دورية أكاديمية
أعرض في EDS

Classification of Pulmonary Nodules in 2-[ 18 F]FDG PET/CT Images with a 3D Convolutional Neural Network.

التفاصيل البيبلوغرافية
العنوان: Classification of Pulmonary Nodules in 2-[ 18 F]FDG PET/CT Images with a 3D Convolutional Neural Network.
المؤلفون: Alves VM; Faculty of Economics, University of Porto, Rua Dr. Roberto Frias, Porto, 4200-464 Porto, Portugal.; Department of Nuclear Medicine, University Hospital Center of São João, Alameda Prof. Hernâni Monteiro, 4200-319 Porto, Portugal., Dos Santos Cardoso J; Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal.; Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Rua Dr. Roberto Frias, 4200-465 Porto, Portugal., Gama J; Faculty of Economics, University of Porto, Rua Dr. Roberto Frias, Porto, 4200-464 Porto, Portugal.; Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Rua Dr. Roberto Frias, 4200-465 Porto, Portugal.
المصدر: Nuclear medicine and molecular imaging [Nucl Med Mol Imaging] 2024 Feb; Vol. 58 (1), pp. 9-24. Date of Electronic Publication: 2023 Aug 30.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Springer Country of Publication: Germany NLM ID: 101530478 Publication Model: Print-Electronic Cited Medium: Print ISSN: 1869-3474 (Print) Linking ISSN: 18693474 NLM ISO Abbreviation: Nucl Med Mol Imaging Subsets: PubMed not MEDLINE
أسماء مطبوعة: Original Publication: Heidelberg : Springer
مستخلص: Purpose: 2-[ 18 F]FDG PET/CT plays an important role in the management of pulmonary nodules. Convolutional neural networks (CNNs) automatically learn features from images and have the potential to improve the discrimination between malignant and benign pulmonary nodules. The purpose of this study was to develop and validate a CNN model for classification of pulmonary nodules from 2-[ 18 F]FDG PET images.
Methods: One hundred thirteen participants were retrospectively selected. One nodule per participant. The 2-[ 18 F]FDG PET images were preprocessed and annotated with the reference standard. The deep learning experiment entailed random data splitting in five sets. A test set was held out for evaluation of the final model. Four-fold cross-validation was performed from the remaining sets for training and evaluating a set of candidate models and for selecting the final model. Models of three types of 3D CNNs architectures were trained from random weight initialization (Stacked 3D CNN, VGG-like and Inception-v2-like models) both in original and augmented datasets. Transfer learning, from ImageNet with ResNet-50, was also used.
Results: The final model (Stacked 3D CNN model) obtained an area under the ROC curve of 0.8385 (95% CI: 0.6455-1.0000) in the test set. The model had a sensibility of 80.00%, a specificity of 69.23% and an accuracy of 73.91%, in the test set, for an optimised decision threshold that assigns a higher cost to false negatives.
Conclusion: A 3D CNN model was effective at distinguishing benign from malignant pulmonary nodules in 2-[ 18 F]FDG PET images.
Supplementary Information: The online version contains supplementary material available at 10.1007/s13139-023-00821-6.
Competing Interests: Competing InterestsVictor Manuel Alves, Jaime dos Santos Cardoso, and João Gama declare no conflict of interest.
(© The Author(s) 2023.)
References: Comput Intell Neurosci. 2019 Dec 31;2019:5065214. (PMID: 32082370)
Magn Reson Imaging. 2012 Nov;30(9):1323-41. (PMID: 22770690)
Nature. 2015 May 28;521(7553):436-44. (PMID: 26017442)
Arch Pathol Lab Med. 2013 Apr;137(4):558-65. (PMID: 23544945)
Radiology. 2020 May;295(2):328-338. (PMID: 32154773)
Ann Transl Med. 2022 Dec;10(23):1265. (PMID: 36618813)
EBioMedicine. 2021 Nov;73:103631. (PMID: 34678610)
J Thorac Dis. 2018 Apr;10(Suppl 7):S846-S859. (PMID: 29780631)
PLoS Med. 2014 Oct 14;11(10):e1001744. (PMID: 25314315)
Eur J Radiol. 2003 Jan;45(1):60-8. (PMID: 12499065)
Eur J Nucl Med Mol Imaging. 2019 Dec;46(13):2638-2655. (PMID: 31240330)
Chest. 2005 Oct;128(4):2490-6. (PMID: 16236914)
Cell. 2018 Feb 22;172(5):1122-1131.e9. (PMID: 29474911)
Nat Commun. 2021 Nov 2;12(1):6311. (PMID: 34728629)
Nat Med. 2018 Sep;24(9):1342-1350. (PMID: 30104768)
Lancet Digit Health. 2022 Apr;4(4):e256-e265. (PMID: 35337643)
Asia Ocean J Nucl Med Biol. 2019 Winter;7(1):29-37. (PMID: 30705909)
Clin Lung Cancer. 2020 Sep;21(5):e417-e422. (PMID: 32276869)
Sci Rep. 2017 Aug 24;7(1):9370. (PMID: 28839156)
N Engl J Med. 2011 Aug 4;365(5):395-409. (PMID: 21714641)
Comput Biol Med. 2021 Dec;139:104924. (PMID: 34688173)
Biomed Res Int. 2018 Mar 28;2018:9453967. (PMID: 29789808)
J Clin Med. 2021 Oct 29;10(21):. (PMID: 34768584)
Nature. 2017 Feb 2;542(7639):115-118. (PMID: 28117445)
Front Neuroinform. 2018 Jun 19;12:35. (PMID: 29970996)
Nucl Med Commun. 2020 Jun;41(6):560-566. (PMID: 32282636)
Lancet Digit Health. 2021 May;3(5):e317-e329. (PMID: 33890579)
Nucl Med Commun. 2017 Jan;38(1):67-75. (PMID: 27741214)
Lancet Digit Health. 2021 Aug;3(8):e486-e495. (PMID: 34325853)
CA Cancer J Clin. 2021 May;71(3):209-249. (PMID: 33538338)
Nat Med. 2019 Jun;25(6):954-961. (PMID: 31110349)
Mol Imaging Radionucl Ther. 2022 Jun 27;31(2):82-88. (PMID: 35770958)
JAMA. 2017 Dec 12;318(22):2199-2210. (PMID: 29234806)
Thorax. 2016 Apr;71(4):367-75. (PMID: 26921304)
Clin Lung Cancer. 2020 Jan;21(1):47-55. (PMID: 31474376)
Thorax. 2015 Aug;70 Suppl 2:ii1-ii54. (PMID: 26082159)
BMC Bioinformatics. 2011 Mar 17;12:77. (PMID: 21414208)
Radiology. 2017 Jul;284(1):228-243. (PMID: 28240562)
PLoS Med. 2018 Nov 20;15(11):e1002686. (PMID: 30457988)
Cancer Treat Res. 2016;170:47-75. (PMID: 27535389)
Nat Biomed Eng. 2021 Jun;5(6):509-521. (PMID: 33859385)
J Big Data. 2021;8(1):101. (PMID: 34306963)
Eur J Nucl Med Mol Imaging. 2021 Feb;48(2):350-360. (PMID: 32776232)
Phys Imaging Radiat Oncol. 2021 Nov 09;20:69-75. (PMID: 34816024)
IEEE Trans Neural Netw. 1999;10(5):988-99. (PMID: 18252602)
Radiology. 2016 Aug;280(2):576-84. (PMID: 26909647)
Breathe (Sheff). 2019 Mar;15(1):15-23. (PMID: 30838056)
Biometrics. 1988 Sep;44(3):837-45. (PMID: 3203132)
J Digit Imaging. 2013 Jun;26(3):447-56. (PMID: 22850933)
Eur J Cancer. 2019 Sep;119:11-17. (PMID: 31401469)
AJR Am J Roentgenol. 2005 Jan;184(1):14-9. (PMID: 15615943)
Diagnostics (Basel). 2020 Sep 15;10(9):. (PMID: 32942729)
Front Oncol. 2021 Dec 17;11:727094. (PMID: 34976790)
فهرسة مساهمة: Keywords: 2-[18F]FDG PET/CT; Artificial intelligence; Convolutional neural networks; Positron emission tomography; Pulmonary nodules
تواريخ الأحداث: Date Created: 20240123 Latest Revision: 20240125
رمز التحديث: 20240125
مُعرف محوري في PubMed: PMC10796312
DOI: 10.1007/s13139-023-00821-6
PMID: 38261899
قاعدة البيانات: MEDLINE
الوصف
تدمد:1869-3474
DOI:10.1007/s13139-023-00821-6