21 Hits in 7.2 sec

Automatic Prostate Zonal Segmentation Using Fully Convolutional Network with Feature Pyramid Attention [article]

Yongkai Liu, Guang Yang, Sohrab Afshari Mirak, Melina Hosseiny, Afshin Azadikhah, Xinran Zhong, Robert E. Reiter, Yeejin Lee, Steven Raman, Kyunghyun Sung
2019 arXiv   pre-print
With IRB approval and HIPAA compliance, we designed a novel convolutional neural network (CNN) for automatic segmentation of the prostatic transition zone (TZ) and peripheral zone (PZ) on T2-weighted (  ...  Our main objective is to develop a novel deep learning-based algorithm for automatic segmentation of prostate zone and to evaluate the proposed algorithm on an additional independent testing data in comparison  ...  DISCUSSION We proposed a novel fully convolutional network-based model with feature pyramid attention for the automatic segmentation of the two prostate zones.  ... 
arXiv:1911.00127v1 fatcat:2a37t4iy35ai5oeeexxdaqgczy

Exploring Uncertainty Measures in Bayesian Deep Attentive Neural Networks for Prostate Zonal Segmentation

Yongkai Liu, Guang Yang, Melina Hosseiny, Afshin Azadikhah, Sohrab Afshari Mirak, Qi Miao, Steven S. Raman, Kyunghyun Sung
2020 IEEE Access  
We designed a spatial attentive Bayesian deep learning network for the automatic segmentation of the peripheral zone (PZ) and transition zone (TZ) of the prostate with uncertainty estimation.  ...  Automatic segmentation of prostatic zones on multiparametric MRI (mpMRI) can improve the diagnostic workflow of prostate cancer.  ...  Both spatial attention and multiple-scale feature pyramid attention modules had their merits for the prostate zonal segmentation.  ... 
doi:10.1109/access.2020.3017168 pmid:33564563 pmcid:PMC7869831 fatcat:sb2okblhgzaudctgt72xyrvdle

Development of Conditional Random Field Insert for UNet-based Zonal Prostate Segmentation on T2-Weighted MRI [article]

Peng Cao and Susan M. Noworolski and Olga Starobinets and Natalie Korn and Sage P. Kramer and Antonio C. Westphalen and Andrew P. Leynes and Valentina Pedoia and Peder Larson
2020 arXiv   pre-print
Conclusion: UNet based deep neural networks demonstrated in this study can perform zonal prostate segmentation, achieving high Dice coefficients compared with those in the literature.  ...  Purpose: A conventional 2D UNet convolutional neural network (CNN) architecture may result in ill-defined boundaries in segmentation output.  ...  SegNet+CRFIs, post end-CRFI 0.757 ± 0.135 0.842 ± 0.091 0.890 ± 0.022 In summary, three fully convolutional neural networks based on SegNet and CRF for zonal prostate segmentation were presented and  ... 
arXiv:2002.06330v1 fatcat:7jhsy4ec2ngeddlahfexfkizy4

Recent Automatic Segmentation Algorithms of MRI Prostate Regions: A Review

Zia Khan, Norashikin Yahya, Khaled Alsaih, Mohammed Isam Al-Hiyali, Fabrice Meriaudeau
2021 IEEE Access  
718 CNN with a novel feature pyramid attention mechanism. 719 The proposed CNN, in particular, was made up of three 720 sub-networks: an enhanced deep residual network (based 721 on the  ...  The proposed method comprises a 1166 fully convolutional generative network of densely connected 1167 blocks and a discriminative network with multi-scale feature 1168 extraction.  ... 
doi:10.1109/access.2021.3090825 fatcat:l2xe2tdwk5b6ldn7axvzbp5a5a

Automatic Segmentation of Pelvic Cancers Using Deep Learning: State-of-the-Art Approaches and Challenges

Reza Kalantar, Gigin Lin, Jessica M. Winfield, Christina Messiou, Susan Lalondrelle, Matthew D. Blackledge, Dow-Mu Koh
2021 Diagnostics  
This review provides a comprehensive, non-systematic and clinically-oriented overview of 74 DL-based segmentation studies, published between January 2016 and December 2020, for bladder, prostate, cervical  ...  The recent rise of deep learning (DL) and its promising capabilities in capturing non-explicit detail from large datasets have attracted substantial research attention in the field of medical image processing  ...  Illustration of (a) convolutional neural networks (CNN) with fully-connected final layers for classification tasks, (b) fully-convolutional network (FCN) for image-to-image or image-to-mask translations  ... 
doi:10.3390/diagnostics11111964 pmid:34829310 pmcid:PMC8625809 fatcat:alr36jtq6fgeddnluclp5neb2i

Autosegmentation of Prostate Zones and Cancer Regions from Biparametric Magnetic Resonance Images by Using Deep-Learning-Based Neural Networks

Chih-Ching Lai, Hsin-Kai Wang Fu-Nien Wang, Yu-Ching Peng, Tzu-Ping Lin, Hsu-Hsia Peng, Shu-Huei Shen
2021 Sensors  
Here we present a method for autosegmenting the prostate zone and cancer region by using SegNet, a deep convolution neural network (DCNN) model.  ...  The accuracy in diagnosing prostate cancer (PCa) has increased with the development of multiparametric magnetic resonance imaging (mpMRI).  ...  [27] used the PROSTATEx dataset to perform segmentation and training by using a fully convolutional network with feature pyramid attention. They achieved a DSC of 86% in the TZ and 74% in the PZ.  ... 
doi:10.3390/s21082709 pmid:33921451 pmcid:PMC8070192 fatcat:cpv3l6gw2zbehlo7noikojtwmi

Training Convolutional Networks for Prostate Segmentation with Limited Data

Sara L. Saunders, Ethan Leng, Benjamin Spilseth, Neil Wasserman, Gregory J. Metzger, Patrick J. Bolan
2021 IEEE Access  
Previously, convolutional neural networks such as the U-Net have been used to produce fully automatic multi-zonal prostate segmentation on magnetic resonance images (MRIs) with performance comparable to  ...  Multi-zonal segmentation is a critical component of computer-aided diagnostic systems for detecting and staging prostate cancer.  ...  et al. trained a Fully Convolutional Network with Feature Pyramid Attention on 250 MRIs, then tested on both internal and external datasets, achieving PZ DSC of 0.74 and TZ DSC of 0.86 on the internal  ... 
doi:10.1109/access.2021.3100585 pmid:34527506 pmcid:PMC8438764 fatcat:zyunndtj6bfthk4qudwjf3dxby

Esophagus Segmentation in CT Images via Spatial Attention Network and STAPLE Algorithm

Minh-Trieu Tran, Soo-Hyung Kim, Hyung-Jeong Yang, Guee-Sang Lee, In-Jae Oh, Sae-Ryung Kang
2021 Sensors  
We employ the spatial attention mechanism with the atrous spatial pyramid pooling module to locate the esophagus effectively, which enhances the segmentation performance.  ...  To address these challenges, we propose a fully automated framework for the esophagus segmentation from CT images.  ...  This framework achieves accurate prostate zonal segmentation results when trained on multi-institutional datasets.  ... 
doi:10.3390/s21134556 fatcat:vjtzoctckrfhthhydzqnh6bqfa

MA-Net: A Multi-Scale Attention Network for Liver and Tumor Segmentation

Tongle Fan, Guanglei Wang, Yan Li, Hongrui Wang
2020 IEEE Access  
[15] embedded the SEblock in the U-Net network, which obtained the channel dependencies between feature maps for prostate zonal segmentation.  ...  [20] introduced cascaded context pyramid with dilation convolution of different dilation rate into the proposed network to capture multi-scale semantic information.  ... 
doi:10.1109/access.2020.3025372 fatcat:555cquzobjaf3jy76eek625zh4

Intelligent Ultra-Light Deep Learning Model for Multi-Class Brain Tumor Detection

Shahzad Ahmad Qureshi, Shan E. Ahmed Raza, Lal Hussain, Mohamed K. Nour, Aziz ul Rehman, Fahd N. Al-Wesabi, Anwer Mustafa Hilal
2022 Applied Sciences  
It forms a Hybrid Feature Space (HFS), which is used for tumor detection using Support Vector Machine (SVM), culminating in high prediction accuracy and optimum false negatives with limited network size  ...  In this context, we propose an automated Ultra-Light Brain Tumor Detection (UL-BTD) system based on a novel Ultra-Light Deep Learning Architecture (UL-DLA) for deep features, integrated with highly distinctive  ...  [20] presented a CNN constituted of three sub-networks (viz. improved ResNet50, feature pyramid attention, and decoder networks) for automated zonal segmentation of the prostate.  ... 
doi:10.3390/app12083715 fatcat:pzexp6svxzhopghnwvn22xpfvm

Mapping the Rest of the Human Connectome: Atlasing the Spinal Cord and Peripheral Nervous System

Andrei Irimia, John Darrell Van Horn
2020 NeuroImage  
Despite increasing interest in an atlas of the spinal cord (SC) and PNS which is simultaneously stereotactic, interactive, electronically dissectible, scalable, population-based and deformable, little attention  ...  Methods are now available for the fully automatic 3D segmentation of the thoracolumbar spinal cord and of the vertebral canal using K -means clustering ( Sabaghian et al., 2020 ) , variational segmentation  ...  Manual segmentation of the SC and of the nerves can be used in combination with automatic and semiautomatic methods of segmentation to achieve cross-validation of atlas models.  ... 
doi:10.1016/j.neuroimage.2020.117478 pmid:33160086 pmcid:PMC8485987 fatcat:nje75t2s4bdrpkqpwtouxu73d4

A Survey of Methods for 3D Histology Reconstruction

Jonas Pichat, Juan Eugenio Iglesias, Tarek Yousry, Sébastien Ourselin, Marc Modat
2018 Medical Image Analysis  
In addition, combining non-invasive imaging with histology unveiled invaluable opportunities to relate macroscopic information with the underlying microscopic properties of tissues through the establishment  ...  This paper reviews almost three decades of methods for 3D reconstruction from serial sections, used in the study of many different types of tissue.  ...  Smriti Patodia, from UCL Institute of Neurology (Department of Neuropathology), for her comments on Section 2 and the images used in Figures  ... 
doi:10.1016/ pmid:29502034 fatcat:ta5hlvqjpzenxhltfwh6p4mhqq

Analysis of room transfer function and reverberant signal statistics

Eleftheria Georganti, John Mourjopoulos, Finn Jacobsen
2008 Journal of the Acoustical Society of America  
Effects of hardware on optimal filter segmentations for the segmented convolution.  ...  The segmented convolution algorithm allows an efficient computation of the convolution in real-time, by segmentation of the impulse response into several parts.  ...  PM Acoustics'08 Paris features of the wave that can be used in automatic classification.  ... 
doi:10.1121/1.2935346 fatcat:lxgnqr6tozajhge3ydet3xomam

A virtual auditory environment for investigating the auditory signal processing of realistic sounds

Sylvain Favrot, Jörg M. Buchholz
2008 Journal of the Acoustical Society of America  
Effects of hardware on optimal filter segmentations for the segmented convolution.  ...  The segmented convolution algorithm allows an efficient computation of the convolution in real-time, by segmentation of the impulse response into several parts.  ...  PM Acoustics'08 Paris features of the wave that can be used in automatic classification.  ... 
doi:10.1121/1.2936003 fatcat:ontu6yamdvgbnooet5fe36fm74

Temporal suppression and augmentation of click‐evoked otoacoustic emissions

Sarah Verhulst, James M. Harte, Torsten Dau
2008 Journal of the Acoustical Society of America  
To avoid the feared explosion of computation time with higher order diffraction, a beam reunification may now be achieved by Quantized Pyramidal Beam Tracing.  ...  with diffuse reflection boundaries are modeled with an energy-intensity boundary element method using uncorrelated broadband directional sources.  ...  Effects of hardware on optimal filter segmentations for the segmented convolution.  ... 
doi:10.1121/1.2935694 fatcat:z6yidzqqendznbmrczb3woaiv4
« Previous Showing results 1 — 15 out of 21 results