1,775 Hits in 5.1 sec

Comparison of Metrics for the Evaluation of Medical Segmentations using Prostate MRI Dataset

Ying-Hwey Nai, Bernice W. Teo, Nadya L. Tan, Sophie O'Doherty, Mary C. Stephenson, Yee Liang Thian, Edmund Chiong, Anthonin Reilhac
2021 Computers in Biology and Medicine  
metrics to identify those which better capture the requirements for clinical segmentation evaluation.  ...  Nine previously proposed segmentation evaluation metrics, targeting medical relevance, accounting for holes, and added regions or differentiating over- and under-segmentation, were compared with 24 traditional  ...  Bertrand Wei Leng Ang from the National University Hospital (NUH), Singapore, for teaching prostate segmentation.  ... 
doi:10.1016/j.compbiomed.2021.104497 pmid:34022486 fatcat:hmqcmzh7hvg3pm4tlz7xold2ee

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

Maysam Shahedi, Derek W. Cool, Glenn S. Bauman, Matthew Bastian-Jordan, Aaron Fenster, Aaron D. Ward
2017 Journal of digital imaging  
In this study, we developed a fully automatic segmentation algorithm for T2-weighted endorectal prostate MRI and evaluated its accuracy within different regions of interest using a set of complementary  ...  Our dataset contained 42 T2-weighted endorectal MRI from prostate cancer patients.  ...  Compliance with Ethical Standards The study was approved by the research ethics board of our institution, and written informed consent was obtained from all patients prior to enrolment.  ... 
doi:10.1007/s10278-017-9964-7 pmid:28342043 fatcat:v5mnagutjvhvpnqyho2jpbkevu

Comparison of automatic prostate zones segmentation models in MRI images using U-net-like architectures [article]

Pablo Cesar Quihui-Rubio and Gilberto Ochoa-Ruiz and Miguel Gonzalez-Mendoza and Gerardo Rodriguez-Hernandez and Christian Mata
2022 arXiv   pre-print
The analysis was performed using three metrics commonly used for image segmentation: Dice score, Jaccard index, and mean squared error.  ...  learning models were trained and analyzed with a dataset of MRI images obtained from the Centre Hospitalaire de Dijon and Universitat Politecnica de Catalunya.  ...  Acknowledgments The authors wish to thank the AI Hub and the CIIOT at ITESM for their support for carrying the experiments reported in this paper in their NVIDIA's DGX computer.  ... 
arXiv:2207.09483v1 fatcat:qeo7lm6hkzfpjp7gdefma45dga

Bridging 2D and 3D Segmentation Networks for Computation Efficient Volumetric Medical Image Segmentation: An Empirical Study of 2.5D Solutions [article]

Yichi Zhang, Qingcheng Liao, Le Ding, Jicong Zhang
2022 arXiv   pre-print
However, unlike segmentation of natural images, most medical images such as MRI and CT are volumetric data. In order to make full use of volumetric information, 3D CNNs are widely used.  ...  We hope the results and conclusions of our study will prove useful for the community on exploring and developing efficient volumetric medical image segmentation methods.  ...  The evaluation using these two metrics can achieve a more comprehensive comparison of segmentation results.  ... 
arXiv:2010.06163v2 fatcat:u3jfvhae7vckzfgcc7tyjvokki

Harnessing clinical annotations to improve deep learning performance in prostate segmentation

Karthik V. Sarma, Alex G. Raman, Nikhil J. Dhinagar, Alan M. Priester, Stephanie Harmon, Thomas Sanford, Sherif Mehralivand, Baris Turkbey, Leonard S. Marks, Steven S. Raman, William Speier, Corey W. Arnold (+1 others)
2021 PLoS ONE  
We evaluated the direct use of a large dataset with only clinically generated annotations in development of high-performance segmentation models for small research-quality challenge datasets.  ...  We also trained versions of the template model using ablated proportions of our dataset, and evaluated the relative benefit of those templates for the final models.  ...  for prostate MRI segmentation.  ... 
doi:10.1371/journal.pone.0253829 pmid:34170972 pmcid:PMC8232529 fatcat:d3vh7g7cjfb57bb3yln3mxt7mi

Deep learning in magnetic resonance prostate segmentation: A review and a new perspective [article]

David Gillespie, Connah Kendrick, Ian Boon, Cheng Boon, Tim Rattay, Moi Hoon Yap
2020 arXiv   pre-print
We evaluate the performance on four publicly available datasets using Dice Similarity Coefficient (DSC) as performance metric.  ...  The best result is achieved by composite evaluation (DSC of 0.9427 on Decathlon test set) and the poorest result is achieved by cross-dataset evaluation (DSC of 0.5892, Prostate X training set, Promise  ...  Acknowledgments This project is funded by the Margaret Baecker Endowment Fund and the Clatterbridge Cancer Centre NHS Trust.  ... 
arXiv:2011.07795v1 fatcat:boimudu54jchxber2oarrw52rq

Prostate Cancer Delineation in MRI Images Based on Deep Learning: Quantitative Comparison and Promising Perspective [chapter]

Eddardaa Ben Loussaief, Mohamed Abdel-Nasser, Domènec Puig
2021 Frontiers in Artificial Intelligence and Applications  
This perspective includes the use of the best segmentation model to detect the prostate tumors in MRI images.  ...  One of the key stages of prostate cancer CAD systems is the automatic delineation of the prostate. Deep learning has recently demonstrated promising segmentation results with medical images.  ...  Acknowledgement The Spanish Government partly supported this research through Project PID2019-105789RB-I00.  ... 
doi:10.3233/faia210148 fatcat:4pbii7acb5gbdaqupeuz5pny6m

USE-Net: incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets [article]

Leonardo Rundo, Changhee Han, Yudai Nagano, Jin Zhang, Ryuichiro Hataya, Carmelo Militello, Andrea Tangherloni, Marco S. Nobile, Claudio Ferretti, Daniela Besozzi, Maria Carla Gilardi, Salvatore Vitabile (+3 others)
2019 arXiv   pre-print
The following mixed scheme is used for training/testing: (i) training on either each individual dataset or multiple prostate MRI datasets and (ii) testing on all three datasets with all possible training  ...  This study evaluates the generalization ability of CNN-based architectures on three T2-weighted MRI datasets, each one consisting of a different number of patients and heterogeneous image characteristics  ...  We thank the Cannizzaro Hospital, Catania, Italy, for providing one of the imaging datasets analyzed in this study. References  ... 
arXiv:1904.08254v2 fatcat:voxb75goxbbtzchnrkk73k3s4y

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  
, and evaluates how the performance varies with the amount of internal data used for training.  ...  For institutions that have limited amounts of labeled MRI exams, it is not clear how much data is needed to train a segmentation model, and which training strategy should be used to maximize the value  ...  We use this level of performance as a benchmark for evaluating our results herein. A variety of convolutional architectures have been used for prostate segmentation.  ... 
doi:10.1109/access.2021.3100585 pmid:34527506 pmcid:PMC8438764 fatcat:zyunndtj6bfthk4qudwjf3dxby

Automatic Segmentation of Prostate MRI using Convolutional Neural Networks: Investigating the Impact of Network Architecture on the Accuracy of Volume Measurement and MRI-Ultrasound Registration

Nooshin Ghavami, Yipeng Hu, Eli Gibson, Ester Bonmati, Mark Emberton, Caroline M. Moore, Dean C. Barratt
2019 Medical Image Analysis  
For applications such as segmentation of the prostate in magnetic resonance images (MRI), the results of the PROMISE12 online algorithm evaluation platform have demonstrated differences between the best-performing  ...  In this work, we quantified the accuracy of six different CNNs in segmenting the prostate in 3D patient T2-weighted MRI scans and compared the accuracy of organ volume estimation and MRI-ultrasound (US  ...  Acknowledgements We would like to acknowledge the UCL EPSRC Centre for Doctoral Training in Medical Imaging (Grant No. EP/L016478/1 ) for supporting Nooshin Ghavami in this work.  ... 
doi:10.1016/ pmid:31526965 pmcid:PMC7985677 fatcat:g2qao37o3zehrakoqepobgyy5a

Challenge of prostate MRI segmentation on T2-weighted images: inter-observer variability and impact of prostate morphology

Sarah Montagne, Dimitri Hamzaoui, Alexandre Allera, Malek Ezziane, Anna Luzurier, Raphaelle Quint, Mehdi Kalai, Nicholas Ayache, Hervé Delingette, Raphaële Renard-Penna
2021 Insights into Imaging  
Several metrics including Dice Score (DSC) and Hausdorff Distance were used to evaluate differences, with both a pairwise and a consensus (STAPLE reference) comparison.  ...  Methods Seven radiologists of varying levels of experience segmented the whole prostate gland (WG) and the transition zone (TZ) on 40 axial T2W prostate MRI images (3D T2W images for all patients, and  ...  Acknowledgements We thank Julien Castelneau, software Engineer Inria, for his help in the development of MedInria Software (MedInria-Medical image visualization and processing software by Inria https:/  ... 
doi:10.1186/s13244-021-01010-9 pmid:34089410 fatcat:px6lvwv2treoxfba2p3yiusemm

An Enhanced Deep Learning Technique for Prostate Cancer Identification Based on MRI Scans [article]

Hussein Hashem, Yasmin Alsakar, Ahmed Elgarayhi, Mohammed Elmogy, Mohammed Sallah
2022 arXiv   pre-print
First, the MRI images have been preprocessed to make the medical image more suitable for the detection step.  ...  Many techniques based on Magnetic Resonance Imaging (MRI) have been used for prostate cancer identification and classification in the last few decades.  ...  Performance evaluation metrics Some evaluation metrics have been used for testing the classifier's performance. Mathematical formulations have been presented to compute the evaluation metrics.  ... 
arXiv:2208.00583v1 fatcat:s665xah4dbgb5iv7elk2njwf6e

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  
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  ...  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  ...  Conflicts of Interest: The authors declare no conflict of interest. The funders had no role in the design of the review, writing of the manuscript or the decision to publish.  ... 
doi:10.3390/diagnostics11111964 pmid:34829310 pmcid:PMC8625809 fatcat:alr36jtq6fgeddnluclp5neb2i

Multiattribute probabilistic prostate elastic registration (MAPPER): Application to fusion of ultrasound and magnetic resonance imaging

Rachel Sparks, B. Nicolas Bloch, Ernest Feleppa, Dean Barratt, Daniel Moses, Lee Ponsky, Anant Madabhushi
2015 Medical Physics (Lancaster)  
Methods: MAPPER involves (1) segmenting the prostate on MRI, (2) calculating a multiattribute probabilistic map of prostate location on TRUS, and (3) maximizing overlap between the prostate segmentation  ...  MAPPER has a root-mean-square error (RMSE) for expert selected fiducials of 3.36 ± 1.10 mm for Dataset 1 and 3.14 ± 0.75 mm for Dataset 2.  ...  RMSE evaluated for different prostate segmentation schemes for (a) D 1 and (b) D 2 using f T .  ... 
doi:10.1118/1.4905104 pmid:25735270 pmcid:PMC4327921 fatcat:a7a64jvtfjcunngb73yrzib2xi

Evaluation of a commercial synthetic computed tomography generation solution for magnetic resonance imaging‐only radiotherapy

A. Gonzalez‐Moya, S. Dufreneix, N. Ouyessad, C. Guillerminet, D. Autret
2021 Journal of Applied Clinical Medical Physics  
A retrospective study was conducted on 47 patients treated with external beam RT for brain or prostate cancer who underwent both MRI and CT for treatment planning. sCT images were generated from MRI using  ...  Large differences for the D98% of the prostate group could be correlated to low Dice index of the PTV.  ...  Comparison between approaches is difficult because of differences in the size of dataset, tumor location, MRI sequences, image registration modalities and performance metrics used to evaluate the method  ... 
doi:10.1002/acm2.13236 pmid:34042268 fatcat:43pnnl4u7fhuxhimc5aahcbxei
« Previous Showing results 1 — 15 out of 1,775 results