A joint convolutional?recurrent neural network with an attention mechanism for detecting intracranial hemorrhage on noncontrast head CT

Basit Öğe Kaydı
dc.authoridCeren Aliş / 0000-0001-9433-4826en_US
dc.authorscopusidCeren Aliş / 57201722345
dc.authorwosidCeren Aliş / GYJ-2640-2022
dc.contributor.authorAliş, Deniz
dc.contributor.authorAliş, Ceren
dc.contributor.authorYergin, Mert
dc.contributor.authorTopel, Çağdaş
dc.contributor.authorAsmakutlu, Ozan
dc.contributor.authorBağcılar, Ömer
dc.contributor.authorDeniz Şenli, Yeşeren
dc.contributor.authorÜstündağ, Ahmet
dc.contributor.authorSalt, Vefa
dc.contributor.authorNacar Doğan, Sebahat
dc.contributor.authorVelioğlu, Murat
dc.contributor.authorSelçuk, Hakan Hatem
dc.contributor.authorKara, Batuhan
dc.contributor.authorÖzer, Caner
dc.contributor.authorÖksüz, İlkay
dc.contributor.authorKızılkılıç, Osman
dc.contributor.authorKaraarslan, Ercan
dc.date.accessioned2022-05-31T05:52:08Z
dc.date.available2022-05-31T05:52:08Z
dc.date.issued2022en_US
dc.departmentİstinye Üniversitesi, Hastaneen_US
dc.description.abstractTo investigate the performance of a joint convolutional neural networks-recurrent neural networks (CNN-RNN) using an attention mechanism in identifying and classifying intracranial hemorrhage (ICH) on a large multi-center dataset; to test its performance in a prospective independent sample consisting of consecutive real-world patients. All consecutive patients who underwent emergency non-contrast-enhanced head CT in five different centers were retrospectively gathered. Five neuroradiologists created the ground-truth labels. The development dataset was divided into the training and validation set. After the development phase, we integrated the deep learning model into an independent center's PACS environment for over six months for assessing the performance in a real clinical setting. Three radiologists created the ground-truth labels of the testing set with a majority voting. A total of 55,179 head CT scans of 48,070 patients, 28,253 men (58.77%), with a mean age of 53.84 ± 17.64 years (range 18-89) were enrolled in the study. The validation sample comprised 5211 head CT scans, with 991 being annotated as ICH-positive. The model's binary accuracy, sensitivity, and specificity on the validation set were 99.41%, 99.70%, and 98.91, respectively. During the prospective implementation, the model yielded an accuracy of 96.02% on 452 head CT scans with an average prediction time of 45 ± 8 s. The joint CNN-RNN model with an attention mechanism yielded excellent diagnostic accuracy in assessing ICH and its subtypes on a large-scale sample. The model was seamlessly integrated into the radiology workflow. Though slightly decreased performance, it provided decisions on the sample of consecutive real-world patients within a minute.en_US
dc.identifier.citationAlis D, Alis C, Yergin M, Topel C, Asmakutlu O, Bagcilar O, Senli YD, Ustundag A, Salt V, Dogan SN, Velioglu M, Selcuk HH, Kara B, Ozer C, Oksuz I, Kizilkilic O, Karaarslan E. A joint convolutional-recurrent neural network with an attention mechanism for detecting intracranial hemorrhage on noncontrast head CT. Sci Rep. 2022 Feb 8;12(1):2084. doi: 10.1038/s41598-022-05872-x. PMID: 35136123; PMCID: PMC8826390.en_US
dc.identifier.doi10.1038/s41598-022-05872-xen_US
dc.identifier.issn2045-2322en_US
dc.identifier.issue1en_US
dc.identifier.pmid35136123en_US
dc.identifier.urihttp://doi.org/10.1038/s41598-022-05872-x
dc.identifier.urihttps://hdl.handle.net/20.500.12713/2752
dc.identifier.volume12en_US
dc.indekslendigikaynakPubMeden_US
dc.institutionauthorAliş, Ceren
dc.language.isoenen_US
dc.publisherNatureen_US
dc.relation.ispartofScientific Reportsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.titleA joint convolutional?recurrent neural network with an attention mechanism for detecting intracranial hemorrhage on noncontrast head CTen_US
dc.typeAnnotationen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
s41598-022-05872-x.pdf
Boyut:
1.56 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

PubMed İndeksli Yayınlar Koleksiyonu
İSÜ Hastaneleri Makale Koleksiyonu