Applications of deep learning to reduce the need for iodinated contrast media for CT imaging: a systematic review

Azarfar, Ghazal; Ko, Seok‐Bum; Adams, Scott; Babyn, Paul

doi:10.1007/s11548-023-02862-w

Cited by 6 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, deep learning models have the capability to produce synthetic contrast-enhanced CT images using non-contrast or low-dose ICM administration, or generate unenhanced CT images from contrast-enhanced CT scans. Nevertheless, it remains uncertain whether unenhanced CT scans consistently provide enough information to distinguish between hyper-enhancing, hypo-enhancing, and non-enhancing regions in all diagnostic scenarios; so, additional efforts are required to improve protocols aimed at minimizing or eliminating the use of ICM for specific medical conditions and to evaluate the clinical usefulness of these synthetic images ( 44 ). Few studies have directly evaluated the validity of artificial intelligence in assigning a RADS in CT. For instance, in the case of LI-RADS, both deep learning and radiomics have shown excellent performance in classifying liver nodules ( 45 ).…”

Section: Discussionmentioning

confidence: 99%

The role of iodinated contrast media in computed tomography structured Reporting and Data Systems (RADS): a narrative review

Parillo,

van der Molen,

Asbach

et al. 2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background and Objective In recent years, there has been a large-scale dissemination of guidelines in radiology in the form of Reporting & Data Systems (RADS). The use of iodinated contrast media (ICM) has a fundamental role in enhancing the diagnostic capabilities of computed tomography (CT) but poses certain risks. The scope of the present review is to summarize the current role of ICM only in clinical reporting guidelines for CT that have adopted the “RADS” approach, focusing on three specific questions per each RADS: (I) what is the scope of the scoring system; (II) how is ICM used in the scoring system; (III) what is the impact of ICM enhancement on the scoring. Methods We analyzed the original articles for each of the latest versions of RADS that can be used in CT [PubMed articles between January, 2005 and March, 2023 in English and American College of Radiology (ACR) official website]. Key Content and Findings We found 14 RADS suitable for use in CT out of 28 RADS described in the literature. Four RADS were validated by the ACR: Colonography-RADS (C-RADS), Liver Imaging-RADS (LI-RADS), Lung CT Screening-RADS (Lung-RADS), and Neck Imaging-RADS (NI-RADS). One RADS was validated by the ACR in collaboration with other cardiovascular scientific societies: Coronary Artery Disease-RADS 2.0 (CAD-RADS). Nine RADS were proposed by other scientific groups: Bone Tumor Imaging-RADS (BTI-RADS), Bone‑RADS, Coronary Artery Calcium Data & Reporting System (CAC-DRS), Coronavirus Disease 2019 Imaging-RADS (COVID-RADS), COVID-19-RADS (CO-RADS), Interstitial Lung Fibrosis Imaging-RADS (ILF-RADS), Lung-RADS (LU-RADS), Node-RADS, and Viral Pneumonia Imaging-RADS (VP-RADS). Conclusions This overview suggests that ICM is not strictly necessary for the study of bones and calcifications (CAC-DRS, BTI-RADS, Bone-RADS), lung parenchyma (Lung-RADS, LU-RADS, COVID-RADS, CO-RADS, VP-RADS and ILF-RADS), and in CT colonography (C-RADS). On the other hand, ICM plays a key role in CT angiography (CAD-RADS), in the study of liver parenchyma (LI-RADS), and in the evaluation of soft tissues and lymph nodes (NI-RADS, Node-RADS). Future studies are needed in order to evaluate the impact of the new iodinated and non-iodinate contrast media, artificial intelligence tools and dual energy CT in the assignment of RADS scores.

show abstract

Section: Discussionmentioning

confidence: 99%

The role of iodinated contrast media in computed tomography structured Reporting and Data Systems (RADS): a narrative review

Parillo,

van der Molen,

Asbach

et al. 2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

show abstract

“…Therefore, preclinical and clinical studies are necessary to answer this question. Possibly, artificial intelligence (AI) could also offer a solution [ 55 ].…”

Section: Discussionmentioning

confidence: 99%

Shortage of iodinated contrast media: Status and possible chances – A systematic review

Koeppel¹,

Boehm²

2023

European Journal of Radiology

View full text Add to dashboard Cite

“…Recently, the field of non-contrast CMR examinations emerged through the support of AI models, with promising results. Several papers have reviewed the role of AI in CMR [ 13 , 14 , 15 , 20 ], or discussed the application of AI in reducing or eliminating contrast media administration in computed tomography, or in other organs beyond the heart [ 21 , 22 , 23 , 24 , 25 ]. However, to the best of our knowledge, none of the previous works have specifically focused on non-contrast AI models in CMR.…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence Applications in Cardiovascular Magnetic Resonance Imaging: Are We on the Path to Avoiding the Administration of Contrast Media?

Cau

Pisu

Suri³

et al. 2023

Diagnostics

View full text Add to dashboard Cite

In recent years, cardiovascular imaging examinations have experienced exponential growth due to technological innovation, and this trend is consistent with the most recent chest pain guidelines. Contrast media have a crucial role in cardiovascular magnetic resonance (CMR) imaging, allowing for more precise characterization of different cardiovascular diseases. However, contrast media have contraindications and side effects that limit their clinical application in determinant patients. The application of artificial intelligence (AI)-based techniques to CMR imaging has led to the development of non-contrast models. These AI models utilize non-contrast imaging data, either independently or in combination with clinical and demographic data, as input to generate diagnostic or prognostic algorithms. In this review, we provide an overview of the main concepts pertaining to AI, review the existing literature on non-contrast AI models in CMR, and finally, discuss the strengths and limitations of these AI models and their possible future development.

show abstract

Applications of deep learning to reduce the need for iodinated contrast media for CT imaging: a systematic review

Cited by 6 publications

References 42 publications

The role of iodinated contrast media in computed tomography structured Reporting and Data Systems (RADS): a narrative review

The role of iodinated contrast media in computed tomography structured Reporting and Data Systems (RADS): a narrative review

Shortage of iodinated contrast media: Status and possible chances – A systematic review

Artificial Intelligence Applications in Cardiovascular Magnetic Resonance Imaging: Are We on the Path to Avoiding the Administration of Contrast Media?

Contact Info

Product

Resources

About