Convolutional attention network for MRI-based Alzheimer's disease classification and its interpretability analysis

Basit Öğe Kaydı
dc.authorid0000-0001-6309-4524
dc.authorid0000-0002-8649-6013
dc.contributor.authorTürkan, Yaseminen_US
dc.contributor.authorTek, Faik Borayen_US
dc.date.accessioned2022-05-23T17:00:46Z
dc.date.available2022-05-23T17:00:46Z
dc.date.issued2021-09-17
dc.departmentIşık Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering, Department of Computer Engineeringen_US
dc.description.abstractNeuroimaging techniques, such as Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET), help to identify Alzheimer's disease (AD). These techniques generate large-scale, high-dimensional, multimodal neuroimaging data, which is time-consuming and difficult to interpret and classify. Therefore, interest in deep learning approaches for the classification of 3D structural MRI brain scans has grown rapidly. In this research study, we improved the 3D VGG model proposed by Korolev et al. [2]. We increased the filters in the 3D convolutional layers and then added an attention mechanism for better classification. We compared the performance of the proposed approaches for the classification of Alzheimer's disease versus mild cognitive impairments and normal cohorts on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. We observed that both the accuracy and area under curve results improved with the proposed models. However, deep neural networks are black boxes that produce predictions that require further explanation for medical usage. We compared the 3D-data interpretation capabilities of the proposed models using four different interpretability methods: Occlusion, 3D Ultrametric Contour Map, 3D Gradient-Weighted Class Activation Mapping, and SHapley Additive explanations (SHAP). We observed that explanation results differed in different network models and data classes.en_US
dc.identifier.citationTürkan, Y. & Tek, F. B. (2021). Convolutional attention network for MRI-based Alzheimer's disease classification and its interpretability analysis. Paper presented at the 2021 6th International Conference on Computer Science and Engineering (UBMK), 151-156. doi:10.1109/UBMK52708.2021.9558882en_US
dc.identifier.doi10.1109/UBMK52708.2021.9558882
dc.identifier.endpage156
dc.identifier.isbn9781665429085
dc.identifier.isbn9781665429078
dc.identifier.isbn9781665429092
dc.identifier.issn2521-1641
dc.identifier.issn2768-0592
dc.identifier.scopus2-s2.0-85125875116
dc.identifier.scopusqualityN/A
dc.identifier.startpage151
dc.identifier.urihttps://hdl.handle.net/11729/4351
dc.identifier.urihttp://dx.doi.org/10.1109/UBMK52708.2021.9558882
dc.indekslendigikaynakScopusen_US
dc.institutionauthorTürkan, Yaseminen_US
dc.institutionauthorTek, Faik Borayen_US
dc.institutionauthorid0000-0001-6309-4524
dc.institutionauthorid0000-0002-8649-6013
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherIEEEen_US
dc.relation.ispartof2021 6th International Conference on Computer Science and Engineering (UBMK)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subject3D Modelingen_US
dc.subject3D Structural MRI brain scansen_US
dc.subject3D Ultrametric contour mapen_US
dc.subject3D VGG modelen_US
dc.subject3D-Data interpretation capabilitiesen_US
dc.subjectActivation analysisen_US
dc.subjectActivation mappingen_US
dc.subjectAlzheimer’s diseaseen_US
dc.subjectAlzheimers diseaseen_US
dc.subjectAttentionen_US
dc.subjectAttention mechanismen_US
dc.subjectBiomedical MRIen_US
dc.subjectBrainen_US
dc.subjectChemical activationen_US
dc.subjectClassification (of information)en_US
dc.subjectCognitionen_US
dc.subjectContour mapen_US
dc.subjectConvolutionen_US
dc.subjectConvolutional attention networken_US
dc.subjectConvolutional networksen_US
dc.subjectConvolutional neural networksen_US
dc.subjectDeep learningen_US
dc.subjectDeep learning approachesen_US
dc.subjectDeep neural networksen_US
dc.subjectDifferent interpretability methodsen_US
dc.subjectDifferent network modelsen_US
dc.subjectDiseasesen_US
dc.subjectHeating systemsen_US
dc.subjectHigh-dimensional neuroimaging dataen_US
dc.subjectImage classificationen_US
dc.subjectInterpretabilityen_US
dc.subjectInterpretability analysisen_US
dc.subjectLearning (artificial intelligence)en_US
dc.subjectMagnetic resonance imagingen_US
dc.subjectMappingen_US
dc.subjectMedical image processingen_US
dc.subjectMild cognitive impairmentsen_US
dc.subjectMRIen_US
dc.subjectMRI-based Alzheimeren_US
dc.subjectMultimodal neuroimaging dataen_US
dc.subjectNeural netsen_US
dc.subjectNeurodegenerative diseasesen_US
dc.subjectNeuroimagingen_US
dc.subjectNeuroimaging techniquesen_US
dc.subjectNeurophysiologyen_US
dc.subjectOcclusionen_US
dc.subjectPositron emission tomographyen_US
dc.subjectSHAPen_US
dc.subjectShapleyen_US
dc.subjectShapley additive explanationen_US
dc.subjectSolid modelingen_US
dc.subjectThree-dimensional displaysen_US
dc.subjectUltrametricsen_US
dc.subjectVisualizationen_US
dc.titleConvolutional attention network for MRI-based Alzheimer's disease classification and its interpretability analysisen_US
dc.typeConference Objecten_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
11729-4351.pdf
Boyut:
790.32 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Publisher's Version
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

MF - Bildiri Koleksiyonu | Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu