Machine learning approaches in the interpretation of endobronchial ultrasound images: a comparative analysis

Basit Öğe Kaydı
dc.authoridKoseoglu, Fatos Dilan/0000-0002-3947-0355
dc.authoridER, Orhan/0000-0002-4732-9490
dc.authorwosidKoseoglu, Fatos Dilan/JFB-6243-2023
dc.contributor.authorKoseoglu, Fatos Dilan
dc.contributor.authorAlici, Ibrahim Onur
dc.contributor.authorEr, Orhan
dc.date.accessioned2024-03-09T18:48:15Z
dc.date.available2024-03-09T18:48:15Z
dc.date.issued2023
dc.departmentİzmir Bakırçay Üniversitesien_US
dc.description.abstractBackgroundThis study explores the application of machine learning (ML) in analyzing endobronchial ultrasound (EBUS) images for the detection of lymph node (LN) malignancy, aiming to augment diagnostic accuracy and efficiency. We investigated whether ML could outperform conventional classification systems in identifying malignant involvement of LNs, based on eight established sonographic features.MethodsRetrospective data from two tertiary care hospital bronchoscopy units were utilized, encompassing healthcare reports of patients who had undergone EBUS between January 2017 and March 2023. The ML model was trained and tested using MATLAB, with 80% of the data allocated for training/validation, and 20% for testing. Performance was evaluated based on validation and testing accuracy, and receiver operating characteristic curves with comparing trained models and existing classification rules.ResultsThe study analyzed 992 LNs, with 42.3% malignancy prevalence. Malignant LNs showed characteristic features such as larger size and distinct margins. The fine tuned models achieved testing accuracies of 95.9% and 96.4% for fine Gaussian SVM and KNN, respectively. Corresponding AUROC's were 0.955 and 0.963, outperforming other similar studies and conventional analyses.ConclusionFine tuned ML applications like SVM and KNN, can significantly enhance the analysis of EBUS images, improving diagnostic accuracy.en_US
dc.identifier.doi10.1007/s00464-023-10488-x
dc.identifier.issn0930-2794
dc.identifier.issn1432-2218
dc.identifier.pmid37903885en_US
dc.identifier.scopus2-s2.0-85175205235en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org/10.1007/s00464-023-10488-x
dc.identifier.urihttps://hdl.handle.net/20.500.14034/1253
dc.identifier.wosWOS:001094642700002en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakPubMeden_US
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.relation.ispartofSurgical Endoscopy and Other Interventional Techniquesen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectArtificial Intelligence; Endobronchial Ultrasound; Lymph Nodes; Machine Learning; Medical Imagingen_US
dc.titleMachine learning approaches in the interpretation of endobronchial ultrasound images: a comparative analysisen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
1253.pdf
Boyut:
1.35 MB
Biçim:
Adobe Portable Document Format
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu