825369) AJNR Am J Neuroradiol. 2009 Mar;30(3):525-31. (PMID: 19147716) J Stroke Cerebrovasc Dis. 2014 Mar;23(3):421-6. (PMID: 23583014) Data Brief. 2022 Aug 14;44:108542. (PMID: 36060820) Neuroradiology. 2022 Dec;64(12):2277-2284. (PMID: 35608629) J Stroke. 2023 May;25(2):179-198. (PMID: 36907186) J Stat Softw. 2010;33(1):1-22. (PMID: 20808728) Biomedicines. 2023 Jan 17;11(2):. (PMID: 36830780) Semin Ultrasound CT MR. 2022 Apr;43(2):142-146. (PMID: 35339254) BMJ. 2018 Mar 9;360:k949. (PMID: 29523557) AJNR Am J Neuroradiol. 2015 Mar;36(3):488-94. (PMID: 25523589) AJNR Am J Neuroradiol. 2012 Mar;33(3):576-82. (PMID: 22135128) J Neurol Neurosurg Psychiatry. 2016 May;87(5):537-44. (PMID: 26063928) Clin Neurol Neurosurg. 2006 Oct;108(7):638-43. (PMID: 16300876) BMC Bioinformatics. 2011 Mar 17;12:77. (PMID: 21414208) Cancer Res. 2017 Nov 1;77(21):e104-e107. (PMID: 29092951) Interv Neuroradiol. 2023 Jan 17;:15910199221150470. (PMID: 36650942) J Clin Med. 2021 Mar 21;10(6):. (PMID: 33801050) Stroke. 2022 Mar;53(3):742-748. (PMID: 34727737) Circulation. 2022 Feb 22;145(8):e153-e639. (PMID: 35078371) J Neuroimaging. 2022 Jan;32(1):63-67. (PMID: 34506667) Trials. 2021 Feb 24;22(1):160. (PMID: 33627168) Eur J Nucl Med Mol Imaging. 2020 Dec;47(13):2978-2991. (PMID: 32399621) Eur J Neurol. 2016 Dec;23(12):1738-1749. (PMID: 27478977) Atherosclerosis. 2019 Mar;282:75-79. (PMID: 30708178) Stat Med. 2000 Mar 15;19(5):723-41. (PMID: 10700742) Brain. 2009 Aug;132(Pt 8):2231-8. (PMID: 19509116) IEEE Trans Image Process. 2008 Apr;17(4):622-9. (PMID: 18390369) J Stroke Cerebrovasc Dis. 2017 Apr;26(4):801-808. (PMID: 27856113) Biometrics. 1988 Sep;44(3):837-45. (PMID: 3203132) Cerebrovasc Dis. 2004;18(4):304-11. (PMID: 15331877) Stroke. 2010 Oct;41(10):2316-22. (PMID: 20829514) AJNR Am J Neuroradiol. 2015 Feb;36(2):289-94. (PMID: 25324493) Cancers Head Neck. 2020 May 4;5:6. (PMID: 32391171) Neuroimage Clin. 2022;34:103034. (PMID: 35550243) Neuroimaging Clin N Am. 2005 Aug;15(3):553-73, x. (PMID: 16360589) Stroke. 2019 Dec;50(12):e344-e418. (PMID: 31662037) Stroke. 2019 Nov;50(11):3115-3120. (PMID: 31554502) |
معلومات مُعتمدة: | K23 NS110980 United States NS NINDS NIH HHS; U24 NS107136 United States NS NINDS NIH HHS; R01 NS097728 United States NS NINDS NIH HHS; R21 NS128641 United States NS NINDS NIH HHS; P30 AG021342 United States AG NIA NIH HHS; R01 NS095993 United States NS NINDS NIH HHS; U24 NS107215 United States NS NINDS NIH HHS; U01 NS106513 United States NS NINDS NIH HHS; 2020097 United States DDCF Doris Duke Charitable Foundation; K23 NS118056 United States NS NINDS NIH HHS; R01 NR018335 United States NR NINR NIH HHS |
فهرسة مساهمة: | Keywords: collateral status; large vessel occlusion; machine learning; radiomics; stroke |
تواريخ الأحداث: | Date Created: 20240313 Latest Revision: 20240412 |
رمز التحديث: | 20240412 |
مُعرف محوري في PubMed: | PMC10930945 |
DOI: | 10.3390/diagnostics14050485 |
PMID: | 38472957 |
قاعدة البيانات: | MEDLINE |
تدمد: | 2075-4418 |
---|---|
DOI: | 10.3390/diagnostics14050485 |