arXiv AI August 19, 2026 By Andrea Angino, Ken Trotti, Diego Ulisse Pizzagalli, Rolf Krause, Tiziano Torre, Stefanos Demertzis

Protect the Brain When Treating the Heart: Feasibility of 2.5D U-Net for Real-Time Gaseous Microemboli Detection

Read the original on arXiv AI →

The study evaluates a 2.5D U‑Net model for detecting gaseous microemboli (GME) in real‑time during cardiac surgery using transesophageal echocardiography (TEE). On a pilot dataset of eight patients, the model achieved high precision (92.55%) and recall (80.54%) with an average inference time of 0.12 s per batch, outperforming classical spot detection and 2D U‑Net while maintaining real‑time speed. External validation on a GME‑negative dataset showed few false positives, supporting the model’s feasibility for real‑time GME segmentation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

computer-vision

arXiv Computer Vision

Sep 10

Federated Learning for Cross-Modality Medical Image Segmentation via Augmentation-Driven Generalization

arXiv:2602.20773v2 Announce Type: replace Abstract: Purpose: Developing generalizable medical image segmentation models is challenging because imaging data are distributed across institutions and dif...

By Sachin Dudda Nagaraju, Ashkan Moradi, Bendik Skarre Abrahamsen, Mattijs Elschot

computer-vision multimodal

arXiv AI

Sep 15

GP-VM$\times$SMA: Benchmarking General-Purpose Vision Models and Specialized Architectures for 2D Medical Image Segmentation

arXiv:2603.13044v2 Announce Type: replace-cross Abstract: Medical image segmentation (MIS) is a fundamental component of computer-assisted diagnosis and clinical decision support. Over the past decad...

By Vanessa Borst, Anna Riedmann, Samuel Kounev

computer-vision benchmarks

arXiv Computer Vision

Sep 2

UI-VISA: U-Net Initialized Vascular Image Segmentation Architecture

arXiv:2609.01598v1 Announce Type: new Abstract: Accurate segmentation of vascular structures in digital subtraction angiography (DSA) images remains challenging due to the thin, elongated, and branch...

By Asees Kaur, Suzanne S. Sindi, Erica M. Rutter

computer-vision

Hugging Face Trending Papers

Aug 26

Unsupervised Anatomical Feature Learning via Diffusion Models: Enhanced Medical Image Segmentation with Denoising Diffusion Probabilistic Models

Acquiring pixel-level annotations for medical image segmentation is a severe bottleneck. Traditional U-Net architectures, while effective, learn local texture patterns and lack awareness of global ana...

diffusion computer-vision fine-tuning

arXiv Computer Vision

Sep 1

MCSeg: Pre-training and Fine-tuning Volumetric Pyramid Transformer for Multi-modal Cardiac Image Segmentation

arXiv:2608.30371v1 Announce Type: new Abstract: Automatic cardiac image segmentation is pivotal for diagnosing and treating cardiac diseases. In this work, we introduce MCSeg, a volumetric transforme...

By Zhiyu Ye, Hairong Zheng, Tong Zhang

llms computer-vision fine-tuning multimodal benchmarks

arXiv Computer Vision

Sep 15

Echo-E$^3$Net: Efficient Endocardial Spatio-Temporal Network for Ejection Fraction Estimation

Echo-E$^3$Net is an anatomy‑guided spatio‑temporal neural network designed to estimate left ventricular ejection fraction (LVEF) from ultrasound images. It uses a dual‑phase Endocardial Border Detector to locate end‑diastole and end‑systole landmarks and an Endocardial Feature Aggregator to fuse these landmarks with global deep‑feature descriptors for EF regression. The model achieves competitive accuracy on EchoNet‑Dynamic and EchoNet‑Pediatric datasets while using only 1.55 M parameters and 8.05 GFLOPs, enabling real‑time deployment on limited‑resource devices.

By Moein Heidari, Afshin Bozorgpour, AmirHossein Zarif-Fakharnia, Wenjin Chen, Dorit Merhof, David J. Foran, Jasmine Grewal, Ilker Hacihaliloglu

rag

One email a morning, machine-written

Related stories

Federated Learning for Cross-Modality Medical Image Segmentation via Augmentation-Driven Generalization

GP-VM$\times$SMA: Benchmarking General-Purpose Vision Models and Specialized Architectures for 2D Medical Image Segmentation

UI-VISA: U-Net Initialized Vascular Image Segmentation Architecture

Unsupervised Anatomical Feature Learning via Diffusion Models: Enhanced Medical Image Segmentation with Denoising Diffusion Probabilistic Models

MCSeg: Pre-training and Fine-tuning Volumetric Pyramid Transformer for Multi-modal Cardiac Image Segmentation

Echo-E$^3$Net: Efficient Endocardial Spatio-Temporal Network for Ejection Fraction Estimation