Filters








309 Hits in 6.5 sec

Federated Whole Prostate Segmentation in MRI with Personalized Neural Architectures [article]

Holger R. Roth, Dong Yang, Wenqi Li, Andriy Myronenko, Wentao Zhu, Ziyue Xu, Xiaosong Wang, Daguang Xu
2021 arXiv   pre-print
In this work, we combine FL with an AutoML technique based on local neural architecture search by training a "supernet".  ...  Furthermore, we propose an adaptation scheme to allow for personalized model architectures at each FL client's site.  ...  Experiments & Results Our proposed method is evaluated on the task of 3D whole prostate segmentation in T2-weighted MRI.  ... 
arXiv:2107.08111v1 fatcat:cuvyccr7ujadrh6psmdsmkpk6q

An overview of deep learning in medical imaging focusing on MRI

Alexander Selvikvåg Lundervold, Arvid Lundervold
2018 Zeitschrift für Medizinische Physik  
Our aim is threefold: (i) give a brief introduction to deep learning with pointers to core references; (ii) indicate how deep learning has been applied to the entire MRI processing chain, from acquisition  ...  As this has become a very broad and fast expanding field we will not survey the entire landscape of applications, but put particular focus on deep learning in MRI.  ...  patients with a prostate-specific antigen level of <20 ng/mL who underwent MRI and extended systematic prostate biopsy with or without MRI-targeted biopsy [289] Automatic approach based on deep CNN,  ... 
doi:10.1016/j.zemedi.2018.11.002 fatcat:kkimovnwcrhmth7mg6h6cpomjm

Deep Learning in Cancer Diagnosis and Prognosis Prediction: A Minireview on Challenges, Recent Trends, and Future Directions

Ahsan Bin Tufail, Yong-Kui Ma, Mohammed K. A. Kaabar, Francisco Martínez, A. R. Junejo, Inam Ullah, Rahim Khan, Iman Yi Liao
2021 Computational and Mathematical Methods in Medicine  
DL is a generic model requiring minimal data manipulations and achieves better results while working with enormous volumes of data.  ...  Reduction of costs associated with sequencing systems offers a myriad of opportunities for building precise models for cancer diagnosis and prognosis prediction.  ...  Acknowledgments We would like to acknowledge the group effort made in this research.  ... 
doi:10.1155/2021/9025470 pmid:34754327 pmcid:PMC8572604 fatcat:wgpostjgsfeijazpyguobcrx4i

Learning Multi-Modal Volumetric Prostate Registration with Weak Inter-Subject Spatial Correspondence [article]

Oleksii Bashkanov, Anneke Meyer, Daniel Schindele, Martin Schostak, Klaus Tönnies, Christian Hansen, Marko Rak
2021 arXiv   pre-print
Furthermore, we introduce an auxiliary input to the neural network for the prior information about the prostate location in the MR sequence, which mostly is available preoperatively.  ...  With weakly labelled MR-TRUS prostate data, we showed registration quality comparable to the state-of-the-art deep learning-based method.  ...  This work does not involve any studies with human participants or animals performed by any of the authors and is in line with the Declaration of Helsinki.  ... 
arXiv:2102.04938v1 fatcat:ln2t35sferewhc47253f3sz4ne

IOP-FL: Inside-Outside Personalization for Federated Medical Image Segmentation [article]

Meirui Jiang, Hongzheng Yang, Chen Cheng, Qi Dou
2022 arXiv   pre-print
This problem becomes even more significant when deploying the global model to unseen clients outside the FL with new distributions not presented during federated training.  ...  To optimize the prediction accuracy of each individual client for critical medical tasks, we propose a novel unified framework for both Inside and Outside model Personalization in FL (IOP-FL).  ...  IMAGE SEGMENTATION DATASETS OF THE RETINAL FUNDUS AND PROSTATE MRI IMAGES.  ... 
arXiv:2204.08467v1 fatcat:j7k6cox7hnadzayhi7xh44576m

Deep learning-based segmentation of the lung in MR-images acquired by a stack-of-spirals trajectory at ultra-short echo-times

Andreas M. Weng, Julius F. Heidenreich, Corona Metz, Simon Veldhoen, Thorsten A. Bley, Tobias Wech
2021 BMC Medical Imaging  
A convolutional neural network was then trained for semantic lung segmentation using 17,713 2D coronal slices, each paired with a label obtained from manual segmentation.  ...  Background Functional lung MRI techniques are usually associated with time-consuming post-processing, where manual lung segmentation represents the most cumbersome part.  ...  Rather severe diffuse infiltrations covering large parts of the whole lung with strong changes in contrast led to incorrect segmentations by the neural network in scattered slices.  ... 
doi:10.1186/s12880-021-00608-1 pmid:33964892 pmcid:PMC8106126 fatcat:267ys5dcqrdwhijhjtyjiny2ui

Deep Learning Application for Analyzing of Constituents and Their Correlations in the Interpretations of Medical Images

Tudor Florin Ursuleanu, Andreea Roxana Luca, Liliana Gheorghe, Roxana Grigorovici, Stefan Iancu, Maria Hlusneac, Cristina Preda, Alexandru Grigorovici
2021 Diagnostics  
The novelty in our paper consists primarily in the unitary approach, of the constituent elements of DL models, namely, data, tools used by DL architectures or specifically constructed DL architecture combinations  ...  Deep learning (DL) has experienced an exponential development in recent years, with a major impact on interpretations of the medical image.  ...  Of these, three types of HA (hybrid architectures), namely the integrated model, the built-in model and the whole model.  ... 
doi:10.3390/diagnostics11081373 fatcat:6p7usnvnxnewtivzeth745s3ga

A review of deep learning in medical imaging: Image traits, technology trends, case studies with progress highlights, and future promises [article]

S. Kevin Zhou, Hayit Greenspan, Christos Davatzikos, James S. Duncan, Bram van Ginneken, Anant Madabhushi, Jerry L. Prince, Daniel Rueckert, Ronald M. Summers
2020 arXiv   pre-print
We cover the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, etc.  ...  It is known that the success of AI is mostly attributed to the availability of big data with annotations for a single task and the advances in high performance computing.  ...  Attention is combined with GAN in [37] and with U-Net in [38] . Neural architecture search (NAS) and light weight design.  ... 
arXiv:2008.09104v1 fatcat:z2gic7or4vgnnfcf4joimjha7i

A Review of Generative Adversarial Networks in Cancer Imaging: New Applications, New Solutions [article]

Richard Osuala, Kaisar Kushibar, Lidia Garrucho, Akis Linardos, Zuzanna Szafranowska, Stefan Klein, Ben Glocker, Oliver Diaz, Karim Lekadir
2021 arXiv   pre-print
With this work, we strive to bridge the gap between the needs of the clinical cancer imaging community and the current and prospective research on GANs in the artificial intelligence community.  ...  The recent advancements in Generative Adversarial Networks (GANs) in computer vision as well as in medical imaging may provide a basis for enhanced capabilities in cancer detection and analysis.  ...  Kim et al (2019) [229] PrivacyNet PPMI [267] Cranial MRI Representation learn- ing, segmentation Segmenting de-identified representations learned via same-person CLF by Siamese Ds.  ... 
arXiv:2107.09543v1 fatcat:jz76zqklpvh67gmwnsdqzgq5he

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future [article]

David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson
2021 arXiv   pre-print
In this survey, we thoroughly review the different types of graph architectures and their applications in healthcare.  ...  As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interactive nodes connected by edges whose weights can be  ...  recurrent neural architectures (RNNs).  ... 
arXiv:2105.13137v1 fatcat:gm7d2ziagba7bj3g34u4t3k43y

Artificial intelligence: Deep learning in oncological radiomics and challenges of interpretability and data harmonization

Panagiotis Papadimitroulas, Lennart Brocki, Neo Christopher Chung, Wistan Marchadour, Franck Vermet, Laurent Gaubert, Vasilis Eleftheriadis, Dimitris Plachouris, Dimitris Visvikis, George C. Kagadis, Mathieu Hatt
2021 Physica medica (Testo stampato)  
Deep Neural Networks (DNN) have achieved outstanding performance and broad implementation in image processing tasks.  ...  Modern radiation oncology is based on the exploitation of advanced computational methods aiming to personalization and high diagnostic and therapeutic precision.  ...  Convolutional segmentation Xenopus 2016 [65] Network kidney V-Net: Fully MRI prostate F Milletari et al.  ... 
doi:10.1016/j.ejmp.2021.03.009 pmid:33765601 fatcat:ejg4x3n4pjbwrdqw4vxukrk2cm

Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods

Shruti Atul Mali, Abdalla Ibrahim, Henry C. Woodruff, Vincent Andrearczyk, Henning Müller, Sergey Primakov, Zohaib Salahuddin, Avishek Chatterjee, Philippe Lambin
2021 Journal of Personalized Medicine  
In this narrative review, we combine systematic keyword searches with prior domain knowledge to discuss various harmonization solutions to make the radiomic features more reproducible across various scanners  ...  We cover a broader range of methods especially GANs and NST methods in more detail than previous reviews.  ...  For example, some DL algorithms learn complex visual features and perform ROI segmentation using cascading layers with non-linearities by using 'sliding' kernels in convolutional neural networks (CNN),  ... 
doi:10.3390/jpm11090842 pmid:34575619 fatcat:2ngorzmaw5alrpj7deecvvf4au

Federated Learning for Smart Healthcare: A Survey [article]

Dinh C. Nguyen, Quoc-Viet Pham, Pubudu N. Pathirana, Ming Ding, Aruna Seneviratne, Zihuai Lin, Octavia A. Dobre, Won-Joo Hwang
2021 arXiv   pre-print
The recent FL designs for smart healthcare are then discussed, ranging from resource-aware FL, secure and privacy-aware FL to incentive FL and personalized FL.  ...  Federated Learning (FL), as an emerging distributed collaborative AI paradigm, is particularly attractive for smart healthcare, by coordinating multiple clients (e.g., hospitals) to perform AI training  ...  Moreover, an FL model for federated brain imaging is also suggested in [99] , aiming to support brain tumour segmentation using deep neural networks (DNNs).  ... 
arXiv:2111.08834v1 fatcat:jmex4e25rbgy3bk67iolrj4uee

MeDaS: An open-source platform as service to help break the walls between medicine and informatics [article]

Liang Zhang, Johann Li, Ping Li, Xiaoyuan Lu, Peiyi Shen, Guangming Zhu, Syed Afaq Shah, Mohammed Bennarmoun, Kun Qian, Björn W. Schuller
2020 arXiv   pre-print
In particular, DL is experiencing an increasing development in applications for advanced medical image analysis in terms of analysis, segmentation, classification, and furthermore.  ...  In the past decade, deep learning (DL) has achieved unprecedented success in numerous fields including computer vision, natural language processing, and healthcare.  ...  The tools are discussed in this section, and the whole architecture of MeDaS is given in Fig. 5 and Section V.  ... 
arXiv:2007.06013v2 fatcat:lhlovk2wendkbk55gjs5nbsgyu

D2.7 Key performance indicators selection and definition - final version

Susanna Bonura, Davide Dalle Carbonare
2020 Zenodo  
This task will therefore provide to the validation work package (WP7) with the expected outcomes, which shall be compared with the real results of the validation activities in order to assess the success  ...  the Smart Manufacturing and Health pilots setup and execution, together with the evaluation of the KPIs, will be reported in order to assess the usage of the MUSKETEER platform.  ...  G3.3_Q02 Given the data on pelvis MRI exams as well as multiparametric MRI exams for male patients and a model adopted for predictions, is MUSKETEER trained model able to better identify and segment prostate  ... 
doi:10.5281/zenodo.5845684 fatcat:zedfi6jdibgptbherd6rp2abte
« Previous Showing results 1 — 15 out of 309 results