Filters








7 Hits in 6.5 sec

Efficient machine learning framework for computer-aided detection of cerebral microbleeds using the Radon transform

Amir Fazlollahi, Fabrice Meriaudeau, Victor L. Villemagne, Christopher C. Rowe, Paul Yates, Olivier Salvado, Pierrick Bourgeat
2014 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)  
This paper presents a computer-aided detection technique that utilizes a novel cascade of random forest classifiers which are trained on robust Radon-based features with an unbalanced sample distribution  ...  Recent developments of susceptibility weighted MR techniques have improved visualization of venous vasculature and underlying pathologies such as cerebral microbleed (CMB).  ...  This method utilizes a cascade of machine learning random forest (RF) classifiers that are trained on a set of robust Radon-based features.  ... 
doi:10.1109/isbi.2014.6867822 dblp:conf/isbi/FazlollahiMVRYSB14 fatcat:lubudmldtnd2dgcqpgzykgqlwq

An Efficient False-Positive Reduction System for Cerebral Microbleeds Detection

Sitara Afzal, Muazzam Maqsood, Irfan Mehmood, Muhammad Tabish Niaz, Sanghyun Seo
2021 Computers Materials & Continua  
Cerebral Microbleeds (CMBs) are microhemorrhages caused by certain abnormalities of brain vessels.  ...  The proposed framework consists of four main phases (i) making clusters of brain Magnetic Resonance Imaging (MRI) using k-mean classifier (ii) reduce false positives for better classification results (  ...  Acknowledgement: The authors are grateful to the COMSATS University Islamabad, Attock Campus, Pakistan for their support for this research.  ... 
doi:10.32604/cmc.2021.013966 fatcat:vumfex7nijh5nd36tmc4pmuts4

DEEPMIR: A DEEP neural network for differential detection of cerebral Microbleeds and IRon deposits in MRI [article]

Tanweer Rashid, Ahmed Abdulkadir, Ilya M. Nasrallah, Jeffrey B. Ware, Hangfan Liu, Pascal Spincemaille, J. Rafael Romero, R. Nick Bryan, Susan R. Heckbert, Mohamad Habes
2021 arXiv   pre-print
We tested different combinations of the three modalities to determine the most informative data sources for the detection tasks.  ...  Our results showed that deep learning could automate the detection of small vessel disease lesions and including multimodal MR data (particularly QSM) can improve the detection of CMB and non-hemorrhage  ...  Efficient machine learning framework for computer-aided detection of cerebral microbleeds using the radon transform. 2014 IEEE 11th international symposium on biomedical imaging (ISBI); 2014: IEEE.  ... 
arXiv:2010.00148v3 fatcat:qfoxkor7prehfo6747wmirslvm

International Journal of Intellectual Advancements and Research in Engineering Computations Cerebral microbleeds detection using convolutional neural network with maxpooling algorithm

Pradeepkumar, Kathirvel, Marimuthu, Mohamad, Ugscholars
unpublished
Compared with the previous methods the detection is based upon the feature extraction process and they used the sliding window approach, and the detection of cerebral Microbleeds is only done.  ...  Compared to the previous methods, this can remove the massive redundant computations and increase the speed and detection of the process.  ...  In such a way various methods such as deep learning based 3D feature representation, Radon transform has a sensitivity of 92.04% and the false detection rate of 16.84 and they use the computer aided detection  ... 
fatcat:fot63yywgncangltxghwtvsodu

Medical machine intelligence: swarm optimization, feature fusion, and neighboring-awareness

Siyuan Lu
2022
An optimal backbone selection method is proposed to obtain the best backbone model, and an extreme learning machine is used for classification.  ...  Specifically, the contributions to the detection of COVID-19 using chest CT scans are demonstrated.  ...  Acknowledgments It still feels like a dream for me to study in the UK in pursuit of PhD because I am a seriously  ... 
doi:10.25392/leicester.data.21063016.v1 fatcat:gxcccxrcyvc3jco5ieaivcozwq

Data harmonization in PET imaging

NICOLA ALCHERA
2021
The possibility of sharing data quickly, the development of machine learning and data mining techniques, the increasing availability of computational power and digital data storage which characterize this  ...  Although the a-priori harmonization guarantees best results, it is not often used for practical and/or technical reasons. In this thesis I will focus on a-posteriori harmonization.  ...  Chapter 3 Methods Machine Learning overview Machine learning (ML) is the study of computer algorithms that improve automatically through experience and by the use of data.  ... 
doi:10.15167/alchera-nicola_phd2021-07-09 fatcat:xrjuuqsyorha7mfr26etdle7si

Robust multi-structure segmentation of magnetic resonance brain images

Christian Ledig, Daniel Rueckert, European Union
2016
The results show that cerebral white matter atrophy is increased in TBI and that the involvement of individual brain structures, such as the hippocampus or the thalamus, is particularly predictive for  ...  Magnetic resonance (MR) imaging is a powerful technique for the non-invasive in-vivo imaging of the human brain.  ...  Two promising approaches to address this limitation are 1) the targeted segmentation of different pathologies (e.g. contusions, lesions) using machine learning (e.g. deep learning, RFs) and 2) the detection  ... 
doi:10.25560/28959 fatcat:c63ztanfoja7dg7mucveidfggi