Browsing by Author "Ersoy, Eda Ozgu"

Now showing 1 - 3 of 3

Accurate Dictionary Matching for Mr Fingerprinting Using Neural Networks and Feature Extraction
(Institute of Electrical and Electronics Engineers Inc., 2020-10-05) Soyak R.; Ersoy E.O.; Navruz E.; Fakultesi M.; Unay D.; Oksuz I.; Ersoy, Eda Ozgu; Unay, Devrim; Navruz, Ebru; Fakultesi, Muhendislik; Soyak, Refik; Oksuz, Ilkay
Magnetic Resonance Fingerprinting is a recent technique which aims at providing simultaneous measurements of multiple parameters. MRF works by varying acquisition parameters in a pseudorandom manner so as to get unique, uncorrelated signal evolutions from each tissue. MRF is a dictionary based approach, and thus requires a database. This database can be created by simulating the signal evolutions from first principles using different physical models for a wide variety of tissue parameter combinations. Having this dictionary, a pattern recognition algorithm is used to match the acquired signal evolutions from each voxel with each signal evolution in the dictionary. In this paper, we compare the efficiency of deep learning based feature extraction method and neural network architectures in order to achieve state-of-the-art accuracy in dictionary matching for MRF. Our results showcase successful dictionary matching with high accuracy both quantitatively and qualitatively. © 2020 IEEE.
Citation - Scopus: 1
Binocular Vision Based Convolutional Networks
(Institute of Electrical and Electronics Engineers Inc., 2020-10-05) Oktar Y.; Ulucan O.; Karakaya D.; Ersoy E.O.; Türkan, Mehmet; Ulucan, Oguzhan; Ersoy, Eda Ozgu; Karakaya, Diclehan; Oktar, Yigit
It is arguable that whether the single camera captured (monocular) image datasets are sufficient enough to train and test convolutional neural networks (CNNs) for imitating the biological neural network structures of the human brain. As human visual system works in binocular, the collaboration of the eyes with the two brain lobes needs more investigation for improvements in such CNN-based visual imagery analysis applications. It is indeed questionable that if respective visual fields of each eye and the associated brain lobes are responsible for different learning abilities of the same scene. There are such open questions in this field of research which need rigorous investigation in order to further understand the nature of the human visual system, hence improve the currently available deep learning applications. This paper analyses a binocular CNNs architecture that is more analogous to the biological structure of the human visual system than the conventional deep learning techniques. While taking a structure called optic chiasma into account, this architecture consists of basically two parallel CNN structures associated with each visual field and the brain lobe, fully connected later possibly as in the primary visual cortex. Experimental results demonstrate that binocular learning of two different visual fields leads to better classification rates on average, when compared to classical CNN architectures. © 2020 IEEE.
Citation - WoS: 13
Citation - Scopus: 15
Channel Attention Networks for Robust Mr Fingerprint Matching
(IEEE-Inst Electrical Electronics Engineers Inc, 2022-04) Soyak, Refik; Navruz, Ebru; Ersoy, Eda Ozgu; Cruz, Gastao; Prieto, Claudia; King, Andrew P.; Unay, Devrim; Oksuz, Ilkay
Objective: Magnetic Resonance Fingerprinting (MRF) enables simultaneous mapping of multiple tissue parameters such as T1 and T2 relaxation times. The working principle of MRF relies on varying acquisition parameters pseudo-randomly, so that each tissue generates its unique signal evolution during scanning. Even though MRF provides faster scanning, it has disadvantages such as erroneous and slow generation of the corresponding parametric maps, which needs to be improved. Moreover, there is a need for explainable architectures for understanding the guiding signals to generate accurate parametric maps. Methods: In this paper, we addressed both of these shortcomings by proposing a novel neural network architecture (CONV-ICA) consisting of a channel-wise attention module and a fully convolutional network. Another contribution of this study is a new channel selection method: attention-based channel selection. Furthermore, the effect of patch size and temporal frames of MRF signal on channel reduction are analyzed by employing a channel-wise attention. Results: The proposed approach, evaluated over 3 simulated MRF signals, reduces error in the reconstruction of tissue parameters by 8.88% for T1 and 75.44% for T2 with respect to state-of-the-art methods. Conclusion: It is demonstrated that channel attention mechanism helps to focus on informative channels and fully convolutional network extracts spatial information achieve the best reconstruction performance. Significance: As a consequence of improvement in fast and accurate manner, presented work can contribute to make MRF appropriate for clinical use.