Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Radiological Investigation I: X-ray and CT01:30

Radiological Investigation I: X-ray and CT

910
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
910
Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

8.8K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
8.8K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

National Mortality Trends Associated with Anomalous Aortic Origin of Coronary Artery in the United States: A CDC WONDER Database Analysis.

Cardiology in review·2026
Same author

Vendor-independent Aortic Valve Calcium Scoring in Patients with Discordant Echocardiographic Criteria of Severe Aortic Stenosis.

Radiology. Cardiothoracic imaging·2026
Same author

Evaluation of anemia in non-enhanced and contrast-enhanced dual-energy CT using electron density imaging.

PloS one·2026
Same author

Where Your Eyes Go: How AI Output Design Impacts Reading Behavior.

Journal of imaging informatics in medicine·2026
Same author

Integrating large language models into radiological practice.

European journal of radiology·2026
Same author

Drug-coated balloon versus drug-eluting stent for isolated ostial side-branch bifurcation (Medina 0.0.1) lesions.

International journal of cardiology·2026

Related Experiment Video

Updated: Dec 12, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.2K

Artificial Intelligence and Machine Learning in Radiology: Current State and Considerations for Routine Clinical

Julian L Wichmann, Martin J Willemink1, Carlo N De Cecco2

  • 1Department of Radiology, Stanford University School of Medicine, Stanford, CA.

Investigative Radiology
|August 11, 2020
PubMed
Summary

This review examines why advanced computer algorithms are not yet widely used in daily hospital imaging practice despite rapid technological growth. It highlights the importance of high-quality data, regulatory hurdles, and the need for doctors to guide these new digital tools.

Keywords:
medical imagingdiagnostic algorithmsclinical workflowdigital health

Frequently Asked Questions

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

631

Related Experiment Videos

Last Updated: Dec 12, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.2K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

631

Area of Science:

  • Medical imaging informatics and artificial intelligence research within radiology
  • Clinical workflow optimization and digital health systems

Background:

No prior work had resolved why advanced computational tools remain largely absent from daily diagnostic practice. It was already known that automated image analysis has been a long-standing academic pursuit. That uncertainty drove interest in how recent software breakthroughs might transform medical diagnostics. Prior research has shown that diverse entities, including established corporations and new ventures, are fueling this rapid progress. This gap motivated a closer look at the disconnect between research success and actual hospital integration. Experts have noted that the profession faces continuous evolution rather than replacement by automated systems. The current landscape involves complex interactions between technology developers and medical practitioners. This context highlights the necessity of understanding the barriers preventing widespread adoption of these sophisticated diagnostic aids.

Purpose Of The Study:

The aim of this review is to describe the relevance of imaging data as a bottleneck for innovation in medical diagnostics. The authors seek to provide insights into the numerous obstacles hindering technical implementation in hospitals. This work intends to offer new perspectives to clinicians who often view these tools solely through their professional role. The study addresses the gap between rapid research advancements and the slow pace of routine clinical adoption. It explores the influence of various stakeholders, including startups and device vendors, on the evolution of the field. The researchers aim to clarify the regulatory challenges that currently complicate the deployment of new medical devices. This article seeks to empower specialists to act as gatekeepers during this technological transition. The motivation is to ensure that these advancements effectively improve clinical workflows and patient outcomes.

Main Methods:

Review approach involved a comprehensive synthesis of current trends in medical software development. The authors examined the contributions of academic institutions, established medical device manufacturers, and emerging startup companies. This methodology focused on identifying the structural barriers that prevent laboratory-tested models from entering hospital environments. The investigation analyzed the regulatory landscape governing the approval of new diagnostic medical devices. The authors evaluated the influence of venture capital on the speed and direction of technological progress. This approach included a critical assessment of how imaging data is collected, curated, and utilized for training. The study synthesized perspectives from various stakeholders to understand conflicting priorities in the healthcare sector. The review approach prioritized the practical challenges faced by clinicians when integrating these tools into their daily routines.

Main Results:

Key findings from the literature indicate that routine clinical application of these advanced algorithms remains rare as of 2020. The authors report that innovation is currently driven by a mix of academia, global vendors, and venture-backed startups. The review identifies that the scarcity of appropriate imaging data acts as a primary bottleneck for sustained progress. Evidence suggests that regulatory approval processes are currently undergoing intense public debate and scrutiny. The researchers observe that radiologists are uniquely positioned to lead the integration of these technologies to improve patient outcomes. The analysis reveals that the profession has not been replaced, despite previous predictions of its decline. The findings highlight that stakeholders often hold conflicting interests regarding the deployment of new diagnostic software. The literature confirms that the transition from research to clinical practice is hindered by complex technical and institutional obstacles.

Conclusions:

The authors suggest that medical specialists must act as primary stewards for the integration of new diagnostic software. Synthesis and implications indicate that navigating diverse stakeholder interests is a requirement for successful deployment. The researchers propose that clinicians should actively shape the evolution of their field to ensure patient safety. Evidence suggests that the current regulatory environment remains a significant factor in the slow pace of adoption. The review highlights that imaging professionals must balance technological enthusiasm with practical clinical requirements. Authors emphasize that the path forward involves addressing the specific bottlenecks identified in data management. The analysis implies that the future of the profession depends on proactive engagement with emerging digital tools. The findings underscore that radiologists are uniquely positioned to bridge the gap between technical innovation and patient care.

The researchers propose that the primary obstacle is the scarcity of high-quality, standardized imaging data. While academic models often succeed in controlled environments, they frequently struggle when applied to the diverse, real-world datasets encountered in routine hospital settings.

The authors identify imaging data as the most significant bottleneck. Unlike traditional software, these tools require massive, curated datasets to learn effectively, making data quality and accessibility more important than the underlying code architecture itself.

The authors argue that clinical oversight is necessary because automated systems often lack the contextual awareness that doctors possess. Without this gatekeeping, there is a risk of misinterpretation when algorithms encounter edge cases or data variations not represented in their training sets.

The researchers characterize data as the foundation for algorithm development. Its role involves training, validating, and testing models to ensure they perform reliably across different patient populations and hardware configurations, rather than just serving as a passive input.

The authors measure success by the transition from research prototypes to routine clinical use. They observe that while innovation is high, the phenomenon of widespread deployment remains rare, indicating a significant gap between laboratory performance and practical utility.

The researchers propose that radiologists must become the primary gatekeepers of this evolution. They suggest that by managing stakeholder interests and regulatory compliance, these specialists can ensure that new technology improves clinical workflows rather than disrupting them.