scholarly journals Accuracy Validation of an Automated Method for Prostate Segmentation in Magnetic Resonance Imaging

2017 ◽  
Vol 30 (6) ◽  
pp. 782-795 ◽  
Author(s):  
Maysam Shahedi ◽  
Derek W. Cool ◽  
Glenn S. Bauman ◽  
Matthew Bastian-Jordan ◽  
Aaron Fenster ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Resonance Imaging ◽  
Automated Method ◽  
Prostate Segmentation ◽  
Accuracy Validation

scholarly journals Deep Learning-Based Methods for Prostate Segmentation in Magnetic Resonance Imaging

2021 ◽  
Vol 11 (2) ◽  
pp. 782 ◽  
Author(s):  
Albert Comelli ◽  
Navdeep Dahiya ◽  
Alessandro Stefano ◽  
Federica Vernuccio ◽  
Marzia Portoghese ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Prostate Gland ◽  
Dice Similarity Coefficient ◽  
Processing Unit ◽  
Imaging Features ◽  
Resonance Imaging ◽  
Central Processing ◽  
Prostate Segmentation

Magnetic Resonance Imaging-based prostate segmentation is an essential task for adaptive radiotherapy and for radiomics studies whose purpose is to identify associations between imaging features and patient outcomes. Because manual delineation is a time-consuming task, we present three deep-learning (DL) approaches, namely UNet, efficient neural network (ENet), and efficient residual factorized convNet (ERFNet), whose aim is to tackle the fully-automated, real-time, and 3D delineation process of the prostate gland on T2-weighted MRI. While UNet is used in many biomedical image delineation applications, ENet and ERFNet are mainly applied in self-driving cars to compensate for limited hardware availability while still achieving accurate segmentation. We apply these models to a limited set of 85 manual prostate segmentations using the k-fold validation strategy and the Tversky loss function and we compare their results. We find that ENet and UNet are more accurate than ERFNet, with ENet much faster than UNet. Specifically, ENet obtains a dice similarity coefficient of 90.89% and a segmentation time of about 6 s using central processing unit (CPU) hardware to simulate real clinical conditions where graphics processing unit (GPU) is not always available. In conclusion, ENet could be efficiently applied for prostate delineation even in small image training datasets with potential benefit for patient management personalization.

scholarly journals Brain volumetric MRI study in healthy adolescent and young person’s using automated method

2021 ◽  
Vol 8 (9) ◽  
pp. 531-537
Author(s):  
Seda Avnioğlu ◽  
Özkan Özen
Keyword(s):  
Magnetic Resonance Imaging ◽  
White Matter ◽  
Magnetic Resonance ◽  
Morphological Changes ◽  
Young Subject ◽  
Resonance Imaging ◽  
Brain Volumes ◽  
Healthy Adolescent ◽  
Automated Method ◽  
Age Related

Objective: Adolescence is a critical period for the maturation of neurobiological processes that underlie higher cognitive functions and social and emotional behaviour. However, there are limited studies that investigated brain volumes in healthy adolescents and young persons.  The aim of this study was to compare the Grey Matter (GM), White Matter (WM) and some specific brain subcortical volumes such as hippocampus and amygdala between healthy adolescents and young groups by using VolBrain. Material and Methods: Magnetic resonance imaging brain scans were retrospectively obtained from 20 healthy adolescent and young subjects.  The mean ages of the adolescent and young persons were 13±1 and 24±2, respectively. Brain parenchyma (BP), GM, WM and asymmetry features were calculated using VolBrain, and the GM and WM volumes of each subjects were compared with those of the both groups. The current study to examine whether regional gray matter (GM), white matter (WM), cerebrospinal fluid (CSF), some brain subcortical structures volumes differed between healthy adolescent and young groups. Also, of the whole brain, hemispheres, and hippocampus, amigdala of adolescent and young subject volumes were measured with an automated method. Results: We have observed that the young group was found to have a 4 % less in volume of GM, when compared with adolescent groups. Conclusion: Our data indicate that quantitative structural Magnetic Resonance Imaging (MRI) data of the adolescent brain is important in understanding the age-related human morphological changes.

scholarly journals Deep dense multi-path neural network for prostate segmentation in magnetic resonance imaging

2018 ◽  
Vol 13 (11) ◽  
pp. 1687-1696 ◽  
Author(s):  
Minh Nguyen Nhat To ◽  
Dang Quoc Vu ◽  
Baris Turkbey ◽  
Peter L. Choyke ◽  
Jin Tae Kwak
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Resonance Imaging ◽  
Prostate Segmentation
Sign in / Sign up

Export Citation Format

Share Document