In this review, we highlight how artificial intelligence, specifically deep learning, is reshaping every aspect of cardiovascular magnetic resonance imaging: from planning and acquisition to reconstruction, analysis, and clinical report generation. We first introduce core machine learning paradigms and concepts, then survey recent deep learning advances to automate and enhance multiple aspects of MRI. We highlight the range of recent advances to provide a conceptual understanding of how the field has rapidly evolved in the last 10 years, enabling improvements in acquisition speed, spatial resolution, suppression of artifacts, and correction for motion. Automation of postprocessing is providing us a deeper look into detailed analysis of regional cardiac function and measurement of hemodynamics, and a greater ability to automatically integrate interpretation with nonimaging clinical data to support prognostication and management. Advances in artificial intelligence will continue to shape our practice of clinical cardiovascular MRI to provide greater efficiency and enrich our ability to guide the management of patients with cardiovascular disease.

In 2021, the US Preventive Services Task Force (USPSTF) revised the guidelines for lung cancer screening (LCS). Numerous studies have examined the effects of the guideline changes on LCS eligibility. Yet, few have focused on their impact on participation and lung cancer outcomes within a clinical LCS cohort.

Accurate lung cancer TNM staging depends on macroscopic and microscopic tumor evaluation of resection specimens. However, small nodules (<1 cm) are difficult to extract and correlate with in vivo imaging. We investigated whether microCT could better localize lesions or guide pathology to otherwise undetected abnormalities.

This study evaluated the diagnostic accuracy and differential diagnostic capabilities of 12 Large Language Models (LLMs), one cardiac radiologist, and 3 general radiologists in cardiac radiology. The impact of the ChatGPT-4o assistance on radiologist performance was also investigated.

To analyze imaging features and pathology of missed and interval lung cancers within an academic lung cancer screening (LCS) program.

This review traces the historical path of artificial intelligence (AI) methods that have been applied to medical image interpretation. Early AI approaches, which were based on clinical expertise and domain-specific medical knowledge, established the basis for data-driven methods, initiating the radiomics era and leading to the widespread use of deep learning in medical imaging. More recently, transformer architectures-originally developed for natural language processing-have been adapted for medical image analysis. In the first section, we explore the literature on the use of AI, specifically addressing lung nodules and lung cancer. AI has been effective in detecting lung nodules, evaluating their characteristics, and predicting cancer risk, while also addressing technical issues like kernel conversion. In lung cancer, AI has been applied to various clinical needs, including prognosis evaluation, mutation identification, treatment response analysis, operability prediction, treatment-related pneumonitis, and clinical information extraction. In the following section, we explore foundation models, multimodal AI, and a multiomic approach in the field of lung nodules and lung cancer. Finally, as AI models continue to evolve, so too must the approaches for evaluating their real-world utility; thus, we outline relevant methods for evaluating the performance and application of AI in thoracic radiology.

To establish an explainable machine learning (ML) approach using patient-related and noncontrast chest CT-derived features to predict the contrast material arrival time ( TARR ) in CT pulmonary angiography (CTPA).

Measurement of mediastinal lymph nodes (LNs) is an integral part of patient assessment, and is performed by manually measuring the short axis length (SAL) of the LNs on axial slices. LNs with SAL ≥10 mm are considered pathologically enlarged. We aimed to quantify the interobserver agreement and variability of SAL measurements, compare them to automatically computed SALs from manual LN delineations, and establish the mean SAL measurement error.

To evaluate the role of chest CT radiomics in classifying mediastinal lymphadenopathy caused by hematologic malignancies and abdominopelvic solid cancers.

Patients with connective tissue diseases (CTDs) and pulmonary arterial hypertension (PAH) have a poor prognosis, and there is a lack of effective noninvasive prognostic tools. This study aimed to retrospectively analyze clinical data and multislice computed tomography (MSCT) chest CT parameters in CTD-PAH patients, and to develop a noninvasive prognostic model incorporating indicators.

The aim of this study was to evaluate T1 and T2 values and to investigate their association with left ventricular (LV) hypertrophy and strains in hypertrophic cardiomyopathy (HCM) without late gadolinium enhancement (LGE).

Cardiac imaging is an integral part of modern diagnostic imaging and a subject heavily tested on the Radiology Core exam. Therefore, radiology residency programs should provide adequate training in this area. This study aims to investigate the current state of cardiac imaging training within radiology residency programs in the United States.

To investigate imaging phenotypes in posthospitalized COVID-19 patients by integrating quantitative CT (QCT) and machine learning (ML), with a focus on small airway disease (SAD) and its correlation with plethysmography.

Primary pulmonary vein stenosis (PPVS) in adults is rare and often incidentally detected on imaging. A 60-year-old man underwent chest CT for respiratory symptoms, revealing a localized reticulonodular opacity in the right upper lung field near the pulmonary hilum. Coronal and sagittal reconstructions demonstrated tortuous collateral veins bridging the right superior and inferior pulmonary veins. Mediastinal-window images confirmed severe stenosis of the proximal right superior pulmonary vein without evidence of external compression or congenital anomaly. As symptoms resolved spontaneously, conservative management was chosen. This case demonstrates that axial reticulonodular opacities can raise suspicion of PPVS, with multiplanar and mediastinal-window imaging enabling accurate diagnosis of this rare condition.

To develop and validate a nomogram to predict hemoptysis after percutaneous transthoracic needle biopsy (PTNB) by integrating clinical and radiologic data, facilitating pre-biopsy decision-making.

The integration of artificial intelligence (AI) with low-dose computed tomography (LDCT) has the potential to transform lung cancer screening into a comprehensive approach to early detection of multiple diseases. Building on over 3 decades of research and global implementation by the International Early Lung Cancer Action Program (I-ELCAP), this paper reviews the development and clinical integration of AI for interpreting LDCT scans. We describe the historical milestones in AI-assisted lung nodule detection, emphysema quantification, and cardiovascular risk assessment using visual and quantitative imaging features. We also discuss challenges related to image acquisition variability, ground truth curation, and clinical integration, with a particular focus on the design and implementation of the open-source IELCAP-AIRS system and the ScreeningPLUS infrastructure, which enable AI training, validation, and deployment in real-world screening environments. AI algorithms for rule-out decisions, nodule tracking, and disease quantification have the potential to reduce radiologist workload and advance precision screening. With the ability to evaluate multiple diseases from a single LDCT scan, AI-enabled screening offers a powerful, scalable tool for improving population health. Ongoing collaboration, standardized protocols, and large annotated datasets are critical to advancing the future of integrated, AI-driven preventive care.

While the primary goal of lung cancer screening CT is to detect early-stage lung cancer in high-risk populations, it often reveals asymptomatic cardiovascular abnormalities that can be clinically significant. These findings include coronary artery calcifications (CACs), myocardial pathologies, cardiac chamber enlargement, valvular lesions, and vascular disease. CAC, a marker of subclinical atherosclerosis, is particularly emphasized due to its strong predictive value for cardiovascular events and mortality. Guidelines recommend qualitative or quantitative CAC scoring on all noncontrast chest CTs. Other actionable findings include aortic aneurysms, pericardial disease, and myocardial pathology, some of which may indicate past or impending cardiac events. This article explores the wide range of incidental cardiovascular findings detectable during low-dose CT (LDCT) scans for lung cancer screening, as well as noncontrast chest CT scans. Distinguishing which findings warrant further evaluation is essential to avoid overdiagnosis, unnecessary anxiety, and resource misuse. The article advocates for a structured approach to follow-up based on the clinical significance of each finding and the patient's overall risk profile. It also notes the rising role of artificial intelligence in automatically detecting and quantifying these abnormalities, potentiating early behavioral modification or medical and surgical interventions. Ultimately, this piece highlights the opportunity to reframe LDCT as a comprehensive cardiothoracic screening tool.

Lung cancer screening (LCS) with low-dose computed tomography (LDCT) has been shown to detect lung cancer at an earlier stage and to reduce mortality among high-risk populations, as demonstrated by major trials including I-ELCAP, NLST, and NELSON. These findings have led to the implementation of national screening programs worldwide. This article outlines the critical components required for the successful implementation of high-quality LCS programs, with a particular focus on quality assurance (QA) mechanisms and radiologist training. Structured radiologist training is essential to ensure the accuracy and effectiveness of LDCT screening. As these requirements are universal, online initiatives such as the I-ELCAP Teaching File, ESTI Lung Cancer Certification Project, and the UK's PERFECTS EQA platform provide scalable models for enhancing radiologic performance in LCS. The success of lung cancer screening programs depends not only on access and infrastructure but also on rigorous training and quality oversight. International collaboration and the adoption of validated educational and QA tools are key to optimizing outcomes and maintaining diagnostic excellence in LDCT-based screening.

Lung cancer in never-smokers (LCINS) presents a distinct epidemiological profile in Asia, with a higher proportion of cases occurring in never-smoking women. This review examines the evidence for lung cancer screening in this population, synthesizing data on risk factors, LDCT screening, and current guidelines across Asian countries. Challenges such as overdiagnosis and economic limitations to screening implementation are discussed, and future research directions, including risk prediction and tailored screening, are highlighted.

Chest radiographic (CXR) screening is currently not recommended in the United States by any major guideline organization. Multiple randomized controlled trials done in the United States and also in Europe, with the largest being the Prostate, Lung, Colorectal and Ovarian (PLCO) trial, all failed to show a benefit and are used as evidence to support the current recommendation. Nevertheless, there is renewed interest in CXR screening, especially in low- and middle-resourced countries around the world. Reasons for this are multi-factorial, including the continued concern that those trials still may have missed a benefit, but perhaps more importantly, it is now established conclusively that finding smaller cancers is better than finding larger ones. This was the key finding in those large randomized controlled trials for CT screening. So, while CT finds cancers smaller than CXR, both clearly perform better than waiting for cancers to be larger and detected by symptom prompting. Without it being well understood that treating cancers found in the asymptomatic state by CXR, there would also be no basis for treating them when found incidentally. In addition, advances in artificial intelligence are allowing for nodules to be found earlier and more reliably with CXR than in those prior studies, and in many countries around the world, TB screening is already taking place on a large scale. This presents a major opportunity for integration with lung screening programs.