Scopus
YÖKSİS DOI Eşleşti
SJR Q1
HMedCaps: a new hybrid capsule network architecture for complex medical images
Neural Computing and Applications · Kasım 2024
YÖKSİS Kayıtları
HMedCaps: a new hybrid capsule network architecture for complex medical images
Neural Computing and Applications · 2024 EI: Engineering Index
Doç. Dr. İLKER ALİ ÖZKAN →
YÖKSİS Kayıtları — ISSN Eşleşmesi
Automatic detection and classification of rotor cage faults in squirrel cage induction motor
2010 ISSN: 0941-0643 SCI-Expanded 6 atıf
Prof. Dr. HAYRİ ARABACI →
Short term load forecasting using fuzzy logic and ANFIS
2015 ISSN: 0941-0643 SCI-Expanded 1 atıf
Dr. Öğr. Üyesi HASAN HÜSEYİN ÇEVİK →
Determination of induction motor parameters with differential evolution algorithm
2012 ISSN: 0941-0643 SCI-Expanded
Prof. Dr. MEHMET ÇUNKAŞ →
Short term load forecasting using fuzzy logic and ANFIS
2015 ISSN: 0941-0643 SCI-Expanded
Prof. Dr. MEHMET ÇUNKAŞ →
Fuzzy logic based induction motor protection system
2013 ISSN: 0941-0643 SCI-Expanded
Prof. Dr. MEHMET ÇUNKAŞ →
Determination of induction motor parameters with differential evolution algorithm
2012 ISSN: 0941-0643 SCI-Expanded
Doç. Dr. TAHİR SAĞ →
Cost optimization of mixed feeds with the particle swarm optimization method
2013 ISSN: 0941-0643 SCI-Expanded
Prof. Dr. ADEM ALPASLAN ALTUN →
A combination of Genetic Algorithm Particle Swarm Optimization and Neural Network for palmprint recognition
2013 ISSN: 0941-0643 SCI-Expanded 1 atıf
Prof. Dr. ADEM ALPASLAN ALTUN →
Cost optimization of mixed feeds with the particle swarm optimization method
2013 ISSN: 0941-0643 SCI-Expanded
Doç. Dr. MEHMET AKİF ŞAHMAN →
Fuzzy logic based induction motor protection system
2013 ISSN: 0941-0643 SCI
Dr. Öğr. Üyesi OKAN UYAR →
A new MILP model proposal in feed formulation and using a hybrid linear binary PSO H LBP approach for alternative solutions
2018 ISSN: 0941-0643 SCI-Expanded Q1
Doç. Dr. MEHMET AKİF ŞAHMAN →
FPGA based self organizing fuzzy controller for electromagnetic filter
2016 ISSN: 0941-0643 SCI-Expanded
Prof. Dr. İSMAİL SARITAŞ →
FPGA-based self-organizing fuzzy controller for electromagnetic filter
2017 ISSN: 0941-0643 SCI-Expanded
Prof. Dr. İSMAİL SARITAŞ →
A new MILP model proposal in feed formulation and using a hybrid linear binary PSO H LBP approach for alternative solutions
2016 ISSN: 0941-0643 SCI-Expanded
Prof. Dr. ADEM ALPASLAN ALTUN →
Application of fuzzy C-means clustering algorithm to spectral features for emotion classification from speech
2018 ISSN: 0941-0643 SCI-Expanded Q1
Prof. Dr. HUMAR KAHRAMANLI ÖRNEK →
A new denoising method for fMRI based on weighted three-dimentional wavelet transform
2018 ISSN: 0941-0643 SCI-Expanded
Dr. Öğr. Üyesi GÜZİN ÖZMEN →
FPGA-based self-organizing fuzzy controller for electromagnetic filter
2017 ISSN: 0941-0643 SCI-Expanded
Prof. Dr. İSMAİL SARITAŞ →
A new MILP model proposal in feed formulation and using a hybrid-linear binary PSO (H-LBP) approach for alternative solutions
2018 ISSN: 0941-0643 SCI-Expanded
Prof. Dr. ADEM ALPASLAN ALTUN →
Hybrid breast cancer detection tem via neural network and feature ion based on SBS SFS and PCA
2013 ISSN: 0941-0643 SCI-Expanded 5 atıf
Dr. Öğr. Üyesi ONUR İNAN →
FPGA-based self-organizing fuzzy controller for electromagnetic filter
2017 ISSN: 0941-0643 SCI-Expanded
Doç. Dr. İLKER ALİ ÖZKAN →
Makale Bilgileri
ISSN09410643
Yayın TarihiKasım 2024
Cilt / Sayfa36 · 20589-20606
Scopus ID2-s2.0-85201230587
Özet
Recognizing and analyzing medical images is crucial for disease early detection and treatment planning with appropriate treatment options based on the patient's individual needs and disease history. Deep learning technologies are widely used in the field of healthcare because they can analyze images rapidly and precisely. However, because each object on the image has the potential to hold illness information in medical images, it is critical to analyze the images with minimal information loss. In this context, Capsule Network (CapsNet) architecture is an important approach that aims to reduce information loss by storing the location and properties of objects in images as capsules. However, because CapsNet maintains information on each object in the image, the existence of several objects in complicated images can impair CapsNet's performance. This work proposes a new model called HMedCaps to improve the performance of CapsNet. In the proposed model, it is aimed to develop a deeper and hybrid structure by using Residual Block and FractalNet module together in the feature extraction layer. While it is aimed to obtain rich feature maps by increasing the number of features extracted by deepening the network, it is aimed to prevent the vanishing gradient problem that may occur in the network with increasing depth with these modules with skip connections. Furthermore, a new squash function is proposed to make distinctive capsules more prominent by customizing capsule activation. The CIFAR10 dataset of complex images, RFMiD dataset of retinal images, and Blood Cell Count Dataset dataset of blood cell images were used to evaluate the study. When the proposed model was compared with the basic CapsNet and studies in the literature, it was observed that the performance in complex images was improved and more accurate classification results were obtained in the field of medical image analysis. The proposed hybrid HMedCaps architecture has the potential to make more accurate diagnoses in the field of medical image analysis.
Yazarlar (2)
1
Sumeyra Busra Sengul
ORCID: 0000-0003-1385-0920
2
Ilker Ali Ozkan
Anahtar Kelimeler
CapsNet
Complex image
FractalNet
Medical image analysis
Squash function
Kurumlar
Selçuk Üniversitesi
Selçuklu Turkey
Scimago Dergi (ISSN Eşleşmesi)
Neural Computing and Applications
Q1
SJR Skoru1,102
H-Index146
YayıncıSpringer London
ÜlkeUnited Kingdom
Artificial Intelligence (Q1)
Software (Q1)
Metrikler
3
Atıf
2
Yazar
5
Anahtar Kelime