Closing the gap in the clinical adoption of computational pathology: a standardized, open-source framework to integrate deep-learning models into the laboratory information system DOI Creative Commons
Miriam Angeloni,

Davide Rizzi,

Simon Schoen

et al.

Genome Medicine, Journal Year: 2025, Volume and Issue: 17(1)

Published: May 26, 2025

Abstract Background Digital pathology (DP) has revolutionized cancer diagnostics and enabled the development of deep-learning (DL) models aimed at supporting pathologists in their daily work improving patient care. However, clinical adoption such remains challenging. Here, we describe a proof-of-concept framework that, leveraging Health Level 7 (HL7) standard open-source DP resources, allows seamless integration both publicly available custom developed DL workflow. Methods Development testing were carried out fully digitized Italian department. A Python-based server-client architecture was implemented to interconnect through HL7 messaging anatomic laboratory information system (AP-LIS) with an external artificial intelligence-based decision support (AI-DSS) containing 16 pre-trained models. Open-source toolboxes for model deployment used run inference, QuPath provide intuitive visualization predictions as colored heatmaps. Results default mode runs continuously background each new slide is digitized, choosing correct model(s) on basis tissue type staining. In addition, can initiate analysis on-demand by selecting specific from virtual tray. cases, AP-LIS transmits message AI-DSS, which processes message, creates appropriate style employed classification model. The AI-DSS inference results AP-LIS, where visualize output and/or directly description Conclusions Taken together, use freely resources offers standardized, portable, solution that lays groundwork future widespread diagnostics.

Language: Английский

The need for balancing ’black box’ systems and explainable artificial intelligence: A necessary implementation in radiology DOI Creative Commons
Fabio De‐Giorgio, Beatrice Benedetti, Matteo Mancino

et al.

European Journal of Radiology, Journal Year: 2025, Volume and Issue: 185, P. 112014 - 112014

Published: Feb. 26, 2025

Language: Английский

Citations

2
AI and Interventional Radiology: A Narrative Review of Reviews on Opportunities, Challenges, and Future Directions DOI Creative Commons
Andrea Lastrucci,

Nicola Iosca,

Yannick Wandael

et al.

Diagnostics, Journal Year: 2025, Volume and Issue: 15(7), P. 893 - 893

Published: April 1, 2025

The integration of artificial intelligence in interventional radiology is an emerging field with transformative potential, aiming to make a great contribution the health domain. This overview reviews seeks identify prevailing themes, opportunities, challenges, and recommendations related process integration. Utilizing standardized checklist quality control procedures, this review examines recent advancements in, future implications of, In total, 27 studies were selected through systematic process. Based on overview, (AI) (IR) presents significant opportunities enhance precision, efficiency, personalization procedures. AI automates tasks like catheter manipulation needle placement, improving accuracy reducing variability. It also integrates multiple imaging modalities, optimizing treatment planning outcomes. aids intra-procedural guidance advanced tracking real-time image fusion. Robotics automation IR are advancing, though full autonomy AI-guided systems has not been achieved. Despite these advancements, complex, involving systems, robotics, other technologies. complexity requires comprehensive certification role regulatory bodies, scientific societies, clinicians essential address challenges. Standardized guidelines, clinician education, careful assessment necessary for safe depends developing guidelines medical devices applications. Collaboration between certifying legislative entities, as seen EU Act, will be crucial tackling AI-specific Focusing transparency, data governance, human oversight, post-market monitoring ensure proceeds safeguards, benefiting patient outcomes advancing field.

Language: Английский

Citations

1
Evolving and Novel Applications of Artificial Intelligence in Cancer Imaging DOI Open Access
Mustaqueem Pallumeera,

Jonathan C. Giang,

Rajanbir Singh

et al.

Cancers, Journal Year: 2025, Volume and Issue: 17(9), P. 1510 - 1510

Published: April 30, 2025

Artificial intelligence (AI) is revolutionizing cancer imaging, enhancing screening, diagnosis, and treatment options for clinicians. AI-driven applications, particularly deep learning machine learning, excel in risk assessment, tumor detection, classification, predictive prognosis. Machine algorithms, especially frameworks, improve lesion characterization automated segmentation, leading to enhanced radiomic feature extraction delineation. Radiomics, which quantifies imaging features, offers personalized response predictions across various modalities. AI models also facilitate technological improvements non-diagnostic tasks, such as image optimization medical reporting. Despite advancements, challenges persist integrating into healthcare, tracking accurate data, ensuring patient privacy. Validation through clinician input multi-institutional studies essential safety model generalizability. This requires support from radiologists worldwide consideration of complex regulatory processes. Future directions include elaborating on existing optimizations, advanced techniques, improving patient-centric medicine, expanding healthcare accessibility. can enhance optimizing precision medicine outcomes. Ongoing multidisciplinary collaboration between radiologists, oncologists, software developers, bodies crucial AI's growing role clinical oncology. review aims provide an overview the applications oncologic while discussing their limitations.

Language: Английский

Citations

0
Systematic review on the impact of deep learning-driven worklist triage on radiology workflow and clinical outcomes DOI

Eshan Momin,

Tessa S. Cook,

Gabrielle Gershon

et al.

European Radiology, Journal Year: 2025, Volume and Issue: unknown

Published: May 21, 2025

Language: Английский

Citations

0
Building trust: improving evidence levels in breast MRI radiomics DOI
Valeria Romeo, Renato Cuocolo

European Radiology, Journal Year: 2025, Volume and Issue: unknown

Published: April 4, 2025

Language: Английский

Citations

0
Education and training satisfaction among radiology residents: Insights from a national survey DOI Creative Commons
Nikolaos‐Achilleas Arkoudis,

Kyriaki Tavernaraki,

Ornella Moschovaki-Zeiger

et al.

European Journal of Radiology, Journal Year: 2025, Volume and Issue: 189, P. 112191 - 112191

Published: May 21, 2025

Language: Английский

Citations

0
Closing the gap in the clinical adoption of computational pathology: a standardized, open-source framework to integrate deep-learning models into the laboratory information system DOI Creative Commons
Miriam Angeloni,

Davide Rizzi,

Simon Schoen

et al.

Genome Medicine, Journal Year: 2025, Volume and Issue: 17(1)

Published: May 26, 2025

Abstract Background Digital pathology (DP) has revolutionized cancer diagnostics and enabled the development of deep-learning (DL) models aimed at supporting pathologists in their daily work improving patient care. However, clinical adoption such remains challenging. Here, we describe a proof-of-concept framework that, leveraging Health Level 7 (HL7) standard open-source DP resources, allows seamless integration both publicly available custom developed DL workflow. Methods Development testing were carried out fully digitized Italian department. A Python-based server-client architecture was implemented to interconnect through HL7 messaging anatomic laboratory information system (AP-LIS) with an external artificial intelligence-based decision support (AI-DSS) containing 16 pre-trained models. Open-source toolboxes for model deployment used run inference, QuPath provide intuitive visualization predictions as colored heatmaps. Results default mode runs continuously background each new slide is digitized, choosing correct model(s) on basis tissue type staining. In addition, can initiate analysis on-demand by selecting specific from virtual tray. cases, AP-LIS transmits message AI-DSS, which processes message, creates appropriate style employed classification model. The AI-DSS inference results AP-LIS, where visualize output and/or directly description Conclusions Taken together, use freely resources offers standardized, portable, solution that lays groundwork future widespread diagnostics.

Language: Английский

Citations

0