Richard D. White

Isolated-Left Ventricular Diastolic Dysfunction [LVDD] ranges (and may progress) from preclinical asymptomatic, symptomatic-LVDD, to LVDD-predominate Heart Failure [HF] presentations; if recognized early, LVDD progression might be preventable. Current early-HF screening remains limited, providing opportunities for insights from a standard Chest X-Ray [CXR]. While CXR assessment for “pulmonary congestion” supports suspected-HF evaluation in evidence-based guidelines, the potential for systematic Pulmonary Venous Hypertension [PVH]-Staging to contribute to initial detection and scaling of LVDD is unclear. This study compared CXR-based PVH-Staging to Doppler Echocardiography [DEcho]-based LVDD-Grading in the absence of systolic dysfunction. Questions included: (1) With PVH-Staging performed by cardiothoracic radiologists, what intra-/inter-reader variabilities remain? (2) Does PVH-Staging track LVDD-Grading? and (3) Can AI-assisted PVH prediction of LVDD-Grade match human performance? CXR examinations of 1,682 (including 750 asymptomatic/healthy) subjects, without: (1) Anatomical/physiological confounders of DEcho or CXR examinations (≤ 24 h apart), and (2) AI model-training confounders, were independently assigned 1 of 11 (9 PVH-related) Pulmonary Vasculature Patterns [PVPs] by 4 cardiothoracic radiologists and repeated for reliability evaluation. Expert-consensus Human Ground Truth [HGT] PVH PVPs were correlated with LVDD Grades (0 to 3–4), as were PVH-Rank predictions by a transformer-based AI model [“PVPI”]. Despite experience-dependent intra-/inter-reader reliability in PVP assignment, there was significant (p < 0.001) overall consistency. With increasing HGT PVH Stage, a significant (p < 0.001) trend towards increasing LVDD Grade was found; while PVH-Staging achieved confidence backing Grade 0/No LVDD, confident LVDD Grade recognition was not achieved until Grades 3–4/Restrictive Filling. However, a significantly (p < 0.001) stronger incrementally positive trend in PVPI PVH-Ranking with LVDD-Grading was demonstrated. Although validated, PVH-Staging for LVDD-Grading is limited by reader variabilities. AI-assisted PVH-Ranking may facilitate earlier and widespread objective CXR screening for LVDD which is ubiquitous in HF.

Artificial intelligence (AI) has become commonplace in solving routine everyday tasks. Because of the exponential growth in medical imaging data volume and complexity, the workload on radiologists is steadily increasing. AI has been shown to improve efficiency in medical image generation, processing, and interpretation, and various such AI models have been developed across research laboratories worldwide. However, very few of these, if any, find their way into routine clinical use, a discrepancy that reflects the divide between AI research and successful AI translation. The goal of this paper is to give an overview of the intersection of AI and medical imaging landscapes. We also want to inform the readers about the importance of using standards in their radiology workflow and the challenges associated with deploying AI models in the clinical workflow. The main focus of this paper is to examine the existing condition of radiology workflow and identify the challenges hindering the implementation of AI in hospital settings. This report reflects extensive weekly discussions and practical problem-solving expertise accumulated over multiple years by industry experts, imaging informatics professionals, research scientists, and clinicians. To gain a deeper understanding of the requirements for deploying AI models, we introduce a taxonomy of AI use cases, supplemented by real-world instances of AI model integration within hospitals. We will also explain how the need for AI integration in radiology can be addressed using the Medical Open Network for AI (MONAI). MONAI is an open-source consortium for providing reproducible deep learning solutions and integration tools for radiology practice in hospitals.

Pharmacogenomic (PGx) biomarkers integrated using machine learning can be embedded within the electronic health record (EHR) to provide clinicians with individualized predictions of drug treatment outcomes. Currently, however, drug alerts in the EHR are largely generic (not patient‐specific) and contribute to increased clinician stress and burnout. Improving the usability of PGx alerts is an urgent need. Therefore, this work aimed to identify principles for optimal PGx alert design through a health‐system‐wide, mixed‐methods study. Clinicians representing multiple practices and care settings (N = 1062) in urban, rural, and underserved regions were invited to complete an electronic survey comparing the usability of three drug alerts for citalopram, as a case study. Alert 1 contained a generic warning of pharmacogenomic effects on citalopram metabolism. Alerts 2 and 3 provided patient‐specific predictions of citalopram efficacy with varying depth of information. Primary outcomes included the System's Usability Scale score (0–100 points) of each alert, the perceived impact of each alert on stress and decision‐making, and clinicians' suggestions for alert improvement. Secondary outcomes included the assessment of alert preference by clinician age, practice type, and geographic setting. Qualitative information was captured to provide context to quantitative information. The final cohort comprised 305 geographically and clinically diverse clinicians. A simplified, individualized alert (Alert 2) was perceived as beneficial for decision‐making and stress compared with a more detailed version (Alert 3) and the generic alert (Alert 1) regardless of age, practice type, or geographic setting. Findings emphasize the need for clinician‐guided design of PGx alerts in the era of digital medicine.

UNSTRUCTURED This paper reviews the challenges hindering the widespread adoption of artificial intelligence (AI) solutions in the healthcare industry, focusing on computer vision applications for medical imaging, and how interoperability and enterprise-grade scalability can be used to address these challenges. The complex nature of healthcare workflows, intricacies in managing large and secure medical imaging data, and the absence of standardized frameworks for AI development pose significant barriers and require a new paradigm to address them. The role of interoperability is examined in this paper as a crucial factor in connecting disparate applications within healthcare workflows. Standards such as DICOM™, Health Level 7 HL7®, and Integrating the Healthcare Enterprise (IHE) are highlighted as foundational for common imaging workflows. A specific focus is placed on the role of DICOM gateways, with Smart Routing Rules and Workflow Management leading transformational efforts in this area. To drive enterprise scalability, new tools are needed. Project MONAI, established in 2019, is introduced as an initiative aiming to redefine the development of medical AI applications. The MONAI Deploy App SDK, a component of Project MONAI, is identified as a key tool in simplifying the packaging and deployment process, enabling repeatable, scalable, and standardized deployment patterns for AI applications. The abstract underscores the potential impact of successful AI adoption in healthcare, offering physicians both life-saving and time-saving insights and driving efficiencies in radiology department workflows. The collaborative efforts between academia and industry, are emphasized as essential for advancing the adoption of healthcare AI solutions.

Mammographic breast density is an early indicator of a patient's risk for breast cancer development. Although the direct cause is not fully understood, increased mammographic breast density increases the chance of developing breast cancer. Based on the density pattern exhibited, a patient's breast density score is assigned by a radiologist using one of four categories outlined by the Breast Imaging Reporting and Data Systems (BI-RADS). The subjective nature of pattern-based assessment of patient breast density can result in increased intra- and inter-rater variability. The identification of objective quantitative scoring systems for breast density lends the opportunity to provide patients and radiologists with increased granularity and precision over the four subjective BI-RADS classes. We propose a quantitative breast-density approach using semantic segmentation to assign each of a patient's breasts with a density value. Using the values for each breast, a patient-level density value can be used to determine the patient's placement on a linear density scale along with the probability that the patient belongs to each of the BI-RADS breast-density classes. We use accuracy and kappa scores to determine the performance of the algorithm with BI-RADS classification. Results show comparative classification and performance can be achieved between our semantic segmentation methodology and previous work which implemented a Vision Transformer (ViT)-based breast-density classification algorithm.

PurposeChest X-ray (CXR) use in pre-MRI safety screening, such as for lead-less implanted electronic device (LLIED) recognition, is common. To assist CXR interpretation, we “pre-deployed” an artificial intelligence (AI) model to assess (1) accuracies in LLIED-type (and consequently safety-level) identification, (2) safety implications of LLIED nondetections or misidentifications, (3) infrastructural or workflow requirements, and (4) demands related to model adaptation to real-world conditions.ApproachA two-tier cascading methodology for LLIED detection/localization and identification on a frontal CXR was applied to evaluate the performance of the original nine-class AI model. With the unexpected early appearance of LLIED types during simulated real-world trialing, retraining of a newer 12-class version preceded retrialing. A zero footprint (ZF) graphical user interface (GUI)/viewer with DICOM-based output was developed for inference-result display and adjudication, supporting end-user engagement and model continuous learning and/or modernization.ResultsDuring model testing or trialing using both the nine-class and 12-class models, robust detection/localization was consistently 100%, with mAP 0.99 from fivefold cross-validation. Safety-level categorization was high during both testing (AUC ≥ 0.98 and ≥0.99, respectively) and trialing (accuracy 98% and 97%, respectively). LLIED-type identifications by the two models during testing (1) were 98.9% and 99.5% overall correct and (2) consistently showed AUC ≥ 0.92 (1.00 for 8/9 and 9/12 LLIED-types, respectively). Pre-deployment trialing of both models demonstrated overall type-identification accuracies of 94.5% and 95%, respectively. Of the small number of misidentifications, none involved MRI-stringently conditional or MRI-unsafe types of LLIEDs. Optimized ZF GUI/viewer operations led to greater user-friendliness for radiologist engagement.ConclusionsOur LLIED-related AI methodology supports (1) 100% detection sensitivity, (2) high identification (including MRI-safety) accuracy, and (3) future model deployment with facilitated inference-result display and adjudication for ongoing model adaptation to future real-world experiences.

Abdominal aortic aneurysm stiffness and stiffness ratio at MR elastography were lower in participants with later aneurysm rupture, repair, or expansion versus participants without such events. Background Abdominal aortic aneurysm (AAA) diameter remains the standard clinical parameter to predict growth and rupture. Studies suggest that using solely AAA diameter for risk stratification is ...

Purpose: Sharing medical images between institutions, or even inside the same institution, is restricted by various laws and regulations; research projects requiring large datasets may suffer as a result. These limitations might be addressed by an abundant supply of synthetic data that (1) are representative (i.e., the synthetic data could produce comparable research results as the original data) and (2) do not closely resemble the original images (i.e., patient privacy is protected). We introduce a framework that generates data with these requirements leveraging generative adversarial network (GAN) ensembles in a controlled fashion. Approach: To this end, an adaptive ensemble scaling strategy with the objective of representativeness is defined. A sampled Fréchet distance-based constraint was then created to eliminate poorly converged candidates. Finally, a mutual information-based validation metric was embedded into the framework to confirm there are visual differences between the original and the generated synthetic images. Results: The applicability of the solution is demonstrated with a case study for generating three-dimensional brain metastasis (BM) from T1-weighted contrast-enhanced MRI studies. A previously published BM detection system was reported to produce 9.12 false-positives at 90% detection sensitivity based on the original data. By using the synthetic data generated with the proposed framework, the system produced 9.53 false-positives at the same sensitivity level. Conclusions: Achieving comparable algorithm performance relying solely on synthetic data unveils a significant potential to eliminate/reduce patient privacy concerns when sharing data in medical imaging.