Medical Image Segmentation Techniques

From Few Labels to Full Insight: 3D Semantic Segmentation of Brain White Matter Microstructures from a Sparsely Annotated X-ray Nano Holotomography Dataset

The paper develops a deep learning framework for 3D segmentation of brain white matter microstructures from X-ray nano holography data, achieving high accuracy in complex anatomical regions.

A Deep Learning Model for Accurate Segmentation of the Drosophila melanogaster Brain from Micro-CT Imaging

This paper introduces a deep learning model that segments Drosophila melanogaster brains from Micro-CT images using minimal training data, enabling rapid phenotypic analysis.

Deep-diffeomorphic networks for conditional brain templates

This paper introduces a deep-learning method for creating age-dependent brain templates using diffeomorphic transformations, showing it produces high-fidelity spatial templates but struggles to capture all age-related morphological changes.

Vessels hiding in plain sight: quantifying brain vascular morphology in anatomical MR images using deep learning

The paper trains a deep learning model to quantify brain vascular morphology from standard MR images, showing it captures aging and health-related features not found in traditional metrics.

A-eye: Automated 3D Segmentation of Healthy Human Eyeand Orbit Structures and Axial Length Extraction

This paper develops automated 3D segmentation techniques for human eye and orbit structures using MRI and evaluates axial length estimation.

WMH-DualTasker: A weakly-supervised deep learning model for automated white matter hyperintensities segmentation and visual rating prediction

WMH-DualTasker is a weakly-supervised deep learning model that segments white matter hyperintensities and predicts visual ratings, outperforming supervised methods on benchmark datasets.

UltraCortex: Submillimeter Ultra-High Field 9.4 T Brain MR Image Collection and Manual Cortical Segmentations

UltraCortex provides high-resolution 9.4 T brain MRI data and validated segmentations, addressing gaps in existing repositories.

SegCSR: Weakly-Supervised Cortical Surfaces Reconstruction from Brain Ribbon Segmentations

This paper introduces a weakly-supervised method for cortical surface reconstruction using brain MRI ribbon segmentations, achieving comparable or better accuracy than supervised methods.

Longitudinal deformation based morphometry pipeline to study neuroanatomical differences in structural MRI based on SyN unbiased templates

This paper introduces a two-level deformation-based morphometry pipeline for longitudinal brain change analysis using MRI, showing improved sensitivity and accuracy in detecting volume changes compared to traditional methods.

Automatic semantic segmentation of the osseous structures of the paranasal sinuses

The paper introduces an open-source model for automatically segmenting osseous structures of the paranasal sinuses, achieving high accuracy in ex vivo CT scans.

A Case for Automated Segmentation of MRI Data in Milder Neurodegenerative Diseases

This study evaluates automated MRI segmentation pipelines in GM1 gangliosidosis patients and controls, finding some methods comparable to manual segmentation for specific brain structures.

Fully Automated MRI-based Analysis of the Locus Coeruleus in Aging and Alzheimer's Disease Dementia using ELSI-Net

This paper introduces ELSI-Net, a deep learning method for automated Locus Coeruleus segmentation and feature extraction in aging and Alzheimer's Disease dementia, showing high agreement with manual ratings and correlations to CSF biomarkers.

Ex vivo human brain volumetry: validation of magnetic resonance imaging measurements

This paper validates MRI brain volume measurements using ex vivo specimens and finds that SynthSeg provides accurate T1-weighted volumes compared to water displacement.

UltraTimTrack: a Kalman-filter-based algorithm to track muscle fascicles in ultrasound image sequences

UltraTimTrack improves fascicle tracking in ultrasound images by combining Kalman filters with existing algorithms, reducing noise and drift across conditions.

EPISeg: Automated segmentation of the spinal cord on echo planar images using open-access multi-center data

The paper introduces EPISeg, a deep learning model for automated spinal cord segmentation on gradient-echo EPI data, showing improved performance over existing methods.

CAN TRANSFER LEARNING IMPROVE SUPERVISED SEGMENTATIONOF WHITE MATTER BUNDLES IN GLIOMA PATIENTS?

This study investigates whether transfer learning can improve segmentation of white matter bundles in glioma patients by addressing domain shift between healthy and patient data.

Precise MRI-Histology Coregistration of Paraffin-Embedded Tissue with Blockface Imaging

This paper develops a pipeline for precise MRI-histology coregistration using blockface imaging, achieving high alignment accuracy for neurodegenerative disease research.

Robust data-driven segmentation of pulsatile cerebral vessels using functional magnetic resonance imaging

This study develops an automatic method to segment cerebral arteries and superior sagittal sinus from fMRI data, showing high reproducibility across age groups.

MortX: A Domain Generalization Benchmark for Mouse Cortex Segmentation and Registration

MortX provides a benchmark dataset for mouse cortex segmentation and registration, enabling domain generalization across postnatal ages.

NeuroAtlas: An Artificial Intelligence-based Framework for Annotation, Segmentation and Registration of Large Scale Biomedical Imaging Data

NeuroAtlas provides an AI framework for brain atlas generation and segmentation, demonstrating robust performance on human and mouse brains across imaging modalities and age groups.

Multimodal 3D Image Registration for Mapping Brain Disorders

This paper introduces an AI-driven 3D brain image registration method that improves alignment across scanners and modalities, enhancing atrophy measurement accuracy in neuroimaging studies.

Comparing Automated Subcortical Volume Estimation Methods; Amygdala Volumes Estimated by FSL and FreeSurfer Have Poor Consistency

The paper compares automated subcortical volume estimation methods, finding poor consistency in amygdala volume estimates between FSL and FreeSurfer, which can lead to conflicting results.

SPROUT: A User-friendly, Scalable Toolkit for Multi-class Segmentation of Volumetric Images

SPROUT provides a user-friendly segmentation framework for volumetric images, achieving high-quality results with less manual input than supervised models.

Necessity and Impact of Specialization of Large Foundation Model for Medical Segmentation Tasks

This study evaluates MedSAM and LiteMedSAM for medical image segmentation, finding that off-the-shelf performance is poor but specialized fine-tuning significantly improves accuracy.

A (Sub)field Guide to Quality Control in Hippocampal Subfield Segmentation on High-resolution T2-weighted MRI

The paper surveys QC practices for hippocampal subfield segmentation in MRI and provides recommendations to improve reliability and reporting.

Baby Open Brains: An Open-Source Repository of Infant Brain Segmentations

The paper introduces Baby Open Brains (BOBs), an open-source repository of manually curated infant brain segmentations to improve reproducibility in neuroimaging research.

A 3D Image Segmentation Study of U-Net on CT Images of the Human Aorta with Morphologically Diverse Anatomy

This study compares 2D and 3D U-Net for segmenting human aorta from CT images, finding 3D U-Net performs better but has geometry reconstruction errors.

LightMed: A Light-weight and Robust FFT-Based Model for Adversarially Resilient Medical Image Segmentation

LightMed improves medical image segmentation by using FFT-based processing to enhance robustness against noise and adversarial attacks.

VesselBoost: A Python Toolbox for Small Blood Vessel Segmentation in Human Magnetic Resonance Angiography Data

VesselBoost is a Python tool for segmenting small blood vessels in human MRA data using deep learning and data augmentation to overcome labeling challenges.

Mouse Brain Extractor: Brain segmentation of mouse MRI using global positional encoding and SwinUNETR

The paper develops a deep learning method for mouse MRI brain segmentation using global positional encoding, achieving high accuracy and outperforming existing methods.