Research

Evaluating the Accuracy of an Artificial Intelligence Solution for Automated Echocardiographic Measurements

Most echocardiographic categorical findings derive from numerical measurements applied through standardized threshold tables. This study aimed to validate the AI by comparing its underlying numerical inputs to confirm clinical diagnostic agreement across standard structural and functional cardiac parameters.

Comparative Analysis of Visual Language Models for Fracture Detection and Anatomical Recognition in Musculoskeletal X-rays

AI fracture detection tools high performance in research settings is established but their effectiveness after deployment in clinical practice is understudied. Post- deployment analysis offers the opportunity to study the tool before and after on- the-fly modifications to operational parameters based on observed performance “in the wild.”

Comparison of AI Tool Performance Against Human Radiologists in 2D Mammography: A Look into Key Error Categories

To evaluate and compare the performance of an AI tool against human radiologists in detecting cancer on 2D mammography, focusing on key error categories such as false positives (FP) and false negatives (FN) using a curated dataset.

Performance and Adjustment of an AI-Assisted Fracture Detection Tool in a Real-World Post-Clinical Deployment Setting

AI fracture detection tools' high performance in research settings is established, but their effectiveness after deployment in clinical practice is understudied. Post-deployment analysis offers the opportunity to study the tool before and after on-the-fly modifications to operational parameters based on observed performance “in the wild.”

Retrospective Comparison of Fracture Detection Performance Before and After Implementation of an AI Fracture Detection Tool

AI tools have been widely implemented in radiology departments, promising improved efficiency, accuracy, and workload management of growing imaging volumes. This study evaluated a fracture detection tool’s effect on emergency worklist prioritization, resident sensitivity, specificity, and concordance of fracture detection.

Clinical validation of a deep learning based automated HUAC analysis for improved sarcopenia assessment

To assess the validity and reliability of an automated sarcopenia estimation approach using a deep-learning based ensemble psoas segmentation and Hounsfield Unit Average Calculation (HUAC) model in comparison to traditional manual measurements.

Age-stratified Assessment of Brain Volumetric Segmentation on the Indian Population Using Quantitative Magnetic Resonance Imaging

Automated methods for quantifying brain tissue volumes have gained clinical interest for their objective assessment of neurological diseases. This study aimed to establish reference curves for brain volumes and fractions in the Indian population using Synthetic MRI (SyMRI), a quantitative imaging technique providing multiple contrast-weighted images through fast postprocessing

Artificial intelligence in healthcare–Crossing the chasm

Crossing the chasm is a seminal book on technology marketing written by Geoffery Moore, which talks about how disruptive technology products and services are sold, and thereby adopted in more traditional industries. As a physician with an MBA building a technology start-up in the artificial intelligence (AI) space.

Style-aware radiology report generation with RadGraph and few-shot prompting

Automatically generated reports from medical images promise to improve the workflow of radiologists. Existing methods consider an image-to-report modeling task by directly generating a fully-fledged report from an image. However, this conflates the content of the report (e.g.

Evaluating progress in automatic chest x-ray radiology report generation

Artificial intelligence (AI) models for automatic generation of narrative radiology reports from images have the potential to enhance efficiency and reduce the workload of radiologists. However, evaluating the correctness of these reports requires metrics that can capture clinically pertinent differences.

Automated prostate multi-regional segmentation in magnetic resonance using fully convolutional neural networks

Automatic MR imaging segmentation of the prostate provides relevant clinical benefits for prostate cancer evaluation such as calculation of automated PSA density and other critical imaging biomarkers. Further, automated T2-weighted image segmentation of central-transition zone (CZ-TZ), peripheral zone (PZ), and seminal vesicle (SV) can help to evaluate clinically significant cancer following the PI-RADS v2.1 guidelines.

Navigating Fairness in Radiology AI: Concepts, Consequences, and Crucial Considerations

Artificial Intelligence (AI) has significantly revolutionized radiology, promising improved patient outcomes and streamlined processes. However, it's critical to ensure the fairness of AI models to prevent stealthy bias and disparities from leading to unequal outcomes.

A semi‐automatic framework based upon quantitative analysis of MR‐images for classification of femur cartilage into asymptomatic, early OA, and advanced‐OA groups

To develop a semi‐automatic framework for quantitative analysis of biochemical properties and thickness of femur cartilage using magnetic resonance (MR) images and evaluate its potential for femur cartilage classification into asymptomatic (AS), early osteoarthritis (OA), and advanced OA groups.

Clinical Explainability Failure (CEF) & Explainability Failure Ratio (EFR)–changing the way we validate classification algorithms

Adoption of Artificial Intelligence (AI) algorithms into the clinical realm will depend on their inherent trustworthiness, which is built not only by robust validation studies but is also deeply linked to the explainability and interpretability of the algorithms.

Estimation of bias of deep learning-based chest X-ray classification algorithm

Estimation Of Bias Of Deep Learning-Based Chest X-Ray Classification Algorithm​ PURPOSE OR LEARNING OBJECTIVE: To evaluate the bias in the diagnostic performance ...

Using Traditional Machine Learning Techniques for Predicting the Best Clinical Outcomes On Improvement In Vas, Mod And Ncos Based Upon Clinical And Imaging Features

Using Traditional Machine Learning Techniques for Predicting the Best Clinical Outcomes On Improvement In Vas, Mod And Ncos Based Upon Clinical And...

Enhanced separation of brain tumors and edema via diffusion tensor distribution imaging: Illustration with lymphoma cases

Enhanced Separation Of Brain Tumors And Edema Via Diffusion Tensor Distribution Imaging: Illustration With Lymphoma Cases PURPOSE OR LEARNING OBJECTIVE: To investigate...

Implementation Of Fast Echo-planar Imaging (EPImix) MRI Sequence For Scan Time Reduction In Critical And Unco-operative Patients

Implementation Of Fast Echo-Planar Imaging (EPImix) MRI Sequence For Scan Time Reduction In Critical And Unco-Operative Patients​ PURPOSE OR LEARNING OBJECTIVE: To...

Why Standardisation Of Pre-Inferencing Image Processing Methods Is Crucial For Deep Learning Algorithms – A Compelling Evidence Based On The Variations In Outputs For Different Inferencing Workflow

Why Standardisation Of Pre-Inferencing Image Processing Methods Is Crucial For Deep Learning Algorithms – A Compelling Evidence Based On The Variations In ...

All True Positives Are Not Truly Positive – Utility Of Explainability Failure Ratio In A High Sensitivity Screening Setting To Compare Incorrect Localizations Among Algorithms

All True Positives Are Not Truly Positive – Utility Of Explainability Failure Ratio In A High Sensitivity Screening Setting To Compare Incorrect...

Move Away HIPAA And GDPR, Here Comes CrypTFlow – Secure AI Inferencing Without Data Sharing

Move Away HIPAA And GDPR, Here Comes CrypTFlow – Secure AI Inferencing Without Data Sharing TEACHING POINTS: Currently, running Artificial Intelligence (AI)...

Clinical Experience Using Novel Multidimensional Diffusion Magnetic Resonance Imaging For Characterization Of Tissue Microstructure In Various Brain Pathologies

Clinical Experience Using Novel Multidimensional Diffusion Magnetic Resonance Imaging For Characterization Of Tissue Microstructure In Various Brain Pathologies TEACHING POINTS: Multidimensional diffusion...

Validation of expert system enhanced deep learning algorithm for automated screening for COVID-Pneumonia on chest X-rays

Validation Of Expert System Enhanced Deep Learning Algorithm For Automated Screening For COVID-Pneumonia On Chest X-Rays...

Artificial intelligence and its contribution to overcome COVID-19

Artificial intelligence (AI) has a great impact on our daily living and makes our lives more efficient and productive. Especially during the coronavirus disease (COVID-19) pandemic, AI has played a key role in response to the global health crisis.

Multi-institution encrypted medical imaging AI validation without data sharing

Adoption of artificial intelligence medical imaging applications is often impeded by barriers between healthcare systems and algorithm developers given that access to both private patient data and commercial model IP is important to perform pre-deployment evaluation.

Method and system for simulating and constructing original medical images from one modality to other modality

The present invention relates to an improved method and system for simulating and constructing original actual Magnetic Resonance Images MRI from first modality of a patient to second modality, wherein the system is configured to receive an input MRI image taken in first modality, pre-process the input MRI image, send the processed image to a Convolutional Neural Network (CNN), and obtain the new constructed MRI images in second modality that are identical at the pixel level to the actual image as captured by the MRI machines.

A novel abnormality annotation database for covid-19 affected frontal lung x-rays

A Novel Abnormality Annotation Database For Covid-19 Affected Frontal Lung X-Rays Abstract Purpose: To advance the usage of CXRs as a viable...

Audit of artificial intelligence algorithms and its impact in relieving shortage of specialist doctors

208The shortage of specialist doctors is one of the major challenges in healthcare delivery in developing countries. Radiologists are one such specialist cohort who play a crucial role in the diagnosis of diseases and the monitoring of disease progression. There is an emerging consensus among global leaders in public health to leverage the potential of artificial intelligence in radiology.

Estimating AI-generated Bias in Radiology Reporting by Measuring the Change in the Kellgren-Lawrence Grades of Knee Arthritis Before and After Knowledge of AI Results—A Multi-reader Retrospective Study

Estimating AI-generated Bias in Radiology Reporting by Measuring the Change in the Kellgren-Lawrence Grades of Knee Arthritis Before and After Knowledge of AI Results - A Multi-reader Retrospective Study

Can AI Help Read Pediatric Chest X-rays? An independent Evaluation on 3,000+ Scans

Can AI Help Read Pediatric Chest X-Rays? An Independent Evaluation On 3,000+ Scans PURPOSE: To evaluate the performance of a commercially available...

Initial Clinical Experiences with EPIMIX Sequence in Multiple Brain Pathologies

Initial Clinical Experiences With EPIMIX Sequence In Multiple Brain Pathologies TEACHING POINTS: A new multi-contrast echo planar imaging sequence called EPIMIX has...

Assessment of Brain Tissue Microstructure by Diffusion Tensor Distribution MRI: An Initial Survey of Various Pathologies

To explore the potential of the novel diffusion tensor distribution (DTD) MRI method for assessment of brain tissue microstructure in terms of nonparametric...

Clinical research with advanced diffusion encoding methods in MRI

This chapter offers a comprehensive summary of applications of advanced diffusion encoding methods in MRI within a narrowly defined area of in vivo human measurements with imaging read-out and voxel-by-voxel data analysis. The list of methods comprises tensor-valued encoding to investigate cell densities,

A What, When and Where Guide on Open Source DICOM viewers for Radiologists.

A What, When And Where Guide On Open Source DICOM Viewers For Radiologists.

HIPAA, GDPR and Best Practice Guidelines for preserving data security and privacy – What Radiologists should know.

HIPAA, GDPR And Best Practice Guidelines For Preserving Data Security And Privacy – What Radiologists Should Know. LEARNING OBJECTIVES: At the end...

Evaluating radiologists’ knowledge of MRI safety – a questionnaire-based survey of practicing radiologists

Evaluating Radiologists’ Knowledge Of MRI Safety – A Questionnaire-Based Survey Of Practicing Radiologists PURPOSE: There is a lot of confusion about whether...

Acceleration of cerebrospinal fluid flow quantification using Compressed-SENSE: A quantitative comparison with standard acceleration techniques

Acceleration Of Cerebrospinal Fluid Flow Quantification Using Compressed-SENSE: A Quantitative Comparison With Standard Acceleration Techniques PURPOSE: CSF quantification study is typically useful...

Establishing Normative Liver Volume and Attenuation for the Population of a Large Developing Country Using Deep Learning – A Retrospective Study of 1,800 CT Scans

Establishing Normative Liver Volume and Attenuation for the Population of a Large Developing Country Using Deep Learning – A Retrospective Study of 1,800 CT Scans

Six must-have features for advanced analytics and visualization platform for validating new-age AI algorithms

Six Must-Have Features For Advanced Analytics And Visualization Platform For Validating New-Age AI Algorithms LEARNING OBJECTIVES: In this exhibit, we discuss the...

Evaluating radiologists’ knowledge of MRI safety–a questionnaire-based survey of practicing radiologists

There is a lot of confusion about whether to scan patients with different types of metal in their bodies, to the extent that patients are often refused MRI scans. In order to assess the scope of the problem and allow targeted designing of educational programs, we conducted a survey on MRI safety amongst radiologists from varying geographies.

DICE Score vs Radiologist – Visual quantification of Virtual Diffusion Sequences – pitfalls of lesion segmentation-based approach as compared to clinical relevance-based qualitative assessment

DICE Score Vs Radiologist – Visual Quantification Of Virtual Diffusion Sequences – Pitfalls Of Lesion Segmentation-Based Approach As Compared To Clinical Relevance-Based...

Automated Vertebral labeling and Quantification of Spondylotic Metrics of MR Lumbar Spine using neural networks-A Retrospective Validation Study on Advanced Analytics Platform.

MRI of the spine is one of the commonest studies performed in clinical practice usually to study the cause of back pain. The reading of spine MR studies involves identifying the vertebral levels, estimating stenosis of the spinal canal,

Modified radial-search algorithm for segmentation of tibiofemoral cartilage in MR images of patients with subchondral lesion

Modified Radial-Search Algorithm For Segmentation Of Tibiofemoral Cartilage In MR Images Of Patients With Subchondral Lesion Abstract Purpose: The quantitative analysis of...

The Algorithmic Audit: Working with Vendors to Validate Radiology-AI Algorithms—How We Do It

There is a plethora of Artificial Intelligence (AI) tools that are being developed around the world aiming at either speeding up or improving the accuracy of radiologists. It is essential for radiologists to work with the developers of such algorithms to determine true clinical utility and risks associated with these algorithms.

DICE Score vs Radiologist-Visual quantification of Virtual Diffusion Sequences–pitfalls of lesion segmentation-based approach as compared to clinical relevance-based

The performances of image segmentation/translation algorithms are typically evaluated by measuring image similarity metrics like DICE score or SSIM. In some instances, this approach may be counter-productive. In this study, we propose to compare such an approach with more clinical relevance focussed qualitative assessment method for estimating the accuracy of a virtually generated diffusion-weighted (DW) sequences using Generative Adversarial Networks (GAN).

Concepts in US Food and Drug Administration regulation of artificial intelligence for medical imaging

Although extensive attention has been focused on the enormous potential of artificial intelligence (AI) technology, a major question remains: how should this fundamentally new technology be regulated? The purpose of this article is to provide an overview of the pathways developed by the U.S. Food and Drug Administration to regulate the incorporation of AI in medical imaging.

Can AI Generate Clinically Appropriate X-Ray Reports? Judging the Accuracy and Clinical Validity of Deep Learning-generated Test Reports as Compared to Reports Generated by Radiologists: A Retrospective Comparative Study

Can AI Generate Clinically Appropriate X-Ray Reports? Judging The Accuracy And Clinical Validity Of Deep Learning-Generated Test Reports As Compared To Reports...

Difference in the Spectrum of Metastatic Disease on 68Ga PSMA PET/CT after Radical Prostatectomy and after Radical Radiotherapy in Patients of Carcinoma Prostate with Biochemical Recurrence

Difference In The Spectrum Of Metastatic Disease On 68Ga PSMA PET/CT After Radical Prostatectomy And After Radical Radiotherapy In Patients Of Carcinoma...

Next Generation Sequencing for the Practicing Radiologist

Next Generation Sequencing For The Practicing Radiologist TEACHING POINTS Next Generation Sequencing (NGS) is a technique of reading the entire genome or...

Circulating Tumor DNA (ctDNA) – A Potential Adjunct to FDG-PET Imaging in Cancer Follow Up

Circulating Tumor DNA (CtDNA) – A Potential Adjunct To FDG-PET Imaging In Cancer Follow Up TEACHING POINTS • With the continuous advances...

Tips and Tricks on Basic Programming Tools for Radiologists to Handle DICOM Data

Tips and Tricks On Basic Programming Tools For Radiologists To Handle DICOM Data TEACHING POINTS • In the era of artificial intelligence,...

Building Robust ML Models Using Federated Learning: The Future of AI Deployment

Building Robust ML Models Using Federated Learning: The Future Of AI Deployment TEACHING POINTS What does Deep Neural Nets learn? Are they...

How to Lie with Statistics: Things To Keep in Mind While Evaluating a Deep Learning Claim

How To Lie With Statistics: Things To Keep In Mind While Evaluating A Deep Learning Claim TEACHING POINTS 1. In today’s age...

Practical Guide for Deployment of AI Solutions in Clinical Environment: How Did We Do It?

Practical Guide For Deployment Of AI Solutions In Clinical Environment: How Did We Do It? TEACHING POINTS • Every AI company developing/validating...

Getting AI Ready for Deployment: Tuning Algorithms to Specific Sites Using a Single Chest X-Ray Image

Getting AI Ready For Deployment: Tuning Algorithms To Specific Sites Using A Single Chest X-Ray Image PURPOSE Lack of generalisation of deep...

Mediastinal Lymph Nodal Staging by 18 F FDG PET CT in Patients with Coexistent Carcinoma Lung and Tuberculosis: A Tertiary Care Centre Experience (RSNA 2019, Sun Dec 01 – 06)

Mediastinal Lymph Nodal Staging By 18 F FDG PET CT In Patients With Coexistent Carcinoma Lung And Tuberculosis: A Tertiary Care Centre...

Making Spine MR Reports More Clinically Appropriate: A Questionnaire-based Survey of Sub-specialty Spine Surgeons

Making Spine MR Reports More Clinically Appropriate: A Questionnaire-Based Survey Of Sub-Specialty Spine Surgeons PURPOSE MR reports have been unchanged for a...

Establishing Normative Kidney Sizes For A Large Developing Country’S Adult Population Using Big Data: A Study Of 30,000 Ultrasound Scans Yields A Potential Gender And Age-Related Difference

Establishing Normative Kidney Sizes For A Large Developing Country's Adult Population Using Big Data: A Study Of 30,000 Ultrasound Scans Yields A...

Deploying Deep Learning for Quality Control: An AI-assisted Review of Chest X-rays Reported as ‘Normal’ in Routine Clinical Practice

Deploying Deep Learning For Quality Control: An AI-Assisted Review Of Chest X-Rays Reported As ‘Normal’ In Routine Clinical Practice PURPOSE Quality control...

Spectrum of Autoimmune Limbic Encephalitis on FDG PET/CT

Spectrum Of Autoimmune Limbic Encephalitis On FDG PET/CT PURPOSE To evaluate the role of FDG PET CT in the diagnosis, treatment response...

Evaluating the Complimentary Role of Pseudo-STIR in Assessment of Hyperintense Marrow Lesions as Compared to T2-STIR

Evaluating The Complimentary Role Of Pseudo-STIR In Assessment Of Hyperintense Marrow Lesions As Compared To T2-STIR PURPOSE T2W weighted images contain inherent...

Automatic delineation of anterior and posterior cruciate ligaments by combining deep learning and deformable atlas based segmentation

Automatic Delineation Of Anterior And Posterior Cruciate Ligaments By Combining Deep Learning And Deformable Atlas Based Segmentation Abstract Quantitative evaluation of bones...

The Secret Seven: Free tools that every'next-gen'practicing radiologist should know!

There are many tools available today free of cost, and freely available, that are user-friendly, require no prior experience of developing software and can enable any radiologist to exponentially improve their performance. The need of such tools stems from the fact that.

Cine Mode MRI in Pre-& Post-Operative Evaluation of Hydrocephalus–Life beyond NPH and aqueduct stenosis

Hydrocephalus is usually defined as ventriculomegaly with sulcal effacement and can be classified as communicating, non-communicating or Normal Pressure Hydrocephalus. Communicating Hydrocephalus is implied if the level of the obstruction is distal to the 4th ventricle while non communicating hydrocephalus is implied if the level of obstruction is cranial to the 4th ventricular outflow.

How much weighting does T1 Weighting deserve?-Tips and tricks for reading T1 sequences in Musculoskeletal MR scans.

Fluid sensitive sequences like FSPD (fat saturated Proton Density) and STIR are given more importance by many readers while interpreting musculoskeletal MRI. T1 weighted sequences are usually ignored as the images are considered as" anatomy weighted".

Stress testing a deep learning algorithm for normal/abnormal classification of chest x-rays on a spectrum-biased abnormal-weighted dataset

To stress test the performance of a deep learning algorithm on a dataset with spectrum bias against normalcy in chestx-ray normal vs. abnormal classifier

Deep learning as triage system for critical findings in head CT scans

Radiologists read scans in the first-in-first-out (FIFO) order or based on the'stat'marker based on clinical indications. This might be suboptimal because scans with critical findings might be on bottom of the work list.

Cloud-based semi-automated liver segmentation: analytical study to compare its speed and accuracy with a semi-automated workstation based software

Living Donor Liver Transplantation (LDLT) is the commonest form of liver transplantation in Asia. While Deceasead Donor Liver Transplantation (DDLT) constitutes more than 90% of liver transplantation in the western world, in India and many other Asian countries, the majority of transplants performed are LDLT.

Cine Mode MRI in Pre- & Post-Operative Evaluation of Hydrocephalus – Life beyond NPH and aqueduct stenosis

Cine Mode MRI In Pre- & Post-Operative Evaluation Of Hydrocephalus – Life Beyond NPH And Aqueduct Stenosis LEARNING OBJECTIVES: 1. To learn...

Automated chest cavity and lung segmentation for temporal tracking of lung pathologies on chest x-ray

Objectively evaluating progression and regression of lung pathologies on frontal Chest X-Ray (CXR) is a challenge. Universally, the temporal evolution of most pathological conditions on chest x-rayis still subjective, whichmight beacceptable for directional prediction butnotreliable for quantification of the change. Here we present a novel Deep Learning (DL) based approach to automatically segment the chest cavity and lungs on a CXR for this purpose.

Towards radiologist-level malignancy detection on chest CT scans: a comparative study of the performance of convolutional neural networks and four thoracic radiologists

The demonstration of a 20% reduction in lung cancer mortality in the USA National Lung Screening Trial (NLST)[1] and the subsequent decision by the US Centers for Medicare and Medicaid Services to provide Medicare coverage for lung cancer screening has paved the way for nationwide lung cancer screening in the USA.

Initial experiences with amide proton transfer imaging: correlation between quantitative MTRasym ratio, rCBV and rCBF values in brain tumours

Amide proton transfer (APT) imaging is a new molecular MRI technique based on chemical exchange saturation transfer mechanism with proposed use as an imaging biomarker in brain tumours.

Automated segmentation of knee cartilage using modified radial approach for OA patients with and without bone abnormality

Automatic Segmentation of articular cartilage is important for the quantitative analysis as well as for 2D or 3D visualization of cartilage. Automatic segmentation of cartilage is quite challenging, particularly for OA patients having Bone Marrow Edema (BME) like lesions. Objective of this study was to develop an automatic segmentation approach which can work well for healthy as well as OA patients with and without BME lesions.

Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study

Non-contrast head CT scan is the current standard for initial imaging of patients with head trauma or stroke symptoms. We aimed to develop and validate a set of deep learning algorithms for automated detection of the following key findings from these scans: intracranial haemorrhage and its types (ie, intraparenchymal, intraventricular, subdural, extradural, and subarachnoid); calvarial fractures; midline shift; and mass effect.

Development and validation of deep learning algorithms for detection of critical findings in head CT scans

To develop and validate a set of deep learning algorithms for automated detection of following key findings from non-contrast head CT scans: intracranial hemorrhage (ICH) and its types, intraparenchymal (IPH), intraventricular (IVH), subdural (SDH), extradural (EDH) and subarachnoid (SAH) hemorrhages, calvarial fractures, midline shift and mass effect.

New Epochs in AI Supervision: Design and Implementation of an Autonomous Radiology AI Monitoring System

With the increasingly widespread adoption of AI in healthcare, maintaining the accuracy and reliability of AI models in clinical practice has become crucial. In this context, we introduce novel methods for monitoring the performance of radiology AI classification models in practice, addressing the challenges of obtaining real-time ground truth for performance monitoring.

AI vs. expert consensus: Evaluating the diagnostic performance of automated fracture detection in real world clinical deployment settings

To evaluate the diagnostic performance of artificial intelligence (AI) solution for fracture detection across various anatomical regions and compare these results with final reports produced by radiologists assisted by AI (expert consensus).

Improving Clinical AI Integration with GSPS: Enhancing Storage and Transfer Efficiency in Radiology Workflows

To evaluate and compare the efficiency of Grayscale Softcopy Presentation State (GSPS) versus Secondary Capture (SC) for storing and visualizing AI outputs in DICOM format, with a focus on storage efficiency, clinical usability, and scalability across modalities.

Clinical Validation of a Commercially available AI Tool for Emergency Intracranial Haemorrhage Detection on NCCT

To evaluate the diagnostic performance of a commercially available AI tool for detecting ICH on non-contrast head CT, using expert radiologist consensus as the reference standard.

Regulation and Ethics in Ensemble AI for Radiology: Balancing Innovation and Responsibility

Ensemble AI systems integrate multiple model outputs to enhance diagnostic performance but introduce novel regulatory and ethical complexities distinct from single-model AI.

Building Trust in Radiology AI: A Framework for Real-World Validation and Oversight

Radiology is under pressure. Imaging volumes are rising, while radiologist shortages persist globally. A 2020 survey by the European Society of Radiology found that 60% of departments reported staff shortages—a reality mirrored in many developing countries. In this context, artificial intelligence (AI) is seen as a key tool to improve diagnostic efficiency and reduce reporting delays.

Artificial Intelligence in Brain CT: Expanding Diagnostic Reach beyond Haemorrhage and Stroke

The purpose of this study was to evaluate the diagnostic performance of a commercially available artificial intelligence (AI) system in detecting brain pathologies on non-contrast head CT scans, using radiologist consensus as the reference standard.

Orchestrating Intelligence: Agentic AI for Scalable, Adaptive, and Efficient Radiology Workflows

The main goal of this work proposes moving beyond isolated, task-specific AI tools in radiology toward a holistic Agentic AI orchestration framework. The contemporary radiology workflow is increasingly characterized by fragmented systems and high cognitive load, where radiologists must manually synthesize data across disconnected EMR, PACS, and reporting interfaces.

Optimizing Intracranial Haemorrhage Detection: Comparative Evaluation of a Commercial AI Triage Tool and a Quantitative Research AI with Ensemble Strategies

Structured Brain CT Reporting with Agentic Large Language Models: Toward Enhanced Clinical Decision Support

Current Artificial Intelligence applications in neuroradiology demonstrate proficiency in detection tasks, such as identifying intracranial hemorrhage, large vessel occlusion, or fractures. These tools primarily function as "triage assistants," optimizing worklist prioritization and decreasing turnaround times.

Processing Free-Text Chest X-ray Reports into Structured Findings Using Agentic Large Language Models

The vast majority of diagnostic data in healthcare resides in unstructured, free-text formats, with radiology reports being a primary example. While these narratives allow radiologists the flexibility to describe complex nuances, this lack of structure creates significant bottlenecks for downstream applications.