دورية أكاديمية
أعرض في EDS

NS-HGlio: A generalizable and repeatable HGG segmentation and volumetric measurement AI algorithm for the longitudinal MRI assessment to inform RANO in trials and clinics.

التفاصيل البيبلوغرافية
العنوان: NS-HGlio: A generalizable and repeatable HGG segmentation and volumetric measurement AI algorithm for the longitudinal MRI assessment to inform RANO in trials and clinics.
المؤلفون: Abayazeed AH; Biomedical Engineering group, Neosoma Inc., Groton, Massachusetts, USA (Originating Institution address:44 Farmers Row, Groton, Massachusetts, 01450), USA., Abbassy A; Biomedical Engineering group, Neosoma Inc., Groton, Massachusetts, USA (Originating Institution address:44 Farmers Row, Groton, Massachusetts, 01450), USA., Müeller M; Biomedical Engineering group, Neosoma Inc., Groton, Massachusetts, USA (Originating Institution address:44 Farmers Row, Groton, Massachusetts, 01450), USA.; ARTORG Biomedical Engineering group, University of Bern, Switzerland., Hill M; Biomedical Engineering group, Neosoma Inc., Groton, Massachusetts, USA (Originating Institution address:44 Farmers Row, Groton, Massachusetts, 01450), USA., Qayati M; Biomedical Engineering group, Neosoma Inc., Groton, Massachusetts, USA (Originating Institution address:44 Farmers Row, Groton, Massachusetts, 01450), USA.; Radiology Department, University of Cairo School of Medicine, Egypt., Mohamed S; Biomedical Engineering group, Neosoma Inc., Groton, Massachusetts, USA (Originating Institution address:44 Farmers Row, Groton, Massachusetts, 01450), USA.; Radiology Department, University of Cairo School of Medicine, Egypt., Mekhaimar M; Radiology Department, University of Cairo School of Medicine, Egypt., Raymond C; Brain Tumor Imaging Laboratory, University of California Los Angeles, Los Angeles, California, USA., Dubey P; Radiology Department, Houston Methodist Hospital, Houston, Texas, USA., Nael K; Radiology Department, University of California Los Angeles, Los Angeles, California, USA., Rohatgi S; Radiology Department, Massachusetts General Hospital, Boston, Massachusetts, USA., Kapare V; Radiology Department, University of Massachusetts, Worcester, Massachusetts, USA., Kulkarni A; Radiology Department, University of Massachusetts, Worcester, Massachusetts, USA., Shiang T; Radiology Department, University of Massachusetts, Worcester, Massachusetts, USA., Kumar A; Radiology Department, Yale School of Medicine, New Haven, Connecticut, USA., Andratschke N; Radiation Oncology Department, University of Zurich, Switzerland., Willmann J; Radiation Oncology Department, University of Zurich, Switzerland., Brawanski A; Radiology Department, University of Cairo School of Medicine, Egypt.; Radiation Oncology Department, University Hospital Regensburg, Cairo Egypt and Regensburg, Germany., De Jesus R; Radiology Department, University of Florida, Gainesville, Florida, USA., Tuna I; Radiology Department, University of Florida, Gainesville, Florida, USA., Fung SH; Radiology Department, Houston Methodist Hospital, Houston, Texas, USA., Landolfi JC; Neurology/Neuro-oncology Department, Hackensack Meridian Health JFK Medical Center, Edison, New Jersey, USA., Ellingson BM; Brain Tumor Imaging Laboratory, University of California Los Angeles, Los Angeles, California, USA., Reyes M; ARTORG Biomedical Engineering group, University of Bern, Switzerland.
المصدر: Neuro-oncology advances [Neurooncol Adv] 2022 Dec 20; Vol. 5 (1), pp. vdac184. Date of Electronic Publication: 2022 Dec 20 (Print Publication: 2023).
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Oxford University Press Country of Publication: England NLM ID: 101755003 Publication Model: eCollection Cited Medium: Internet ISSN: 2632-2498 (Electronic) Linking ISSN: 26322498 NLM ISO Abbreviation: Neurooncol Adv Subsets: PubMed not MEDLINE
أسماء مطبوعة: Original Publication: [Oxford] : Oxford University Press, [2019]-
مستخلص: Background: Accurate and repeatable measurement of high-grade glioma (HGG) enhancing (Enh.) and T2/FLAIR hyperintensity/edema (Ed.) is required for monitoring treatment response. 3D measurements can be used to inform the modified Response Assessment in Neuro-oncology criteria. We aim to develop an HGG volumetric measurement and visualization AI algorithm that is generalizable and repeatable.
Methods: A single 3D-Convoluted Neural Network, NS-HGlio, to analyze HGG on MRIs using 5-fold cross validation was developed using retrospective (557 MRIs), multicentre (38 sites) and multivendor (32 scanners) dataset divided into training (70%), validation (20%), and testing (10%). Six neuroradiologists created the ground truth (GT). Additional Internal validation (IV, three institutions) using 70 MRIs, and External validation (EV, single institution) using 40 MRIs through measuring the Dice Similarity Coefficient (DSC) of Enh., Ed. ,and Enh. + Ed. (WholeLesion/WL) tumor tissue and repeatability testing on 14 subjects from the TCIA MGH-QIN-GBM dataset using volume correlations between timepoints were performed.
Results: IV Preoperative median DSC Enh. 0.89 (SD 0.11), Ed. 0.88 (0.28), WL 0.88 (0.11). EV Preoperative median DSC Enh. 0.82 (0.09), Ed. 0.83 (0.11), WL 0.86 (0.06). IV Postoperative median DSC Enh. 0.77 (SD 0.20), Ed 0.78. (SD 0.09), WL 0.78 (SD 0.11). EV Postoperative median DSC Enh. 0.75 (0.21), Ed 0.74 (0.12), WL 0.79 (0.07). Repeatability testing; Intraclass Correlation Coefficient of 0.95 Enh. and 0.92 Ed.
Conclusion: NS-HGlio is accurate, repeatable, and generalizable. The output can be used for visualization, documentation, treatment response monitoring, radiation planning, intra-operative targeting, and estimation of Residual Tumor Volume among others.
(© The Author(s) 2022. Published by Oxford University Press, the Society for Neuro-Oncology and the European Association of Neuro-Oncology.)
References: Neuro Oncol. 2015 Sep;17(9):1188-98. (PMID: 26250565)
J Neurosurg. 2017 Oct;127(4):798-806. (PMID: 28059651)
AJNR Am J Neuroradiol. 2014 Mar;35(3):498-503. (PMID: 23988756)
Radiology. 2014 Apr;271(1):200-10. (PMID: 24475840)
Sci Data. 2017 Sep 05;4:170117. (PMID: 28872634)
Eur Radiol. 2009 Mar;19(3):599-609. (PMID: 18925402)
J Neurooncol. 2013 Apr;112(2):165-72. (PMID: 23397270)
J Clin Oncol. 2010 Apr 10;28(11):1963-72. (PMID: 20231676)
Clin Cancer Res. 2021 Jul 15;27(14):3916-3925. (PMID: 33863808)
Pathol Oncol Res. 2014 Oct;20(4):777-87. (PMID: 25156108)
Neuro Oncol. 2022 May 4;24(5):770-778. (PMID: 34751786)
IEEE Trans Med Imaging. 2015 Oct;34(10):1993-2024. (PMID: 25494501)
JAMA. 2013 Nov 6;310(17):1842-50. (PMID: 24193082)
J Neurooncol. 2013 May;112(3):427-35. (PMID: 23417358)
AJNR Am J Neuroradiol. 2015 Sep;36(9):1654-61. (PMID: 26066626)
Neurotherapeutics. 2017 Apr;14(2):307-320. (PMID: 28108885)
Oncogene. 2016 Nov 10;35(45):5819-5825. (PMID: 27041580)
Neuro Oncol. 2020 Dec 18;22(12):1822-1830. (PMID: 32328652)
Neuroimage Clin. 2019;22:101727. (PMID: 30825711)
Neuro Oncol. 2013 Nov;15 Suppl 2:ii1-56. (PMID: 24137015)
AJNR Am J Neuroradiol. 2005 Apr;26(4):770-6. (PMID: 15814919)
Lancet Oncol. 2019 May;20(5):728-740. (PMID: 30952559)
J Clin Oncol. 2001 Jan 15;19(2):551-7. (PMID: 11208850)
Sci Rep. 2016 Mar 22;6:23376. (PMID: 27001047)
معلومات مُعتمدة: P50 CA211015 United States CA NCI NIH HHS; R01 CA270027 United States CA NCI NIH HHS
فهرسة مساهمة: Keywords: RANO; artificial intelligence; glioma; machine learning; segmentation
تواريخ الأحداث: Date Created: 20230123 Latest Revision: 20230616
رمز التحديث: 20240628
مُعرف محوري في PubMed: PMC9850874
DOI: 10.1093/noajnl/vdac184
PMID: 36685009
قاعدة البيانات: MEDLINE
الوصف
تدمد:2632-2498
DOI:10.1093/noajnl/vdac184