After decades of strong federal support for scientific research, the US government is now proposing deep cuts. Here’s what that investment made possible in modern medicine. Medscape Medical News
We scan the top radiology sources so you don’t have to.
From AI breakthroughs to imaging trends, we serve up real-time radiology insights.
-
Ultrasound screening for vasa previa tied to better pregnancy outcomes
Screening for vasa previa with ultrasound leads to higher survival rates among prenatally diagnosed cases in pregnancy.
-
AI could be cost-effective for osteoporosis screening
A study highlights the public health potential of AI-driven osteoporosis screening to improve early detection.
-
Generative AI improves clinical decision-making in the ED
Study results suggest that AI could reduce variability among emergency department (ED) physicians when it comes to ordering imaging…
-
Sexual Health Is Overlooked in Breast Cancer Survivors
Nearly 90% survivors of breast cancer report sexual health problems, including reduced libido and vaginal dryness, highlighting the need for better care post-treatment. Medscape Medical News
-
Clinical value of CT enterography imaging features in predicting enteroscopy passage in Crohn’s disease
Small bowel strictures in Crohn’s disease (CD) can hinder enteroscopy, limiting its diagnostic utility. This study aimed to evaluate whether CT enterography (CTE) imaging features can predict enteroscopy passage in CD patients.
-
Contrast-Enhanced Mammography: Bridging the research gaps and defining the future
In the last two decades new breast imaging techniques have been developed, in an attempt to overcome magnetic resonance imaging (MRI) limitations, such as high cost and patchy access, among others.
-
Auto-METRICS: LLM-assisted scientific quality control for radiomics research
Machine-learning (ML) studies can inflate their conclusions due to methodological biases or errors [1]. Coupled with fast-paced innovation in the world of artificial intelligence (AI), this can lead to excessive confidence in the capacities of AI and ML [2]. This is the case in clinical AI: Maleki et al. showed how three major methodological pitfalls (violation of the independence assumption, model evaluation with inappropriate metrics or baselines, and batch effect) led to unrealistic performan…
-
Development and validation of interpretable machine learning model for pre-treatment predicting the response to targeted and immune therapy in hepatocellular carcinoma
Hepatocellular carcinoma (HCC) accounts for 75 %-85 % of primary liver malignancies and ranks as the sixth most common and the third highest mortality malignancy worldwide, persisting as a major global health burden, notably in China [1]. Due to its insidious onset, approximately 70 % of HCC patients are diagnosed at middle to advanced stages, missing the chance for surgical resection [2]. While trans-arterial chemoembolization (TACE) remains the first-line therapy for intermediate-stage HCC [3]…
-
FDA Approves Drug for Aggressive Glioma
Jazz Pharmaceuticals bet $1 billion on the commercial potential of a first-in-class oral imipridone for recurrent H3 K27M-mutant diffuse glioma. Medscape Medical News