Dimensionality Reduction and Feature Matching in Functional MRI Imaging Data

AbstractSeveral different groups have demonstrated the feasibility of building forward models of functional MRI data in response to concrete stimuli such as pictures or video, and of using these models to decode or reconstruct stimuli shown while acquiring test fMRI data. In this paper, we introduce an approach for building forward models of conceptual stimuli, concrete or abstract, and for using these models to carry out decoding of semantic information from new imaging data. We show that this approach generalizes to topics not seen in training, and provides a straightforward path to decoding from more complex stimuli such as sentences or paragraphs.

Download Full-text

Supporting protocol for use-case 1: Dimensionality reduction in "M2aia - Interactive, fast and memory efficient analysis of 2D and 3D multi-modal mass spectrometry imaging data" v1 (protocols.io.brw4m7gw)

protocols.io ◽

10.17504/protocols.io.brw4m7gw ◽

2021 ◽

Author(s):

Jonas Cordes

Keyword(s):

Mass Spectrometry ◽

Dimensionality Reduction ◽

Mass Spectrometry Imaging ◽

Use Case ◽

Imaging Data ◽

Modal Mass ◽

2D And 3D ◽

Memory Efficient

Download Full-text

MRI Findings of Acute Sports Injury of the Gastrocnemius Muscle

Scientific Programming ◽

10.1155/2021/9899036 ◽

2021 ◽

Vol 2021 ◽

pp. 1-9

Author(s):

Li Xue

Keyword(s):

Muscle Tissue ◽

Muscle Injury ◽

Gastrocnemius Muscle ◽

Sports Injury ◽

Muscle Group ◽

Imaging Data ◽

Mri Imaging ◽

Mri Findings ◽

Texture Characteristics ◽

Before And After

Objective.To investigate the MRI findings of acute sports injury of the gastrocnemius muscle and to provide evidence for clinical diagnosis. Methods. The MRI imaging data of 16 cases of gastrocnemius muscle group sports injury were compared, analyzed, and collated. In this paper, the variation of MRI image entropy before and after gastrocnemius muscle injury was studied by using the texture characteristics of the muscle image. Results. The experiment demonstrated that the entropy of MRI images before and after fatigue showed a decrease after muscle tissue was raised; that is, after muscle tissue underwent centrifugal and centripetal contraction. This result is more effective and convenient for nondestructive prediction of the gastrocnemius muscle injury state. Conclusion. MRI can show the site and pathological changes of acute gastrocnemius injury.

Download Full-text

Enabling On-demand Real-time Functional MRI Analysis Using Grid Technology

Methods of Information in Medicine ◽

10.1055/s-0038-1634023 ◽

2005 ◽

Vol 44 (05) ◽

pp. 665-673 ◽

Cited By ~ 11

Author(s):

K. Matsuo ◽

Y. Tanaka ◽

L. F. G. Sarmenta ◽

T. Nakai ◽

E. Bagarinao

Keyword(s):

Real Time ◽

Functional Mri ◽

System Integration ◽

Data Transfer ◽

Acquisition Time ◽

Imaging Data ◽

Computing Power ◽

Medical Practitioners ◽

On Demand ◽

Image Volume

Summary Objectives: The analysis of brain imaging data such as functional MRI often requires considerable computing resources, which in most cases are not readily available in many medical imaging facilities. This lack of computing power makes it difficult for researchers and medical practitioners alike to perform on-site analysis of the generated data. This paper presents a system that is capable of analyzing functional MRI data in real time with results available within seconds after data acquisition. Methods: The system employs remote computational servers to provide the necessary computing power. System integration is accomplished by an accompanying software package, which includes fMRI analysis tools, data transfer routines, and an easy-to-use graphical user interface. The remote analysis is transparent to the user as if all computations are performed locally. Results: The use of PC clusters in the analysis of fMRI data significantly improved the performance of the system. Simulation runs fully achieved real-time performance with a total processing time of 1.089 s per image volume (64 x 64 x 30 in size), much less than the per volume acquisition time set to 3.0 s. Conclusions: The results show the feasibility of using remote computational resources to enable on-demand real-time fMRI capabilities to imaging sites. It also offers the possibility of doing more intensive analysis even if the imaging site doesn’t have the necessary computing resources.

Download Full-text

Early effects of surgery and radiotherapy on activity levels in patients with brain tumours: preliminary data from the BrainWear trial

Neuro-Oncology ◽

10.1093/neuonc/noz167.048 ◽

2019 ◽

Vol 21 (Supplement_4) ◽

pp. iv12-iv12

Author(s):

Seem Dadhania ◽

James Wei Wang ◽

Boyu Yu ◽

Waqar Saleem ◽

Catherine Blake ◽

...

Keyword(s):

Brain Tumours ◽

Activity Levels ◽

Imaging Data ◽

Mri Imaging ◽

Activity Data ◽

Fractionated Radiotherapy ◽

Early Results ◽

Before And After ◽

Treatment Data ◽

Early Effects

Abstract Background BrainWear is a phase II observational clinical trial which collects data on patient activity levels, fatigue, Quality of Life (QoL) and imaging in patients with brain tumours Methods Newly diagnosed patients were offered wrist worn accelerometers (Axivity AX3) to be worn continuously throughout their treatment (surgery, chemoradiotherapy or radiotherapy) to monitor physical activity. We collected standardised measures of QoL, fatigue, MRI imaging data and disease progression. Here, we report early results on activity data 5 days before and after treatment. Results Of 23 patients recruited, we report complete pre and post treatment data in 4 patients (2 HGG, 2 metastatic) who underwent craniotomy (2), fractionated radiotherapy (1) and SRS (1). Both craniotomy patients experienced an immediate 60 – 70% reduction in activity, and were successfully discharged at day 2 post-op even though their activity was still significantly reduced. Both patients recovered another 10% in their activity levels following discharge. Radiotherapy patients experienced no early change within 5 days of starting treatment. Conclusion As expected craniotomy results in much larger changes in activity levels than SRS and radical radiotherapy. Activity levels recover post craniotomy, but this takes > 5 days. Using wearable activity monitors in brain tumour patients is feasible, although there are multiple practical problems. Interpreting such data will require consideration of inpatient vs. outpatient settings.

Download Full-text

Robust unsupervised dimensionality reduction based on feature clustering for single-cell imaging data

Applied Soft Computing ◽

10.1016/j.asoc.2020.106421 ◽

2020 ◽

Vol 93 ◽

pp. 106421

Author(s):

Daniel Peralta ◽

Yvan Saeys

Keyword(s):

Dimensionality Reduction ◽

Single Cell ◽

Cell Imaging ◽

Imaging Data ◽

Feature Clustering ◽

Single Cell Imaging

Download Full-text

MiRNAs, Myostatin, and Muscle MRI Imaging as Biomarkers of Clinical Features in Becker Muscular Dystrophy

Diagnostics ◽

10.3390/diagnostics10090713 ◽

2020 ◽

Vol 10 (9) ◽

pp. 713 ◽

Cited By ~ 1

Author(s):

Roberta Marozzo ◽

Valentina Pegoraro ◽

Corrado Angelini

Keyword(s):

Muscular Dystrophy ◽

Dystrophin Gene ◽

Becker Muscular Dystrophy ◽

Muscle Disease ◽

Clinical Variable ◽

Imaging Data ◽

Mri Imaging ◽

Muscle Mri ◽

Lower Extremity Weakness ◽

Significant Difference

Becker muscular dystrophy (BMD) is an X-linked recessive disorder caused by dystrophin gene mutations. The phenotype and evolution of this muscle disorder are extremely clinical variable. In the last years, circulating biomarkers have acquired remarkable importance in their use as noninvasive biological indicators of prognosis and in monitoring muscle disease progression, especially when associated to muscle MRI imaging. We investigated the levels of circulating microRNAs (myo-miRNAs and inflammatory miRNAs) and of the proteins follistatin (FSTN) and myostatin (GDF-8) and compared results with clinical and radiological imaging data. In eight BMD patients, including two cases with evolving lower extremity weakness treated with deflazacort, we evaluated the expression level of 4 myo-miRNAs (miR-1, miR-206, miR-133a, and miR-133b), 3 inflammatory miRNAs (miR-146b, miR-155, and miR-221), FSTN, and GDF-8 proteins. In the two treated cases, there was pronounced posterior thigh and leg fibrofatty replacement assessed by muscle MRI by Mercuri score. The muscle-specific miR-206 was increased in all patients, and inflammatory miR-221 and miR-146b were variably elevated. A significant difference in myostatin expression was observed between steroid-treated and untreated patients. This study suggests that microRNAs and myostatin protein levels could be used to better understand the progression and management of the disease.

Download Full-text