On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

9 results for “T2-weighted”

A deep learning-based method for prostate segmentation in T2-weighted magnetic resonance imagingeess.IV

Deep CNNs segment prostate from MRI images.

problem Variability and scarcity of annotated prostate MRI data.

method Two-step CNN approach: global bounding box, local delineation; data augmentation.

result State-of-the-art Dice scores (90.6) on PROMISE12 dataset.

prostate segmentation MRI deep learning CNN T2-weighted

2019-01-27abs ↗pdf ↗

Comprehensive analysis of synthetic learning applied to neonatal brain MRI segmentationstat.ML

Synthetic learning improves neonatal brain MRI segmentation robustness.

problem Challenges in neonatal brain MRI segmentation due to image contrast and anatomical variations.

method Synthetic learning model trained on few T2-weighted volumes, then enhanced with motion artifacts and over-segmentation.

result Synthetic learning robust to image contrast and improves segmentation of both T1- and T2-weighted images.

neonatal brain MRI synthetic learning segmentation motion artifacts over-segmentation

2023-09-11abs ↗pdf ↗

Intensity augmentation for domain transfer of whole breast segmentation in MRIeess.IV

Intensity augmentation improves breast MRI segmentation accuracy.

problem Improving segmentation accuracy across different MRI scanners and protocols.

method Applied intensity augmentation in addition to geometric augmentation during training.

result Increased segmentation performance from 0.71 to 0.90.

breast MRI segmentation domain adaptation intensity augmentation 3D U-net

2019-09-05abs ↗pdf ↗

Reconstructing Multi-echo Magnetic Resonance Images via Structured Deep Dictionary Learningcs.LG

New technique halves scan time for multi-echo MR images.

problem Slow acquisition of multi-echo magnetic resonance images.

method Structured deep dictionary learning for adaptive reconstruction.

result Scan time reduced by half compared to state-of-the-art.

Magnetic Resonance Imaging Multi-Echo Compressed Sensing Deep Learning Dictionary Learning

2019-12-10abs ↗pdf ↗

Deep learning-based development of personalized human head model with non-uniform conductivity for brain stimulationcs.LG

Paper proposes a neural network for estimating brain conductivity without segmentation.

problem Accurate head model generation for personalized TMS with realistic conductivity.

method Convolutional neural network estimating conductivity from MRI data.

result Smooth electric field results similar to conventional methods without segmentation.

brain stimulation neural network MRI conductivity estimation TMS

2019-10-06abs ↗pdf ↗

Brain MRI Tumor Segmentation with Adversarial Networkseess.IV

SegAN-CAT improves brain tumor segmentation in MRI using adversarial networks.

problem Improving brain tumor segmentation accuracy in MRI.

method Adversarial Networks, transfer learning, single modality MRI.

result Transfer learning improves single modality MRI segmentation performance.

brain tumor segmentation MRI adversarial networks transfer learning deep learning

2019-10-07abs ↗pdf ↗

Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximizationcs.LG

In this paper, we address the problem of synthesizing multi-parameter magnetic resonance imaging (mp-MRI) data, i.e. Apparent Diffusion Coefficients (ADC) and T2-weighted (T2w), containing clinically significant (CS) prostate cancer (PCa) via semi-supervised adversarial learning. Specifically, our synthesizer generates…

2018-12-17abs ↗pdf ↗

Improvement of Multiparametric MR Image Segmentation by Augmenting the Data with Generative Adversarial Networks for Glioma Patientseess.IV

Study generates synthetic MR images to improve glioma segmentation.

problem Scarce annotated medical image data for glioma patients.

method Used generative adversarial networks (GANs) to create synthetic MR images.

result Synthetic images improved U-Net segmentation performance.

glioma brain tumor MR imaging GANs image segmentation

2019-10-01abs ↗pdf ↗

Predicted disease compositions of human gliomas estimated from multiparametric MRI can predict endothelial proliferation, tumor grade, and overall survivalq-bio.QM

MRI method predicts glioma features, survival, and endothelial proliferation.

problem Invasive biopsy limits detection of glioma features due to tumor heterogeneity.

method Voxel-wise, multiparametric MRI radiomics with k-NN classifier.

result Model accurately predicts disease compositions, survival, and endothelial proliferation.

gliomas MRI radiomics endothelial proliferation survival prediction minimally invasive

2019-08-06abs ↗pdf ↗