Medical Image Segmentation Techniques

Multi-model Segmentation and Morphometric Quantification of Cerebral Amyloid Angiopathy in Alzheimer's Disease Whole Slide Histopathology Images

This paper develops a deep learning framework to segment and quantify cerebral amyloid angiopathy in whole-slide histopathology images, achieving high accuracy and robust generalization across cohorts.

A Deep Learning Framework for Biomarker Segmentation and Classification in Traumatic Brain Injury

This paper introduces a deep learning framework for automated segmentation and classification of traumatic brain injury using GFAP and IBA1 biomarkers, showing improved performance over manual methods.

Automated Ventricle Assessment via Three-dimensional Anatomical Reconstruction (AVA-TAR): a computational toolkit for autonomous lateral ventricle assessment in preclinical hydrocephalus models

This paper develops a deep learning tool for automated segmentation and morphological analysis of lateral ventricles in rodent MRIs, achieving high accuracy and correlation with manual measurements.

ScaleSurfer: multi-scale anatomical segmentation and parcellation of the human brain

ScaleSurfer rapidly estimates whole-brain morphometric features using a multi-scale vision transformer, achieving speeds up to five orders of magnitude faster than traditional methods.

CODAvision: best practices and a user-friendly interface for rapid, customizable segmentation of medical images

CODAvision provides a user-friendly interface for rapid, customizable medical image segmentation using deep learning, enabling non-experts to train and evaluate models across diverse imaging modalities.

Vasculature segmentation in 3D hierarchical phase-contrast tomography images of human kidneys

The paper presents a benchmark for 3D blood vessel segmentation in human kidney phase-contrast tomography images using top-performing deep learning solutions from a global competition.

A-eye: Automated 3D MRI Segmentation and Morphometric Feature Extraction for Eye and Orbit Atlas Construction

This study introduces an automated 3D MRI segmentation method for the human eye and orbit, providing large-scale unbiased atlases for clinical research.

Apparent Anatomical Variability Through Rigid Augmentation Enables Reliable Corpus Callosum Segmentation

This study develops a pipeline to generate synthetic MRI scans with anatomical variation and trains a U-Net model to segment the corpus callosum in marmosets, achieving high accuracy in both healthy and disease contexts.

Anatomy-Guided 3D Graph Networks for Couinaud Segmentation in Tumor Affected Livers

This paper introduces a two-stage framework combining 3D UNet and 3D GCN for accurate Couinaud segmentation in tumor-affected livers, achieving a mean Dice score of 0.828 on blind testing.

A probabilistic atlas of the human thalamic reticular nucleus derived from 7T MRI

This paper constructs a probabilistic atlas of the human thalamic reticular nucleus using 7T MRI, showing high consistency with postmortem data.

Automated Segmentation of Prostatic Gold Fiducial Markers for MR-Only Radiotherapy Planning Using Multi-Modal Consensus Deep Learning

The paper develops a multi-model consensus deep learning approach for automated gold fiducial marker segmentation in prostate MRI, achieving high sensitivity and precision.

MacaSurfer: unified surface-volume mapping of the macaque brain across the lifespan

MacaSurfer provides a unified framework for automated surface-volume mapping of the macaque brain across age and sites, showing high consistency and robustness.

The ENIGMA-PD-WML Pipeline: A Containerized, User-Friendly Approach for Accurate, Standardized Segmentation of White Matter Lesions in Multi-Site MRI Data

Breaking the bottleneck: self-supervised deep learning framework for fully automated fossil CT segmentation

This paper introduces a self-supervised deep learning framework for automated fossil CT segmentation, achieving high accuracy and significantly reducing processing time.

LVentiView: An Open-Source Software for Automated 3D Left Ventricular Mesh Reconstruction and Analysis from Cardiac MRI

LVentiView automates 3D left ventricular mesh reconstruction and analysis from cardiac MRI, achieving accuracy comparable to expert manual segmentation.

Label-Free Multimodal Volumetric Imaging of Colon Cancer Tissue via Registration of Propagation-Based Phase-Contrast CT, Light-Sheet, and Three-Photon Microscopy

This paper develops a registration pipeline to align multimodal 3D imaging data from colon cancer tissue and uses unsupervised clustering to identify spatially coherent tissue regions.

Vascular Deformation Mapping Calibration with Physics-based Synthetic Data on Multi-axial Aortic Motion

This paper calibrates penalty parameters in vascular deformation mapping using synthetic data to improve 3D aortic deformation analysis in health and disease.

Dual-view Guided Context-aware Network for Automated Bone Lesion Segmentation and Quantification in Whole-body SPECT

This paper introduces Bone-Segnet, a dual-view guided network for automated bone lesion segmentation in SPECT images, achieving improved Dice scores and enabling quantitative analysis of lesion characteristics.

Automatic deep learning-based segmentation and quantification of stented arterial cross-sections for morphometric analysis

This paper develops an automated framework for morphometric analysis of stented arterial cross-sections, achieving high accuracy and significantly reducing analysis time.

Automated Segmentation of Hepatic Vessels and Lobules in Whole-Slide Images Using U-Net Models

The paper develops a deep learning pipeline using U-Net models to segment hepatic vessels and lobules in histological images, achieving high Dice scores for various structures.

A Decade of Deep Learning-based Biomedical Image Segmentation

This paper reviews the evolution of deep learning in biomedical image segmentation, highlighting the shift to foundation models and introducing a taxonomy for promptable segmentation methods.

DeepBranchAI: A Novel Cascade Workflow Enabling Accessible 3D Branching Network Segmentation

DeepBranchAI reduces annotation time for 3D branching network segmentation by using a cascade workflow that transforms sparse labels into comprehensive training data.

QNPtoVox: A methods pipeline for mapping 2D quantitative neuropathology to 3D MNI voxel space.

QNPtoVox maps 2D quantitative neuropathology data to 3D MNI voxel space for spatial standardization and integration with neuroimaging tools.

Multi-Contrast MRI Inputs Enable Self-Consistent Tissue Segmentation & Robust Perivascular Space Identification

The paper develops an automated method combining MRI contrasts to improve tissue segmentation and perivascular space detection using data from aging and Alzheimer's studies.

VesSynth: Tubes Are All You Need for Robust Cross-Scale Cross-Modal 3D Vessel Segmentation

This paper introduces VesSynth, a vessel segmentation framework trained on synthetic data that achieves state-of-the-art accuracy across multiple imaging modalities and spatial resolutions.

PRMix: Primary Region Mix Augmentation and Benchmark Dataset for Precise Whole Mouse Brain Anatomical Delineation

The paper introduces PRMix, an augmentation method for improving segmentation of mouse brain regions, and presents a benchmark dataset for anatomical delineation.

Robust Trachea Segmentation from CT Imaging Using Fully Automated and Prompt-Based Models

This paper compares automated and prompt-based models for trachea segmentation in CT scans, showing that dataset structure affects reliability and interpretability.

ROIMAPer: An Open Source Framework for Rapid and Accurate Atlas Based Registration of Individual Brain Images in FIJI

ROIMAPer is an open-source FIJI plugin for registering brain images to standard atlases, demonstrating accuracy in quantifying marker genes across brain regions and subregions.

BIBSNet: A Deep Learning Baby Image Brain Segmentation Network for MRI Scans

BIBSNet is a deep learning model for infant brain segmentation in MRI scans that outperforms JLF in accuracy and speed, with compatible outputs for further analysis.

Evaluating the quality of brainstem ROI registration using structural and diffusion MRI

The paper evaluates diffusion MRI's role in improving brainstem ROI registration accuracy compared to T1w-only methods, showing better performance with diffusion-based pipelines.