An Efficient and Robust 3d Medical Image Classification Approach Based on 3d Cnn, Time-Distributed 2d Cnn-Blstm Models, and Mrmr Feature Selection

dc.authorscopusid 57218549439
dc.authorscopusid 57193696379
dc.authorwosid AKBACAK, ENVER/AAA-7122-2021
dc.authorwosid muzoglu, nedim/HNI-4228-2023
dc.contributor.author Akbacak, Enver
dc.contributor.author Muzoglu, Nedim
dc.contributor.other Bilgisayar Mühendisliği Bölümü
dc.date.accessioned 2025-01-11T13:03:22Z
dc.date.available 2025-01-11T13:03:22Z
dc.date.issued 2024
dc.department Fenerbahçe University en_US
dc.department-temp [Akbacak, Enver] Fenerbahce Univ, Fac Engn, Dept Comp Engn, Istanbul, Turkiye; [Muzoglu, Nedim] Univ Hlth Sci, Inst Hlth Sci, Dept Bioengn, Istanbul, Turkiye en_US
dc.description.abstract The advent of 3D medical imaging has been a turning point in the diagnosis of various diseases, as voxel information from adjacent slices helps radiologists better understand complex anatomical relationships. However, the interpretation of medical images by radiologists with different levels of expertise can vary and is also time-consuming. In the last decades, artificial intelligence-based computer-aided systems have provided fast and more reliable diagnostic insights with great potential for various clinical purposes. This paper proposes a significant deep learning based 3D medical image diagnosis method. The method classifies MedMNIST3D, which consists of six 3D biomedical datasets obtained from CT, MRA, and electron microscopy modalities. The proposed method concatenates 3D image features extracted from three independent networks, a 3D CNN, and two time-distributed ResNet BLSTM structures. The ultimate discriminative features are selected via the minimum redundancy maximum relevance (mRMR) feature selection method. Those features are then classified by a neural network model. Experiments adhere to the rules of the official splits and evaluation metrics of the MedMNIST3D datasets. The results reveal that the proposed approach outperforms similar studies in terms of accuracy and AUC. en_US
dc.description.woscitationindex Science Citation Index Expanded
dc.identifier.citation 0
dc.identifier.doi 10.1111/coin.70000
dc.identifier.issn 0824-7935
dc.identifier.issn 1467-8640
dc.identifier.issue 5 en_US
dc.identifier.scopus 2-s2.0-85207524161
dc.identifier.scopusquality Q2
dc.identifier.uri https://doi.org/10.1111/coin.70000
dc.identifier.uri https://hdl.handle.net/20.500.14627/264
dc.identifier.volume 40 en_US
dc.identifier.wos WOS:001368179700001
dc.identifier.wosquality Q3
dc.language.iso en en_US
dc.publisher Wiley en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/closedAccess en_US
dc.scopus.citedbyCount 2
dc.subject 3D Classification en_US
dc.subject 3D Cnn en_US
dc.subject Blstm en_US
dc.subject Fitcnet en_US
dc.subject Mrmr Feature Selection en_US
dc.subject Time-Distributed Resnet en_US
dc.title An Efficient and Robust 3d Medical Image Classification Approach Based on 3d Cnn, Time-Distributed 2d Cnn-Blstm Models, and Mrmr Feature Selection en_US
dc.type Article en_US
dc.wos.citedbyCount 1
dspace.entity.type Publication
relation.isAuthorOfPublication 5475b6ea-6aa9-4763-ba07-dba75c8f8e9d
relation.isAuthorOfPublication.latestForDiscovery 5475b6ea-6aa9-4763-ba07-dba75c8f8e9d
relation.isOrgUnitOfPublication 85e04a04-fb9d-4894-961f-e92f27bb6cb6
relation.isOrgUnitOfPublication.latestForDiscovery 85e04a04-fb9d-4894-961f-e92f27bb6cb6

Files