Medical Image Segmentation Techniques

Riffle Shuffle: A Supervised, Symmetry-Driven, GUI Toolkit for Mouse Brain Stack Registration and Plane Assignment

The paper introduces a GUI toolkit for registering brain slices and assigning them to planes from the Allen Mouse Brain Atlas, using symmetry constraints and dynamic programming.

Non-Linear Realignment Improves Hippocampus Subfield Segmentation

This paper improves hippocampus subfield segmentation by using non-linear realignment to reduce movement artefacts and enhance image quality in MR scans.

Automated lesion segmentation with BIANCA: impact of population-level features, classification algorithm and locally adaptive thresholding

This paper improves the BIANCA tool for WMH segmentation by introducing a locally adaptive thresholding method, LOCATE, which significantly enhances segmentation performance compared to global thresholding.

A comparison of automated lesion segmentation approaches for chronic stroke T1-weighted MRI data

The paper compares automated lesion segmentation methods for chronic stroke T1-weighted MRI data, finding LINDA performs best overall while Gaussian Bayes has highest recall.

Dilated Saliency U-Net for White Matter Hyperintensities Segmentation using Irregularity Age Map

This paper introduces a Dilated Saliency U-Net for WMH segmentation using an irregularity age map, achieving better performance with fewer parameters and shorter training time.

Mammogram Segmentation using Multi-atlas Deformable Registration

This paper proposes a method for breast region segmentation in mammograms using multi-atlas deformable registration, achieving better performance than existing methods.

A framework for evaluating correspondence between brain images using anatomical fiducials

This paper introduces anatomical fiducials (AFIDs) to improve spatial correspondence in brain imaging and demonstrates their effectiveness over traditional voxel overlap metrics.

Evaluation of Enhanced Learning Techniques for Segmenting Ischaemic Stroke Lesions in Brain Magnetic Resonance Perfusion Images using a Convolutional Neural Network Scheme

The paper evaluates enhanced machine learning techniques for segmenting ischaemic stroke lesions in MR perfusion images using a CNN, finding data augmentation with binary closing improves segmentation accuracy.

High resolution nonlinear registration with simultaneous modelling of intensities

This paper evaluates FNIRT, a nonlinear image registration tool, showing its effectiveness in handling intensity differences and producing diffeomorphic warps across simulated and experimental data.

Automated analysis of whole brain vasculature using machine learning

The paper develops a deep learning framework to analyze whole brain vasculature in cleared mouse brains, revealing new insights into vascular architecture and collateralization.

EM-LDDMM for 3D to 2D registration

The paper introduces an EM-LDDMM algorithm for registering 3D atlases to 2D sparse target sections, handling uncertainties through hidden variables and diffeomorphic mappings.

Brain tissue segmentation based on MP2RAGE multi-contrast images in 7 T MRI

This paper proposes a brain tissue segmentation method using MP2RAGE multi-contrast images, showing faster processing and comparable segmentation accuracy to existing tools.

Desikan-Killiany-Tourville Atlas Compatible Version of M-CRIB Neonatal Parcellated Whole Brain Atlas: The M-CRIB 2.0

The paper updates the M-CRIB neonatal brain atlas to align with the Desikan-Killiany-Tourville adult atlas and FreeSurfer subcortical segmentations, resulting in a more compatible and accurate whole-brain parcellation.

The semantic segmentation approach for normal and pathologic tympanic membrane using deep learning

This paper develops a deep learning model using Mask R-CNN to segment tympanic membrane structures in endoscopic images, achieving high accuracy in detection and segmentation.

White Matter Hyperintensity Quantification in Large-Scale Clinical Acute Ischemic Stroke Cohorts - The MRI-GENIE Study

The paper presents an automated pipeline for quantifying white matter hyperintensity in acute ischemic stroke cohorts, showing improved accuracy and enabling large-scale analysis.

Automated Quantification of Enlarged Perivascular Spaces in Clinical Brain MRI across Sites

This paper evaluates two automated methods for quantifying enlarged perivascular spaces in clinical MRI scans across multiple sites, finding one method achieves correlation with visual scoring comparable to inter-rater agreement in some regions.

On variational solutions for whole brain serial-section histology using the computational anatomy random orbit model

This paper develops a variational framework for aligning histology stacks to an atlas, addressing curvature non-identifiability and enabling accurate reconstruction of whole-brain structures.

Mapping Mouse Brain Slice Sequence to a Reference Brain Without 3D Reconstruction

This paper introduces a method to map brain slices to a reference atlas without 3D reconstruction, achieving results comparable to experts and better than reconstruction-first approaches.

Statistical shape analysis of large datasets based on diffeomorphic iterative centroids

This paper introduces a diffeomorphic centroid method for shape analysis of large datasets, showing it achieves similar results to variational templates but with 70% faster computation.

Performance of semi-automated hippocampal subfield segmentation methods across ages in a pediatric sampl

This study evaluates two semi-automated hippocampal subfield segmentation methods across different age groups in a pediatric sample, finding negligible age-related differences in subfield validity.

Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure

This paper evaluates MS lesion segmentation algorithms using a new open-science infrastructure, finding that automatic methods lag behind human experts in detection and delineation.

Deep Learning for Quality Control of Subcortical Brain 3D Shape Models

The paper develops deep learning models to assess the quality of subcortical brain shape models from MRI, reducing human rater time by 46-70%.

Using Outliers in Freesurfer Segmentation Statistics to Identify Cortical Reconstruction Errors in Structural Scans

The paper evaluates a statistical QA method for detecting cortical reconstruction errors in neuroimaging data and finds it less accurate than visual inspection but less resource-intensive.

Unbiased Age-Appropriate Structural Brain Atlases for Chinese Pediatrics

The paper creates age-appropriate structural brain atlases for Chinese children using MRI data and shows they improve brain age prediction compared to Western-based atlases.

Segmentation of Myelin-like Signals on Clinical MR Images for Age Estimation in Preterm Infants

This paper develops a segmentation method for myelin-like signals on T2-weighted MRI to estimate gestational age in preterm infants using manual annotations and an expectation-maximization framework.

A scalable method to improve gray matter segmentation at ultra high field MRI

The paper introduces a method to improve gray matter segmentation in ultra high field MRI by using 2D histograms, showing improved borders and providing an open implementation.

Automated Segmentation of Epithelial Tissue Using Cycle-Consistent Generative Adversarial Networks

This paper introduces a cycle-consistent GAN for automated epithelial tissue segmentation without requiring image-mask pairs.

Automated delineation of non-small cell lung cancer

The paper develops an automated tool for delineating non-small cell lung cancer on CT scans, achieving high sensitivity, specificity, and accuracy across diverse tumor characteristics.

Deep learning of quality control for stereotaxic registration of human brain MRI

The paper introduces a deep learning method for automatic quality control of stereotaxic MRI registration, achieving higher accuracy than manual assessment.

A High-Resolution Probabilistic In Vivo Atlas of Human Subcortical Brain Nuclei

The paper constructs a high-resolution probabilistic in vivo atlas of human subcortical brain nuclei using MRI data from 168 adults and provides software tools for atlas development.