Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters








111 Hits in 3.9 sec

Interpretable CNN for ischemic stroke subtype classification with active model adaptation

Shuo Zhang, Jing Wang, Lulu Pei, Kai Liu, Yuan Gao, Hui Fang, Rui Zhang, Lu Zhao, Shilei Sun, Jun Wu, Bo Song, Honghua Dai (+2 others)
2022 BMC Medical Informatics and Decision Making  
Background TOAST subtype classification is important for diagnosis and research of ischemic stroke.  ...  Utilizing active learning framework, we propose a novel causal CNN, in which it combines with a mixed active selection criterion to optimize the uncertainty of samples adaptively.  ...  Meanwhile, our deepest gratitude goes to the anonymous reviewers and editors for their careful work and thoughtful suggestions that have helped improve this paper substantially.  ... 
doi:10.1186/s12911-021-01721-5 pmid:34986813 pmcid:PMC8729146 fatcat:hw27g2yji5e3pekuffnwdormom

Artificial Intelligence and Acute Stroke Imaging

J.E. Soun, D.S. Chow, M. Nagamine, R.S. Takhtawala, C.G. Filippi, W. Yu, P.D. Chang
2020 American Journal of Neuroradiology  
Artificial intelligence technology is a rapidly expanding field with many applications in acute stroke imaging, including ischemic and hemorrhage subtypes.  ...  Artificial intelligence can help with various aspects of the stroke treatment paradigm, including infarct or hemorrhage detection, segmentation, classification, large vessel occlusion detection, Alberta  ...  ACKNOWLEDGMENTS The authors thank Aidoc, Avicenna, Brainomix, RapidAI, and Viz.ai for providing information regarding commercially available products and sample images of their applications for publication  ... 
doi:10.3174/ajnr.a6883 pmid:33243898 pmcid:PMC7814792 fatcat:uwvjtq42ejfzjoi46eqlublmya

A Review on Computer Aided Diagnosis of Acute Brain Stroke

Mahesh Anil Inamdar, Udupi Raghavendra, Anjan Gudigar, Yashas Chakole, Ajay Hegde, Girish R. Menon, Prabal Barua, Elizabeth Emma Palmer, Kang Hao Cheong, Wai Yee Chan, Edward J. Ciaccio, U. Rajendra Acharya
2021 Sensors  
There are two classes of stroke, namely ischemic stroke (due to impairment of blood supply, accounting for ~70% of all strokes) and hemorrhagic stroke (due to bleeding), both of which can result, if untreated  ...  status and challenges faced by computer aided diagnosis (CAD), machine learning (ML) and deep learning (DL) based techniques for CT and MRI as prime modalities for stroke detection and lesion region segmentation  ...  Regression Automated prognosis for post-treatment ischemic stroke 2016 Chen et al. [121] CT CNN Early stroke detection (ischemic) system with CNN 2017 Lucas et al. [122] CT 3D U-net appended with Convolutional  ... 
doi:10.3390/s21248507 pmid:34960599 pmcid:PMC8707263 fatcat:zc4gtjhkoje2jotcqr5gvlatu4

Deep Learning in Ischemic Stroke Imaging Analysis: A Comprehensive Review

Liyuan Cui, Zhiyuan Fan, Yingjian Yang, Rui Liu, Dajiang Wang, Yingying Feng, Jiahui Lu, Yifeng Fan, Yu Chang Tyan
2022 BioMed Research International  
Particularly, deep learning models with massive data learning capabilities are recognized as powerful auxiliary tools for the acute intervention and guiding prognosis of ischemic stroke.  ...  Ischemic stroke is a cerebrovascular disease with a high morbidity and mortality rate, which poses a serious challenge to human health and life.  ...  In ischemic stroke lesion analysis, the model, including CNN and transformer for encoding and the multihead cross-attention (MHCA) module for decoding, leads to stroke lesion morphology and edges with  ... 
doi:10.1155/2022/2456550 pmid:36420096 pmcid:PMC9678444 fatcat:5sxmcvsgfnb7bbui3y23w5hc5m

Computational Approaches for Acute Traumatic Brain Injury Image Recognition

Emily Lin, Esther L. Yuh
2022 Frontiers in Neurology  
Triage algorithms that can re-order radiological reading queues have been developed, using classification to prioritize exams with suspected critical findings.  ...  Localization models move a step further to capture more granular information such as the location and, in some cases, size and subtype, of intracranial hematomas that could aid in neurosurgical management  ...  (92) reported and publicly released a deep learning model that segmented acute ischemic stroke lesions on diffusionweighted imaging (DWI) with a Dice coefficient of 0.76, similar to interrater agreement  ... 
doi:10.3389/fneur.2022.791816 pmid:35370919 pmcid:PMC8964403 fatcat:oj67mgbelbed5g5i4474gaklxi

An Improved Detection Algorithm for Ischemic Stroke NCCT Based on YOLOv5

Lifeng Zhang, Hongyan Cui, Anming Hu, Jiadong Li, Yidi Tang, Roy Elmer Welsch
2022 Diagnostics  
Ischemic stroke (IS) is a subtype of CS that causes a disruption of cerebral blood flow with subsequent tissue damage.  ...  In this paper, we propose AC-YOLOv5, which is an improved detection algorithm for IS.  ...  Chalela et al. evaluated NCCT to screen acute ischemic stroke. The result was only 56 acute IS patients were screened from 217 acute IS patients, with a sensitivity of 26% [21] .  ... 
doi:10.3390/diagnostics12112591 pmid:36359435 pmcid:PMC9688968 fatcat:lhzunoun2zafhoe24na2lbe2sq

How to Improve the Management of Acute Ischemic Stroke by Modern Technologies, Artificial Intelligence, and New Treatment Methods

Kamil Zeleňák, Antonín Krajina, Lukas Meyer, Jens Fiehler, Daniel Behme, Deniz Bulja, Jildaz Caroff, Amar Ajay Chotai, Valerio Da Ros, Jean-Christophe Gentric, Jeremy Hofmeister, Omar Kass-Hout (+5 others)
2021 Life  
Stroke remains one of the leading causes of death and disability in Europe. The European Stroke Action Plan (ESAP) defines four main targets for the years 2018 to 2030.  ...  Innovative technologies can be implemented for acute stroke patient management soon. Artificial intelligence (AI) and robotics are used increasingly often without the exception of medicine.  ...  The perfusion-diffusion mismatch model can be outperformed by CNN-based models.  ... 
doi:10.3390/life11060488 pmid:34072071 fatcat:knirhcz2zvbmzh7wscu26yacuu

Machine Learning in Action: Stroke Diagnosis and Outcome Prediction

Shraddha Mainali, Marin E. Darsie, Keaton S. Smetana
2021 Frontiers in Neurology  
In stroke, commercially available machine learning algorithms have already been incorporated into clinical application for rapid diagnosis.  ...  The creation and advancement of deep learning techniques have greatly improved clinical utilization of machine learning tools and new algorithms continue to emerge with improved accuracy in stroke diagnosis  ...  • (0.465- 0.533; 0.170-0.328) Giri et al. (33) Ischemic stroke 1D CNN vs. various Leave-one-out • 32 -AIS 15-min EEG with 24 • Accuracy -0.86 Leave-one-out In areas with Time to apply EEG diagnosis by  ... 
doi:10.3389/fneur.2021.734345 pmid:34938254 pmcid:PMC8685212 fatcat:xr7uilf2sneajamrq5ckxyy3ue

Artificial Intelligence: A Shifting Paradigm in Cardio-Cerebrovascular Medicine

Vida Abedi, Seyed-Mostafa Razavi, Ayesha Khan, Venkatesh Avula, Aparna Tompe, Asma Poursoroush, Alireza Vafaei Sadr, Jiang Li, Ramin Zand
2021 Journal of Clinical Medicine  
In this context, the field of cardio-cerebrovascular diseases, which encompasses a wide range of conditions—from heart failure to stroke—has made some advances to provide assistive tools to care providers  ...  technological engines have the potential to improve healthcare access and equitability while reducing overall costs, diagnostic errors, and disparity in a system that affects patients and providers and strives for  ...  [63] developed an automated stroke subtype classification using radiology and progress reports and showed agreement with the manual TOAST (Trial of ORG 10172 in acute stroke treatment) [64] classification  ... 
doi:10.3390/jcm10235710 pmid:34884412 fatcat:uzn2wx5tzvaovme4h7p36z775q

Advances in Deep Learning-Based Medical Image Analysis

Xiaoqing Liu, Kunlun Gao, Bo Liu, Chengwei Pan, Kongming Liang, Lifeng Yan, Jiechao Ma, Fujin He, Shu Zhang, Siyuan Pan, Yizhou Yu
2021 Health Data Science  
With the booming growth of artificial intelligence (AI), especially the recent advancements of deep learning, utilizing advanced deep learning-based methods for medical image analysis has become an active  ...  Overall, according to the best available evidence, deep learning models performed well in medical image analysis, but what cannot be ignored are the algorithms derived from small-scale medical datasets  ...  [64] used a U-shaped network (Res-CNN) to automatically segment acute ischemic stroke lesions from multimodality MRIs, and the average Dice coefficient was 0.742. Zhao et al.  ... 
doi:10.34133/2021/8786793 pmid:38487506 pmcid:PMC10880179 fatcat:d6nkb4yoxrcgni4y5owju5pnh4

A Deep Learning-Based Model for Classification of Different Subtypes of Subcortical Vascular Cognitive Impairment With FLAIR

Qi Chen, Yao Wang, Yage Qiu, Xiaowei Wu, Yan Zhou, Guangtao Zhai
2020 Frontiers in Neuroscience  
Deep learning methods have shown their great capability of extracting high-level features from image and have been used for effective medical imaging classification recently.  ...  The accuracy of our proposed model has reached 98.6% on a training set and 97.3% on a validation set. The test accuracy on an untrained testing set reaches 93.8% with robustness.  ...  Considering the importance of VaMCI subtypes for clinical decision, and the possibility for image classification suggested by limited neuroimaging studies, we constructed an efficient 3D-CNN model to achieve  ... 
doi:10.3389/fnins.2020.00557 pmid:32625048 pmcid:PMC7315844 fatcat:qoxyauz25few7omx2gqo6driqi

Accurate and Efficient Intracranial Hemorrhage Detection and Subtype Classification in 3D CT Scans with Convolutional and Long Short-Term Memory Neural Networks [article]

Mihail Burduja, Radu Tudor Ionescu, Nicolae Verga
2020 arXiv   pre-print
For efficient processing, we consider various feature selection methods to produce a subset of useful CNN features for the LSTM.  ...  After the challenge, we conducted a subjective intracranial hemorrhage detection assessment by radiologists, indicating that the performance of our deep model is on par with that of doctors specialized  ...  They employed a cascaded model, with an RNN for intracranial hemorrhage detection and another RNN for subtype classification.  ... 
arXiv:2008.00302v3 fatcat:i6hzazwwwna5hbryxy6ufodmva

Artificial Intelligence in Neuroradiology: A Review of Current Topics and Competition Challenges

Daniel T. Wagner, Luke Tilmans, Kevin Peng, Marilyn Niedermeier, Matt Rohl, Sean Ryan, Divya Yadav, Noah Takacs, Krystle Garcia-Fraley, Mensur Koso, Engin Dikici, Luciano M. Prevedello (+1 others)
2023 Diagnostics  
Numerous applications relevant to ischemic stroke, intracranial hemorrhage, brain tumors, demyelinating disease, and neurodegenerative/neurocognitive disorders were discussed.  ...  The AI applications examined perform a variety of tasks, including localization, segmentation, longitudinal monitoring, diagnostic classification, and prognostication.  ...  Ischemic Stroke Stroke is a leading cause of death and the number one cause of serious long-term disability in the United States, with ischemic stroke accounting for most stroke types [7] .  ... 
doi:10.3390/diagnostics13162670 pmid:37627929 pmcid:PMC10453240 fatcat:eevdxlkyjbfodj4woysetendje

Accurate and Efficient Intracranial Hemorrhage Detection and Subtype Classification in 3D CT Scans with Convolutional and Long Short-Term Memory Neural Networks

Mihail Burduja, Radu Tudor Ionescu, Nicolae Verga
2020 Sensors  
For efficient processing, we consider various feature selection methods to produce a subset of useful CNN features for the LSTM.  ...  After the challenge, we conducted a subjective intracranial hemorrhage detection assessment by radiologists, indicating that the performance of our deep model is on par with that of doctors specialized  ...  While hemorrhagic strokes are less frequent than ischemic strokes (87%), the former ones present a higher mortality rate.  ... 
doi:10.3390/s20195611 pmid:33019508 pmcid:PMC7582288 fatcat:3xkw6dmoxnezrhuimwzmcvikaa

Stroke recovery phenotyping through network trajectory approaches and graph neural networks [article]

Sanjukta Krishnagopal, Keith Lohse, Robynne Braun
2021 arXiv   pre-print
Our analysis identified 3 distinct stroke trajectory profiles that align with clinically relevant stroke syndromes, characterized both by distinct clusters of symptoms, as well as differing degrees of  ...  We demonstrate that trajectory profile clustering is an effective method for identifying clinically relevant recovery subtypes in multidimensional longitudinal datasets, and for early prediction of symptom  ...  Lindgren for their diligent critical review and comments on the manuscript.  ... 
arXiv:2109.14659v1 fatcat:ktffypd2lrhlpaqohl33bzvyn4
« Previous Showing results 1 — 15 out of 111 results