Differentiating HER2-Zero, -Low, and -Positive Breast Cancers Using Multiparametric MRI Radiomics With Machine Learning
Release Date: 12/16/2024
Creativity in Education: AJR Podcast Series on Training and Education, Episode 10
AJR Podcasts
In this episode of the AJR Podcast Series on Training and Education, Omer Awan, MD, joins host Monica Cheng, MD, in a conversation that delves into the role of creativity in education, sharing innovative teaching methods and technologic advancements that are shaping our learning and educational practices.
info_outline
Resident Wellness: AJR Podcast Series on Wellness, Episode 12
AJR Podcasts
In this episode of the AJR Podcast Series on Wellness, Sherry Wang, MBBS, and Jessica T. Wen, MD, PhD, discuss the current state of radiology resident wellness, along with challenges and potential opportunities.
info_outline
White Matter Hyperintensities: Biomarker or Incidental Finding? A Radiology Trainee’s Perspective on Imaging of Mild Traumatic Brain Injury
AJR Podcasts
Full article: Pranjal Rai, MBBS, discusses the AJR article by Tanwar et al., reporting a prospective multicenter study evaluating the potential role of white matter hyperintensities as a biomarker of mild traumatic brain injury.
info_outline
Sustainability in Radiology: Global Perspectives on Greener Healthcare—AJR Podcast Series on Sustainability, Episode 5
AJR Podcasts
In this episode of the AJR Podcast Series on Sustainability, Sean Woolen, MD, MS, speaks with Christopher Hess, MD, PhD, Elmar Merkle, MD, and Charles Goh, MBBS, about global perspectives on sustainability in radiology. They explore regional challenges, innovative solutions, and collaborative strategies to drive environmentally responsible radiology practices worldwide.
info_outline
Use of Large Language Models to Facilitate Adherence to Imaging Recommendations
AJR Podcasts
Full article: Morgan McLuckey, MD, discusses the AJR article by Li et al. exploring the use of large language models for extracting details related to recommendations for additional imaging from radiology reports.
info_outline
Follow-up Recommendations: AJR Podcast Series on Diagnostic Excellence and Error, Episode 9
AJR Podcasts
In this episode of the AJR Podcast Series on Diagnostic Excellence and Error, Francis Deng, MD and Neena Kapoor, MD discuss challenges in follow-up imaging recommendations, including low adherence and reporting variability. They emphasize system-based solutions like tracking tools and safety net teams to ensure necessary follow-up and reduce errors.
info_outline
Bosniak 2019 Classification of Cystic Renal Masses: A Meta-Analysis With Implications for Future Investigation
AJR Podcasts
Full article: Aric Berning, MD, discusses the AJR article by McGrath et al. that provides a meta-analysis of malignancy proportions for Bosniak classification version 2019, stratified by class and subclass.
info_outline
Abdominal CT Body Composition Measures and Systemic Disease: The Need for Normative Reference Ranges
AJR Podcasts
Full article: Bardia Nadim, MD, discusses the article by Pooler et al., exploring associations of CT body composition measurements, derived using automated artificial intelligence tools, with common systemic diseases.
info_outline
Innovation: AJR Podcast Series on Training and Education, Episode 9
AJR Podcasts
In this episode of the AJR Podcast Series on Training and Education, Marc Succi, MD, joins host Monica Cheng, MD, to discuss insights in healthcare innovation, from founding MESH Incubator at Mass General Brigham to exploring how leadership and education can foster innovation in radiology to meaningfully impact patient care.
info_outline
Using Machine Learning Models to Detect Cervical Spine Fractures Missed by Radiologists
AJR Podcasts
Full article: Shailin Thomas, MD, discusses the AJR article by Chen et al. exploring the use of award-winning machine-learning models to detect cervical spine fractures missed by radiologists.
info_outlineAishwariya S Vegunta, MBBS, discusses the AJR article by Chen et al. that explores the use of MRI radiomics with machine learning for differentiating among three-tiered HER2 expression statuses of breast cancer, with a focus on interpretability analysis.