Radiology
PulseAugur coverage of Radiology — every cluster mentioning Radiology across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
AI integration in consumer products questioned over risks and environmental impact
The author expresses skepticism about the widespread integration of AI, particularly in consumer products. While acknowledging potential benefits in specialized fields like radiology, they argue against its use in every…
-
Radiologists urged to become AI creators to combat workforce shortage
The radiology field faces a significant workforce shortage, prompting a discussion on how to address it. One proposed solution involves shifting the role of radiologists from passive consumers of AI tools to active crea…
-
Remene helps patients understand MRI scans and reports
Remene is a new web-based tool designed to help patients understand their MRI scans and radiology reports. It allows users to upload their MRI data and reports, providing plain-language explanations of medical terms and…
-
AI in Radiology Should Enhance Human Understanding, Not Replace It
Radiologists and mathematicians both prioritize human understanding over simply arriving at a correct answer. The development of artificial intelligence in medicine should aim to augment this human understanding, rather…
-
RADIOlogy offers single-pass zero-shot anomaly detection
Researchers have developed RADIOlogy, a novel single-pass approach for training-free zero-shot anomaly detection. This method leverages an emergent property of multi-head attention pooling in vision-language models to a…
-
Google AI advances TB screening with foundational models · 2 sources tracked
Google Research has developed an AI tool to aid in tuberculosis screening, aiming to improve early detection in underserved regions. The AI analyzes chest X-rays to identify signs of TB, performing comparably to expert …
-
Radiology AI impact questioned amid Texas academic censorship concerns
An AI researcher and radiology resident expresses frustration with the limited real-world impact of AI in their field, despite hype from tech leaders. The resident notes that even basic diagnostic AI tools are subpar an…
-
New ECG Foundation Model Leverages Multi-Source Clinical Data for Enhanced Health Monitoring
Researchers have developed a new foundation model for electrocardiogram (ECG) analysis called MS-ECG-FM. Unlike previous models that relied solely on ECG interpretation reports, MS-ECG-FM is trained using contrastive al…
-
AI's impact on radiology: efficiency boosts demand, defying predictions
AI pioneer Geoffrey Hinton predicted in 2016 that machines would replace radiologists within five years, but the opposite occurred. Increased AI efficiency in scan analysis led to faster reading times, which in turn boo…
-
AI-drafted patient messages increase physician workload, study finds
A study published in NEJM AI, titled "Physician Edits to AI-Drafted Patient Messages and Their Impact on Clinical Workload," investigated the time physicians spent editing AI-generated patient messages. The research fou…
-
UltraPIPS library enhances B-mode ultrasound image analysis with domain-specific models
Researchers have developed UltraPIPS, a new library of perceptual image similarity metrics specifically designed for B-mode ultrasound data. Unlike models trained on natural images, UltraPIPS utilizes foundation models …
-
New benchmark CRS-Bench evaluates medical image encoder reliability
Researchers have developed CRS-Bench, a new benchmark designed to evaluate the reliability of medical image encoders. Unlike previous methods that focused solely on discrimination, CRS-Bench assesses encoders across fou…
-
New LLM frameworks automate radiology report generation and template creation · 2 sources tracked
Researchers have developed new methods for improving radiology report generation using large language models (LLMs). One approach, ASTAR, automates the creation of standardized radiology reporting templates from clinica…
-
AI system structures radiology reports and improves quality assurance
A new multi-agent AI system has been developed to structure radiology reports and perform quality assurance. The system, which uses local large language models and regex rules, successfully organized findings from CT ex…
-
New foundation model unifies pathology and radiology for medical image analysis
Researchers have developed CoM$^3$eT, a novel foundation model for medical image analysis that integrates pathology and radiology data. This model utilizes federated learning and attention mechanisms to handle multidime…
-
AI system TumorBoard enhances neuro-oncology decision support
Researchers have developed TumorBoard, a novel multi-agent decision support system designed for longitudinal neuro-oncology care. This system integrates various specialist agents, including radiology, neuropathology, an…
-
New agent architecture improves longitudinal personal health management
Researchers have developed HealthClaw, an open-source agent architecture designed for longitudinal personal health management. Unlike existing systems that treat each request in isolation, HealthClaw updates its support…
-
New radiology foundation models show promise, but evaluation and translation challenges remain · 4 sources tracked
Two new technical reports detail advancements in radiology foundation models. One review paper analyzes 67 studies on vision foundation models (VFMs) in radiology, highlighting the prevalence of transformer architecture…
-
New CORTEX benchmark aims for trustworthy AI in 3D chest CT analysis
Researchers have introduced CORTEX, a new benchmark designed to improve the trustworthiness of multimodal large language models (MLLMs) in 3D chest CT analysis. Existing datasets often reduce complex radiology reports t…
-
AI models exhibit "Inattentional Gap," missing safety signals when tasked
A new research paper introduces the concept of the "Inattentional Gap," describing how language and vision AI models, when conditioned on specific tasks, suppress their ability to report safety-critical signals they wou…