Scopus
🔓 Açık Erişim YÖKSİS DOI Eşleşti
SJR Q2
Histological tissue classification with a novel statistical filter-based convolutional neural network
Journal of Veterinary Medicine Series C Anatomia Histologia Embryologia · Temmuz 2024
YÖKSİS Kayıtları
Histological tissue classification with a novel statistical filter‐based convolutional neural network
Anatomia, Histologia, Embryologia · 2024 SCI-Expanded
Prof. Dr. ŞAKİR TAŞDEMİR →
Histological tissue classification with a novel statistical filter‐based convolutional neural network
Anatomia, Histologia, Embryologia · 2024 SCI-Expanded
Dr. Öğr. Üyesi NEJAT ÜNLÜKAL →
YÖKSİS Kayıtları — ISSN Eşleşmesi
The Influence of Stomach Volume on the Liver Topography in Cats
2002 ISSN: 0340-2096 SCI 1 atıf
Prof. Dr. EMRULLAH EKEN →
Morphological Studies on Meckel s Diverticulum in Geese Anser Anser Domesticus
2002 ISSN: 0340-2096 SCI 4 atıf
Prof. Dr. EMRULLAH EKEN →
The Distribution of the Cardiac Veins in Angora Rabbits Oryctolagus cuniculus
2007 ISSN: 0340-2096 SCI 8 atıf
Prof. Dr. SADULLAH BAHAR →
The Distribution of the Coronary Arteries in the Angora Rabbit
2007 ISSN: 0340-2096 SSCI
Prof. Dr. SADULLAH BAHAR →
The Distribution of the Coronary Arteries in the Angora Rabbit
2007 ISSN: 0340-2096 SSCI
Prof. Dr. SADULLAH BAHAR →
Comparison of the Morphometric Features of the Left and Right Horse Kidneys A Stereological Approach
2013 ISSN: 03402096 SSCI
Prof. Dr. SADULLAH BAHAR →
The distribution of the coronary arteries in the angora rabbit
2007 ISSN: 0340-2096 SCI-Expanded 1 atıf
Prof. Dr. SADULLAH BAHAR →
Investigation of Developmental Toxicity and Teratogenicity of Macrolide Antibiotics in Cultured Rat Embryos
2008 ISSN: 03402096 SCI-Expanded
Prof. Dr. ZELİHA FAZLIOĞULLARI →
Investigation of Developmental Toxicity and Teratogenicity of Antiemetics on Rat Embryos Cultured In Vitro
2013 ISSN: 03402096 SCI-Expanded
Prof. Dr. ZELİHA FAZLIOĞULLARI →
Human Fetal Sacral Length Measurement for the Assessment of Fetal Growth and Development by Ultrasonography and Dissection
2001 ISSN: 0340-2096 SCI-Expanded
Prof. Dr. AHMET KAĞAN KARABULUT →
Comparison of the Morphometric Features of the Left and Right Horse Kidneys: A Stereological Approach
2013 ISSN: 03402096 SCI-Expanded Q3
Prof. Dr. SADULLAH BAHAR →
Morphological Studies on Meckel’s Diverticulum in Geese (Anser Anser Domesticus)
2002 ISSN: 0340-2096 SCI
Prof. Dr. KAMİL BEŞOLUK →
Comparative Macroanatomic Investigations of the Venous Drainage of the Heart in Akkaraman Sheep and Angora Goats
2001 ISSN: 0340-2096 SCI
Prof. Dr. KAMİL BEŞOLUK →
A three-dimensional reconstructive study of pelvic cavity in the red fox (Vulpes vulpes)
2021 ISSN: 0340-2096 SCI-Expanded Q3
Prof. Dr. EMRULLAH EKEN →
The Distribution of the Cardiac Veins in Angora Rabbits (Oryctolagus cuniculus)
2007 ISSN: 0340-2096 SCI-Expanded Q3
Prof. Dr. SADULLAH BAHAR →
The distribution of the coronary arteries in the angora rabbit
2007 ISSN: 0340-2096 SCI-Expanded
Prof. Dr. SADULLAH BAHAR →
Comparison of the Morphometric Features of the Left and Right HorseKidneys A Stereological Approach
2013 ISSN: 0340-2096 SCI-Expanded
Prof. Dr. SADULLAH BAHAR →
Morphometric analysis of the skull of Hamdani sheep via
Three‐Dimensional
modelling
2022 ISSN: 0340-2096 SCI-Expanded Q2
Prof. Dr. MUSTAFA ORHUN DAYAN →
Investigation of Developmental Toxicity and Teratogenicity of Antiemetics on Rat Embryos Cultured title
2013 ISSN: 03402096 SSCI
Prof. Dr. HASAN ACAR →
Calculation of cerebral hemispheres volume values (grey matter, white matter and lateral ventricle) of sheep and goat: A stereological study
2024 ISSN: 0340-2096 SCI-Expanded Q3
Dr. Öğr. Üyesi SEDAT AYDOĞDU →
Makale Bilgileri
ISSN03402096
Yayın TarihiTemmuz 2024
Cilt / Sayfa53
Scopus ID2-s2.0-85196122824
Erişim🔓 Açık Erişim
Özet
Deep networks have been of considerable interest in literature and have enabled the solution of recent real-world applications. Due to filters that offer feature extraction, Convolutional Neural Network (CNN) is recognized as an accurate, efficient and trustworthy deep learning technique for the solution of image-based challenges. The high-performing CNNs are computationally demanding even if they produce good results in a variety of applications. This is because a large number of parameters limit their ability to be reused on central processing units with low performance. To address these limitations, we suggest a novel statistical filter-based CNN (HistStatCNN) for image classification. The convolution kernels of the designed CNN model were initialized by continuous statistical methods. The performance of the proposed filter initialization approach was evaluated on a novel histological dataset and various histopathological benchmark datasets. To prove the efficiency of statistical filters, three unique parameter sets and a mixed parameter set of statistical filters were applied to the designed CNN model for the classification task. According to the results, the accuracy of GoogleNet, ResNet18, ResNet50 and ResNet101 models were 85.56%, 85.24%, 83.59% and 83.79%, respectively. The accuracy was improved by 87.13% by HistStatCNN for the histological data classification task. Moreover, the performance of the proposed filter generation approach was proved by testing on various histopathological benchmark datasets, increasing average accuracy rates. Experimental results validate that the proposed statistical filters enhance the performance of the network with more simple CNN models.
Yazarlar (5)
1
Nejat Ünlükal
ORCID: 0000-0002-8107-4882
2
Erkan Ülker
3
Merve Solmaz
4
Kübra Uyar
5
Şakir Taşdemir
Anahtar Kelimeler
artificial intelligence
CNN
deep learning
feature extraction
image classification
statistical filter
Kurumlar
Alanya Alaaddin Keykubat University
Alanya Turkey
Konya Technical University
Konya Turkey
Selçuk Üniversitesi
Selçuklu Turkey
Scimago Dergi (ISSN Eşleşmesi)
Journal of Veterinary Medicine Series C: Anatomia Histologia Embryologia
Q2
SJR Skoru0,317
H-Index46
YayıncıWiley-Blackwell Publishing Ltd
ÜlkeUnited Kingdom
Veterinary (miscellaneous) (Q2)
Medicine (miscellaneous) (Q3)
Metrikler
1
Atıf
5
Yazar
6
Anahtar Kelime