66 Hits in 7.4 sec

Improved inter-scanner MS lesion segmentation by adversarial training on longitudinal data [article]

Mattias Billast, Maria Ines Meyer, Diana M. Sima, David Robben
2020 arXiv   pre-print
Finally, the base model and the discriminator are trained adversarially on multi-scanner longitudinal data to improve the inter-scanner consistency of the base model.  ...  We propose a model that improves the consistency of MS lesion segmentations in inter-scanner studies.  ...  Both the adversarial network and the discriminator were trained on longitudinal inter-scanner data.  ... 
arXiv:2002.00952v1 fatcat:cpgavach55funmeew5yejj2jam

Multiple Sclerosis Lesion Analysis in Brain Magnetic Resonance Images: Techniques and Clinical Applications [article]

Yang Ma, Chaoyi Zhang, Mariano Cabezas, Yang Song, Zihao Tang, Dongnan Liu, Weidong Cai, Michael Barnett, Chenyu Wang
2022 arXiv   pre-print
Traditionally, MS lesions have been manually annotated on 2D MRI slices, a process that is inefficient and prone to inter-/intra-observer errors.  ...  However, their effectiveness is limited by the heterogeneity of both MRI data acquisition techniques and the appearance of MS lesions.  ...  The ISBI 2015 MS lesion challenge focused on longitudinal lesion segmentation task [62] . All scans were acquired using the same protocol on a 3.0 Tesla MRI scanner.  ... 
arXiv:2104.10029v3 fatcat:elds3foafrdc5ireld5wahp5ra

Deep Learning in Large and Multi-Site Structural Brain MR Imaging Datasets

Mariana Bento, Irene Fantini, Justin Park, Leticia Rittner, Richard Frayne
2022 Frontiers in Neuroinformatics  
Then we reviewed methods for correcting batch effects by exploring the two main classes of approaches: Data Harmonization that uses data standardization, quality control protocols or other similar algorithms  ...  The presence of variation in the training dataset is important as it more closely reflects the true underlying data distribution and, thus, may enhance the overall generalizability of the tool.  ...  MS Minimize false-positive lesion classification on brain segmentation Dewey et al. (2019) Explicit Segmentation HC Propose a data harmonization-segmentation method based on image contrast (DeepHarmony  ... 
doi:10.3389/fninf.2021.805669 pmid:35126080 pmcid:PMC8811356 fatcat:57znd2kfhfgkflil62jnnpkqm4

Emerging deep learning techniques using magnetic resonance imaging data applied in multiple sclerosis and clinical isolated syndrome patients (Review)

Eleftherios Kontopodis, Efrosini Papadaki, Eleftherios Trivzakis, Thomas Maris, Panagiotis Simos, Georgios Papadakis, Aristidis Tsatsakis, Demetrios Spandidos, Apostolos Karantanas, Kostas Marias
2021 Experimental and Therapeutic Medicine  
The current study presents a thorough review covering DL techniques that have been applied in MS and CIS during recent years, shedding light on their current advances and limitations.  ...  Recent advances in deep learning (DL) techniques have led to novel computational paradigms in MS and CIS imaging designed for automatic segmentation and detection of areas of interest and automatic classification  ...  Evaluation of the proposed method was on two datasets, one private (37 MS patients) as well as the International Symposium on Biomedical Imaging (ISBI) 2015 longitudinal MS lesion segmentation challenge  ... 
doi:10.3892/etm.2021.10583 pmid:34504594 pmcid:PMC8393268 fatcat:yolthcmsgfhdbbwwpcn5nte2ly

Improving segmentation reliability of multi-scanner brain images using a generative adversarial network

Kai Niu, Xueyan Li, Li Zhang, Zhensong Yan, Wei Yu, Peipeng Liang, Yan Wang, Ching-Po Lin, Huimao Zhang, Chunjie Guo, Kuncheng Li, Tianyi Qian
2021 Quantitative Imaging in Medicine and Surgery  
In addition, the segmentation model improved intra-scanner variability (0.9-1.67%) compared with that of FS (2.47-4.32%).  ...  scanners was reduced by 1.57%, 2.01%, and 0.56%, respectively.  ...  Improving segmentation reliability of multi-scanner brain images using a generative adversarial network.  ... 
doi:10.21037/qims-21-653 pmid:35284270 pmcid:PMC8899955 fatcat:rio22psyj5ghlare6a6nlpujue

A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI

Maria Ines Meyer, Ezequiel de la Rosa, Nuno Pedrosa de Barros, Roberto Paolella, Koen Van Leemput, Diana M. Sima
2021 Frontiers in Neuroscience  
We found that the addition of the GMM-DA improves the generalization capability of the DL model to other scanners not present in the training data, even when the train set is already multi-scanner.  ...  Besides, the consistency between same-patient segmentation predictions is improved, both for same-scanner and different-scanner repetitions.  ...  The MS dataset is a subset of data processed with icobrain ms in clinical practice, for which subjects had agreed to allow icometrix to use an anonymized version of the already analysed MR images for research  ... 
doi:10.3389/fnins.2021.708196 pmid:34531715 pmcid:PMC8439197 fatcat:phwzu5vsercwhaalankai7veuq

Transductive Transfer Learning for Domain Adaptation in Brain Magnetic Resonance Image Segmentation

Kaisar Kushibar, Mostafa Salem, Sergi Valverde, Àlex Rovira, Joaquim Salvi, Arnau Oliver, Xavier Lladó
2021 Frontiers in Neuroscience  
The experiments showed that the segmentation performance of a pre-trained model could be significantly improved by up to 10%.  ...  However, these methods suffer from generalisability problem due to inter-centre and inter-scanner variabilities of the MRI images.  ...  We have noticed that for this segmentation problem, inter-operator variability in the gold-standard lesion masks has an enormous effect on the lesion detection.  ... 
doi:10.3389/fnins.2021.608808 pmid:33994917 pmcid:PMC8116893 fatcat:le26kk4qbfh3dhwnofsmxybdpa

Multiple Sclerosis Lesion Segmentation – A Survey of Supervised CNN-Based Methods [article]

Huahong Zhang, Ipek Oguz
2020 arXiv   pre-print
In this survey, we investigate the supervised CNN-based methods for MS lesion segmentation. We decouple these reviewed works into their algorithmic components and discuss each separately.  ...  Lesion segmentation is a core task for quantitative analysis of MRI scans of Multiple Sclerosis patients.  ...  This work was supported, in part, by the NIH grant R01-NS094456 and National Multiple Sclerosis Society award PP-1905-34001.  ... 
arXiv:2012.08317v2 fatcat:2usedwsl2bbe5gbp35e5blnf3q

POPCORN: Progressive Pseudo-labeling with Consistency Regularization and Neighboring [article]

Reda Abdellah Kamraoui, Vinh-Thong Ta, Nicolas Papadakis, Fanny Compaire, José V Manjon, Pierrick Coupé
2021 arXiv   pre-print
POPCORN estimates a proximity graph to select data from easiest ones to more difficult ones, in order to ensure accurate pseudo-labeling and to limit confirmation bias.  ...  Applied to multiple sclerosis lesion segmentation, our method demonstrates competitive results compared to other state-of-the-art SSL strategies.  ...  This study has been also supported by the DPI2017-87743-R grant from the Spanish Ministerio de Economia, Industria Competitividad.  ... 
arXiv:2109.06361v1 fatcat:pjscu3rpynf4dnqp6mspmwqwiq

MoDL-QSM: Model-based Deep Learning for Quantitative Susceptibility Mapping [article]

Ruimin Feng, Jiayi Zhao, He Wang, Baofeng Yang, Jie Feng, Yuting Shi, Ming Zhang, Chunlei Liu, Yuyao Zhang, Jie Zhuang, Hongjiang Wei
2021 arXiv   pre-print
Recently, deep learning has shown promising results to improve accuracy by reducing the streaking artifacts.  ...  network training.  ...  Acknowledgments This study is supported by the National Natural Science Foundation of China (61901256, 91949120, 62071299).  ... 
arXiv:2101.08413v2 fatcat:2pq6zm4l2bfuhisnganstjylii

Automated Segmentation of Midbrain Structures in High-Resolution Susceptibility Maps Based on Convolutional Neural Network and Transfer Learning

Weiwei Zhao, Yida Wang, Fangfang Zhou, Gaiying Li, Zhichao Wang, Haodong Zhong, Yang Song, Kelly M. Gillen, Yi Wang, Guang Yang, Jianqi Li
2022 Frontiers in Neuroscience  
Consistencies of volume and magnetic susceptibility values by different extraction strategies were assessed by Pearson correlation coefficients and Bland-Altman analyses.ResultsThe automated CNN segmentation  ...  This study aims to segment midbrain structures in high-resolution susceptibility maps using a method based on a convolutional neural network (CNN).MethodsThe susceptibility maps of 75 subjects were acquired  ...  Longitudinal change in magnetic susceptibility of new enhanced multiple sclerosis (MS) lesions measured on serial quantitative susceptibility mapping (QSM). J. Magn. Reson.  ... 
doi:10.3389/fnins.2022.801618 pmid:35221900 pmcid:PMC8866960 fatcat:bi3m63jldfd5tjv6fepcsa2lqu

Cross-modality (CT-MRI) prior augmented deep learning for robust lung tumor segmentation from small MR datasets [article]

Jue Jiang, Yu-Chi Hu, Neelam Tyagi, Pengpeng Zhang, Andreas Rimner, Joseph O. Deasy, Harini Veeraraghavan
2019 arXiv   pre-print
Therefore, a cross-modality (MR-CT) deep learning segmentation approach that augments training data using pseudo MR images produced by transforming expert-segmented CT images was developed.  ...  A novel deep learning MR segmentation was developed that overcomes the limitation of learning robust models from small datasets by leveraging learned cross-modality priors to augment training.  ...  Mageras for his insightful suggestions for improving the clarity of the manuscript.  ... 
arXiv:1901.11369v2 fatcat:kfo4wsx6nvaxdhudwc3gwnnjl4

PSACNN: Pulse sequence adaptive fast whole brain segmentation

Amod Jog, Andrew Hoopes, Douglas N. Greve, Koen Van Leemput, Bruce Fischl
2019 NeuroImage  
CNNs trained on such datasets are unable to generalize on test data with different acquisition protocols.  ...  Our method trains a single CNN that can segment input MRI images with acquisition parameters as disparate as T1-weighted and T2-weighted contrasts with only T1-weighted training data.  ...  In addition, BF has a financial interest in CorticoMetrics, a company whose medical pursuits focus on brain imaging and measurement technologies.  ... 
doi:10.1016/j.neuroimage.2019.05.033 pmid:31129303 pmcid:PMC6688920 fatcat:ra35vfagj5gsdfbvq7sga3553q

Machine Learning in Prostate MRI for Prostate Cancer: Current Status and Future Opportunities

Huanye Li, Chau Hung Lee, David Chia, Zhiping Lin, Weimin Huang, Cher Heng Tan
2022 Diagnostics  
Machine learning provides vast opportunities for automated organ and lesion depiction that could increase the reproducibility of PI-RADS categorisation, and improve co-registration across imaging modalities  ...  The Prostate Imaging Reporting and Data System (PI-RADS) is an established imaging-based scoring system that scores the probability of clinically significant prostate cancer on MRI to guide management.  ...  Recent studies suggest that applying ML in prostate MRI could improve diagnostic accuracy and reduce inter-reader variability by highlighting suspicious areas on MRI, allowing a more focused interpretation  ... 
doi:10.3390/diagnostics12020289 pmid:35204380 pmcid:PMC8870978 fatcat:rpaecwqodveqplmvuyvu5ne52m

Data Harmonisation for Information Fusion in Digital Healthcare: A State-of-the-Art Systematic Review, Meta-Analysis and Future Research Directions

Yang Nan, Javier Del Ser, Simon Walsh, Carola Schönlieb, Michael Roberts, Ian Selby, Kit Howard, John Owen, Jon Neville, Julien Guiot, Benoit Ernst, Ana Pastor (+14 others)
2022 Information Fusion  
by different scanners and protocols to improve stability and robustness.  ...  based on different theories.  ...  Acknowledgement This study was supported in part by the European Research Council Innovative Medicines Initiative (DRAGON # , H2020-JTI-IMI2 101005122), the AI for Health Imaging Award (CHAIMELEON ## ,  ... 
doi:10.1016/j.inffus.2022.01.001 pmid:35664012 pmcid:PMC8878813 fatcat:57zns35robfzxg5qojnyvntcyy
« Previous Showing results 1 — 15 out of 66 results