PulseAugur
LIVE 12:23:54
research · [2 sources] ·
0
research

AI model synthesizes pseudo-CT scans from ultrasound for safer medical guidance

Researchers have developed a new framework for generating pseudo-Computed Tomography (pCT) images from 3D Ultrasound (US) data. This method, utilizing a Bottleneck Transformer Residual U-Net3D (BT-ResUNet3D) model, aims to provide real-time anatomical guidance for medical procedures, potentially reducing the need for radiation-exposed CT scans. The system was evaluated on the TRUSTED dataset and demonstrated superior performance in structural fidelity and image quality compared to existing methods. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT This technique could reduce reliance on CT scans for certain medical procedures, offering a safer alternative for patient imaging and guidance.

RANK_REASON This is a research paper detailing a new method for medical image synthesis.

Read on arXiv cs.CV →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 · Sapna Sachan, Amulya Kumar Mahto ·

    3D Ultrasound-Derived Pseudo-CT Synthesis Using a Transformer-Augmented Residual Network for Real-Time Operator Guidance

    arXiv:2605.04856v1 Announce Type: new Abstract: Computed tomography (CT) is indispensable for clinical diagnosis and image-guided interventions but exposes patients to ionizing radiation, motivating the development of safer imaging alternatives. Ultrasound (US) is non-ionizing an…

  2. arXiv cs.CV TIER_1 · Amulya Kumar Mahto ·

    3D Ultrasound-Derived Pseudo-CT Synthesis Using a Transformer-Augmented Residual Network for Real-Time Operator Guidance

    Computed tomography (CT) is indispensable for clinical diagnosis and image-guided interventions but exposes patients to ionizing radiation, motivating the development of safer imaging alternatives. Ultrasound (US) is non-ionizing and widely accessible; however, it is highly opera…