Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Investigating the Performance of Generative Adversarial Networks for Prostate Tissue Detection and Segmentation
Date
2020-09-01
Author
Birbiri, Ufuk Cem
Hamidinekoo, Azam
Grall, Amelie
Malcolm, Paul
Zwiggelaar, Reyer
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
194
views
0
downloads
Cite This
The manual delineation of region of interest (RoI) in 3D magnetic resonance imaging (MRI) of the prostate is time-consuming and subjective. Correct identification of prostate tissue is helpful to define a precise RoI to be used in CAD systems in clinical practice during diagnostic imaging, radiotherapy and monitoring the progress of disease. Conditional GAN (cGAN), cycleGAN and U-Net models and their performances were studied for the detection and segmentation of prostate tissue in 3D multi-parametric MRI scans. These models were trained and evaluated on MRI data from 40 patients with biopsy-proven prostate cancer. Due to the limited amount of available training data, three augmentation schemes were proposed to artificially increase the training samples. These models were tested on a clinical dataset annotated for this study and on a public dataset (PROMISE12). The cGAN model outperformed the U-Net and cycleGAN predictions owing to the inclusion of paired image supervision. Based on our quantitative results, cGAN gained a Dice score of 0.78 and 0.75 on the private and the PROMISE12 public datasets, respectively.
Subject Keywords
Prostate MRI
,
Generative adversarial network
,
Segmentation
,
Computer aided diagnosis
,
Detection
URI
https://hdl.handle.net/11511/68122
Journal
JOURNAL OF IMAGING
DOI
https://doi.org/10.3390/jimaging6090083
Collections
Department of Computer Engineering, Article
Suggestions
OpenMETU
Core
Enhancing induced current magnetic resonance electrical impedance tomography ICMREIT image reconstruction
NAJI, NASHWAN; EROĞLU, HASAN HÜSEYİN; SÜMSER, KEMAL; SADIGHI, MEHDI; Eyüboğlu, Behçet Murat (2016-02-15)
Induced Current Magnetic Resonance Electrical Impedance Tomography (ICMREIT) is an emerging imaging methodology that utilizes Magnetic Resonance Imaging (MRI) techniques to visualize the electrical conductivity as a new contrast. In ICMREIT, by fast switching of gradient fields of Magnetic Resonance (MR) system eddy currents are induced in the imaging volume. The secondary magnetic field generated by the induced eddy currents can be extracted from the MR phase images. Image reconstruction algorithms then us...
An Improved Receiver for Harmonic Motion Microwave Doppler Imaging
Soydan, Damla Alptekin; Irgin, Umit; Top, Can Baris; Gençer, Nevzat Güneri (2020-03-01)
© 2020 EurAAP.Harmonic motion microwave Doppler imaging is a novel imaging modality that combines focused ultrasound and radar techniques to obtain data based on mechanical and electrical properties of the tissue. In previous experimental studies, the Doppler component of the scattered signal is sensed and used to create 2D images of a tumor inside a homogeneous fat phantom. Due to the drawbacks of the receiver configuration, scanning time was high, the signal-to-noise ratio was low, and the multi-frequency...
Realization of magnetic resonance current density imaging at 3 Tesla,
Göksu, Cihan; SADIGHI, MEHDI; Eyüboğlu, Behçet Murat (2014-08-26)
Magnetic Resonance Current Density Imaging (MRCDI) is an imaging modality, which reconstructs electrical current density distribution inside a material by using Magnetic Resonance Imaging (MRI) techniques. In this study, a current source with maximum current injection capability of 224.7mA, under 1k Omega resistive load is used. Experiments are performed with a 2D uniform phantom, in which a current steering insulator is inserted. Magnetic flux density distributions are measured, and current density images ...
Experimental and mathematical investigation of mass transfer in food andhydrogel systems using magnetic resonance imaging and NMR relaxometry
Çıkrıkcı, Sevil; Öztop, Halil Mecit; Department of Food Engineering (2019)
Nuclear magnetic resonance (NMR) and Magnetic Resonance Imaging (MRI) are well-known non-invasive characterization methods used in a wide range of areas; from medical to food applications. NMR experiments are conducted either through spectroscopy with high resolution systems or with relaxometery (Time Domain NMR) through mid or low field systems. Time domain NMR is primarily based on relaxation times and diffusion measurements from the signal coming from the whole sample while MRI enables to visualize the i...
Visualisation of cakes differing in oil content with magnetic resonance imaging
Kırtıl, Emrah; Aydogdu, AYÇA; Bulut, Elif Yildiz; Tatar, Betul Cilek; Öztop, Halil Mecit (Informa UK Limited, 2017-01-01)
Magnetic resonance imaging (MRI) is a non-invasive imaging technique that can visualise samples' interior by using the signal coming from mobile protons. The aim of this study was to examine the effects of oil content and peanut/raisin addition on cake quality and to illustrate the power of MRI in analysis of moisture and oil distribution. For this purpose, MR images were acquired with a spin echo sequence and relaxation times T-1 and T-2, and moisture content and firmness of cakes were measured. High oil c...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
U. C. Birbiri, A. Hamidinekoo, A. Grall, P. Malcolm, and R. Zwiggelaar, “Investigating the Performance of Generative Adversarial Networks for Prostate Tissue Detection and Segmentation,”
JOURNAL OF IMAGING
, pp. 0–0, 2020, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/68122.