Image Segmentation

Image segmentation is the task of labeling an image at the pixel level, and it underpins much of modern medical imaging, autonomous perception, and scene understanding. Here we break down segmentation architectures, loss functions, and evaluation practices, with frequent attention to the medical settings where boundary accuracy and robustness matter most. Each piece traces the method back to its source research.

MAAPO Optimizes Image Thresholds With Membrane Computing

MAAPO Optimizes Image Thresholds With Membrane Computing

Leave a Comment / Image Segmentation, Optimization & Learning Theory /

Analysis by the aitrendblend editorial team  •  Optimization and learning theory  •  Peer reviewed in Artificial Intelligence Review  •  2025 multilevel thresholding image segmentation artificial protozoa optimizer membrane computing metaheuristic optimization Otsu and Kapur MAAPO treats each candidate set of image thresholds as a protozoan searching a histogram, splits the population into membranes to keep […]

MAAPO Optimizes Image Thresholds With Membrane Computing Read More »

One Model Learns To Segment The Pancreas On CT And MRI

One Model Learns To Segment The Pancreas On CT And MRI

Leave a Comment / Image Segmentation, Medical AI /

Analysis by the aitrendblend editorial team. Medical review. Source preprint posted to arXiv, September 2026. Medical Imaging AI Domain Adaptation Pancreas Segmentation nnU-Net CT and MRI One Encoder, Two Imaging WorldsTeaching one model to see the same pancreas whether it is looking at a CT scan or an MRI. A patient enrolled in a pancreatic

One Model Learns To Segment The Pancreas On CT And MRI Read More »

DeepCut++'s Single Best Fusion Weight Does Not Actually Win Every Task.

DeepCut++’s Single Best Fusion Weight Does Not Actually Win Every Task

Leave a Comment / Computer Vision, Image Segmentation /

Analysis by the aitrendblend editorial team. Nine minute read. Graph Neural Networks Unsupervised Segmentation Computer Vision Feature Fusion Ablation Study Object masks produced by graph based unsupervised segmentation, the task DeepCut++ targets without any labeled training data. Somewhere in a supplementary table, deep inside a paper that already claims state of the art results across

DeepCut++’s Single Best Fusion Weight Does Not Actually Win Every Task Read More »

Prototype Guided Graph Reasoning for Few Shot Medical Segmentation

Prototype Guided Graph Reasoning for Few Shot Medical Segmentation

Leave a Comment / Image Segmentation, Medical AI /

Analysis by the aitrendblend editorial team · Medical review· Pillar: AI for medical imaging and healthcare · Source paper published in IEEE Transactions on Medical Imaging, February 2025 Few Shot Segmentation Graph Convolutional Networks Medical Imaging MRI and CT Abdominal and Cardiac Organs A model trained to recognize a kidney in one hospital’s scans often

Prototype Guided Graph Reasoning for Few Shot Medical Segmentation Read More »

CardioMorphNet: Shape-Guided Bayesian Recurrent Deep Learning for 3D Cardiac Motion Estimation.

CardioMorphNet: Shape-Guided Bayesian Recurrent Deep Learning for 3D Cardiac Motion Estimation

Leave a Comment / Machine Learning, Image Segmentation, Medical AI /

CardioMorphNet: Shape-Guided Bayesian Recurrent Deep Learning for 3D Cardiac Motion Estimation | AI Trend Blend Medical AI · Medical Image Analysis 113 (2026) 104149 · 18 min read CardioMorphNet Taught an AI to Track Your Heartbeat Without Ever Looking at Raw Pixels Researchers at the University of Glasgow and the University of Manchester built a

CardioMorphNet: Shape-Guided Bayesian Recurrent Deep Learning for 3D Cardiac Motion Estimation Read More »

GM-ABS: SAM-Driven Active Barely Supervised 3D Medical Image Segmentation.

GM-ABS: SAM-Driven Active Barely Supervised 3D Medical Image Segmentation

Leave a Comment / Machine Learning, Image Segmentation, Medical AI /

GM-ABS: SAM-Driven Active Barely Supervised 3D Medical Image Segmentation | AI Trend Blend AITrendBlend Medical AI Computer Vision Image Segmentation About Medical AI · IEEE Transactions on Medical Imaging, Vol. 45, Jan. 2026 · CUHK / Harvard · 23 min read GM-ABS: What Happens When You Let SAM Do the Pseudo-Labeling and Your Expert Only

GM-ABS: SAM-Driven Active Barely Supervised 3D Medical Image Segmentation Read More »

BundleParc: Tractography-Free White Matter Bundle Parcellation with MedNeXt + Cross-Attention

BundleParc: Tractography-Free White Matter Bundle Parcellation with MedNeXt + Cross-Attention

Leave a Comment / Machine Learning, Image Segmentation, Medical AI, Vision Transformers & Attention /

BundleParc: Tractography-Free White Matter Bundle Parcellation with MedNeXt + Cross-Attention | AI Trend Blend AITrendBlend Medical AI Image Segmentation About Medical AI · Medical Image Analysis 112 (2026) · Université de Sherbrooke · 22 min read BundleParc: The Brain Mapping Method That Skips Tractography Entirely — and Does It Better Researchers at Université de Sherbrooke

BundleParc: Tractography-Free White Matter Bundle Parcellation with MedNeXt + Cross-Attention Read More »

YoloSeg: One Labeled Image Is All You Need for Medical Image Segmentation.

YoloSeg: One Labeled Image Is All You Need for Medical Image Segmentation

Leave a Comment / Machine Learning, Image Segmentation, Medical AI /

YoloSeg: One Labeled Image Is All You Need for Medical Image Segmentation | AI Trend Blend AITrendBlend Machine Learning Computer Vision Image Segmentation About Medical AI · Medical Image Analysis, Vol. 112 (2026) · 20 min read One Image, Ten Datasets, Near-Perfect Scores: YoloSeg Redefines What Medical AI Needs to Learn A team at the

YoloSeg: One Labeled Image Is All You Need for Medical Image Segmentation Read More »

MEWS: Semantic Segmentation With Almost No Labels — A Few Pixels Per Class Is All You Need.

MEWS: Semantic Segmentation With Almost No Labels — A Few Pixels Per Class Is All You Need

Leave a Comment / Machine Learning, Computer Vision, Image Segmentation /

MEWS: Semantic Segmentation With Almost No Labels — A Few Pixels Per Class Is All You Need | AI Trend Blend AITrendBlend Machine Learning Computer Vision Image Segmentation About Computer Vision · Neurocomputing 680 (2026) 133290 · 18 min read MEWS: The Segmentation Framework That Beats CLIP With Just a Few Pixel Clicks Per Class

MEWS: Semantic Segmentation With Almost No Labels — A Few Pixels Per Class Is All You Need Read More »

MeCSAFNet: Dual-Branch ConvNeXt for Multispectral Semantic Segmentation.

MeCSAFNet: Dual-Branch ConvNeXt for Multispectral Semantic Segmentation

Leave a Comment / Machine Learning, Image Segmentation, Remote Sensing AI /

MeCSAFNet: Dual-Branch ConvNeXt for Multispectral Semantic Segmentation | AI Trend Blend Remote Sensing AI · Neurocomputing 685 (2026) 133533 · 22 min read Seeing Every Wavelength at Once: How MeCSAFNet Rewires Multispectral Segmentation Researchers at Universitat Autònoma de Barcelona built a dual-branch ConvNeXt network that separates visible and non-visible spectral information, fuses them with CBAM

MeCSAFNet: Dual-Branch ConvNeXt for Multispectral Semantic Segmentation Read More »