Three-dimensional interactive heart models created with AI-enabled segmentation of CT scans may reduce ventricular tachycardia ablation procedure times by 60 percent.
The Food and Drug Administration (FDA) has granted 510(k) clearance for an artificial intelligence (AI)-enabled module from inHEART that delivers automated segmentation of preprocedural computed tomography (CT) scans that can create three-dimensional (3D) models of the heart.
Offering enhanced visualization of cardiac anatomy through the 3D models, the AI module can be seamlessly integrated into major electroanatomic mapping (EAM) systems, according to inHEART.
The company pointed out that early clinical evaluations of the AI module have shown a capability of reducing conventional ventricular tachycardia (VT) ablation procedures from five hours to less than two hours. inHeart added that image-guided procedures with the AI module’s 3D models may lead to a 38 percent reduction in VT recurrence rates.
"Our mission is to make world-class cardiac imaging expertise available to all physicians to optimize treatment strategies, improve clinical outcomes, and treat patients in a timely manner. With our new AI module, we look forward to scaling the production of inHEART's digital twin of the heart in more centers across the U.S.,” noted Todor Jeliaskov, the president and CEO of inHEART.
MRI-Based Deep Learning Algorithm Shows Comparable Detection of csPCa to Radiologists
May 8th 2024In a study involving over 1,000 visible prostate lesions on biparametric MRI, a deep learning algorithm detected 96 percent of clinically significant prostate cancer (csPCa) in comparison to a 98 percent detection rate for an expert genitourinary radiologist.
Study Finds High Concordance Between AI and Radiologists for Cervical Spine Fractures on CT
May 6th 2024Researchers found a 98.3 percent concordance between attending radiology reports and AI assessments for possible cervical spine fractures on CT, according to new research presented at the 2024 ARRS Annual Meeting.
Can a CT-Based Radiomics Model Bolster Detection of Malignant Thyroid Nodules?
May 3rd 2024A computed tomography (CT)-based radiomics model that includes 28 radiomic features showed significantly higher accuracy, sensitivity, and specificity than conventional CT in differentiating benign and malignant thyroid nodules, according to newly published research.
New Literature Review Finds ChatGPT Effective in Radiology in 84 Percent of Studies
April 29th 2024While noting a variety of pitfalls with the chatbot ranging from hallucinations to improper citations, the review authors found the use of ChatGPT in radiology demonstrated “high performance” in 37 out of 44 studies.