Challenges and solutions for introducing artificial intelligence (AI) in daily clinical workflow

Kotter, Elmar; Ranschaert, Erik

doi:10.1007/s00330-020-07148-2

Cited by 49 publications

(32 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the enthusiasm about AI-based tools there are some barriers to be addressed when implementing this new technology in clinical practice. These include the large amount of annotated image data required for supervised learning as well as validation and quality assurance for each use case scenario of these algorithms, and, last but not least, regulatory aspects including certification [ 5 , 6 ]. A recent overview of commercially available CE-marked AI products for radiological use found that scientific evidence of potential efficacy of level 3 or higher was documented in only 18 of 100 products from 54 vendors and that for most of these products evidence of clinical impact was lacking [ 3 ].…”

Section: Discussionmentioning

confidence: 99%

Current practical experience with artificial intelligence in clinical radiology: a survey of the European Society of Radiology

Becker¹,

Kotter²,

Fournier³

et al. 2022

Insights Imaging

Self Cite

View full text Add to dashboard Cite

A survey among the members of European Society of Radiology (ESR) was conducted regarding the current practical clinical experience of radiologists with Artificial Intelligence (AI)-powered tools. 690 radiologists completed the survey. Among these were 276 radiologists from 229 institutions in 32 countries who had practical clinical experience with an AI-based algorithm and formed the basis of this study. The respondents with clinical AI experience included 143 radiologists (52%) from academic institutions, 102 radiologists (37%) from regional hospitals, and 31 radiologists (11%) from private practice. The use case scenarios of the AI algorithm were mainly related to diagnostic interpretation, image post-processing, and prioritisation of workflow. Technical difficulties with integration of AI-based tools into the workflow were experienced by only 49 respondents (17.8%). Of 185 radiologists who used AI-based algorithms for diagnostic purposes, 140 (75.7%) considered the results of the algorithms generally reliable. The use of a diagnostic algorithm was mentioned in the report by 64 respondents (34.6%) and disclosed to patients by 32 (17.3%). Only 42 (22.7%) experienced a significant reduction of their workload, whereas 129 (69.8%) found that there was no such effect. Of 111 respondents who used AI-based algorithms for clinical workflow prioritisation, 26 (23.4%) considered algorithms to be very helpful for reducing the workload of the medical staff whereas the others found them only moderately helpful (62.2%) or not helpful at all (14.4%). Only 92 (13.3%) of the total 690 respondents indicated that they had intentions to acquire AI tools. In summary, although the assistance of AI algorithms was found to be reliable for different use case scenarios, the majority of radiologists experienced no reduction of practical clinical workload.

show abstract

Section: Discussionmentioning

confidence: 99%

Current practical experience with artificial intelligence in clinical radiology: a survey of the European Society of Radiology

Becker¹,

Kotter²,

Fournier³

et al. 2022

Insights Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…Currently, most DL models are not fully automated diagnosis systems; rather, they are adjunct tools that aid radiologists in reading prostate mpMRI results. Kotter et al ( 32 ) determined that new DL technology would not threaten a radiologist's career but rather help strengthen his or her diagnostic ability. In summary, our proposed DL model can improve PCa diagnostic performance for both senior and junior radiologists, indicating that DL assistance can potentially improve the clinical workflow.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning in Prostate Cancer Diagnosis Using Multiparametric Magnetic Resonance Imaging With Whole-Mount Histopathology Referenced Delineations

Han

Gao

et al. 2022

Front. Med.

View full text Add to dashboard Cite

Background: Multiparametric magnetic resonance imaging (mpMRI) plays an important role in the diagnosis of prostate cancer (PCa) in the current clinical setting. However, the performance of mpMRI usually varies based on the experience of the radiologists at different levels; thus, the demand for MRI interpretation warrants further analysis. In this study, we developed a deep learning (DL) model to improve PCa diagnostic ability using mpMRI and whole-mount histopathology data.Methods: A total of 739 patients, including 466 with PCa and 273 without PCa, were enrolled from January 2017 to December 2019. The mpMRI (T2 weighted imaging, diffusion weighted imaging, and apparent diffusion coefficient sequences) data were randomly divided into training (n = 659) and validation datasets (n = 80). According to the whole-mount histopathology, a DL model, including independent segmentation and classification networks, was developed to extract the gland and PCa area for PCa diagnosis. The area under the curve (AUC) were used to evaluate the performance of the prostate classification networks. The proposed DL model was subsequently used in clinical practice (independent test dataset; n = 200), and the PCa detective/diagnostic performance between the DL model and different level radiologists was evaluated based on the sensitivity, specificity, precision, and accuracy.Results: The AUC of the prostate classification network was 0.871 in the validation dataset, and it reached 0.797 using the DL model in the test dataset. Furthermore, the sensitivity, specificity, precision, and accuracy of the DL model for diagnosing PCa in the test dataset were 0.710, 0.690, 0.696, and 0.700, respectively. For the junior radiologist without and with DL model assistance, these values were 0.590, 0.700, 0.663, and 0.645 versus 0.790, 0.720, 0.738, and 0.755, respectively. For the senior radiologist, the values were 0.690, 0.770, 0.750, and 0.730 vs. 0.810, 0.840, 0.835, and 0.825, respectively. The diagnosis made with DL model assistance for radiologists were significantly higher than those without assistance (P < 0.05).Conclusion: The diagnostic performance of DL model is higher than that of junior radiologists and can improve PCa diagnostic accuracy in both junior and senior radiologists.

show abstract

“…With the growing use of artificial intelligence-related applications in radiology, several noninterpretive artificial intelligence applications such as patient scheduling or improved workflow have received attention (23). Use of machine learning tools could allow us to tailor the trigger threshold and iodine load for different protocols based on the desired kiloelectron-volt image series, renal function of the patient, or clinical background of the patient as part of improving workflow.…”

Section: Discussionmentioning

confidence: 99%

Optimized Bolus Threshold for Dual-Energy CT Angiography with Monoenergetic Images: A Randomized Clinical Trial

et al. 2021

View full text Add to dashboard Cite

C T angiography (CTA) has been widely used for a broad range of indications: evaluation of aortic vascular anatomy and disease condition (1), therapy planning for endovascular aortic aneurysm repair and transcatheter aortic valve implantation (2,3), and follow-up after endovascular aortic aneurysm repair (4). Surveillance imaging with CTA after endovascular aortic aneurysm repair is routinely recommended in detecting potential complications such as endoleak (5). Patients undergoing endovascular aortic aneurysm repair often have associated medical comorbidities including varying degrees of renal dysfunction. Intravenous iodinated contrast agent administration for CTA often poses the risk for contrast agent-associated acute renal injury, which is related to the iodine load (6,7).Virtual monochromatic images (VMIs) generated from a dual-energy CT (DECT) acquisition have been reported to enable lower iodine load in several studies (8-10). VMIs at lower energy levels show increased CT numbers because of approximation of the energy level closer to the k-edge of iodine at 33 keV (11). DECT angiography (DECTA) with reduced iodine dose (24 g) provided up to 185% higher CT attenuation and 25% higher contrast-to-noise ratio at low-energy VMIs compared with conventional single-energy CTA (SECTA) at 120 kVp by using a standard iodine dose (33.3 g) ( 9). Studies investigating DECTA commonly use a threshold of 100 HU for triggering scanning with the bolus-tracking technique (9,12-14), a threshold adapted from traditional single-energy CT Background: The bolus-tracking technique from single-energy CT has been applied to dual-energy CT (DECT) without optimization or validation. Further optimization is imperative because of a paucity of literature and differences in the attenuation profile of virtual monoenergetic images (VMIs).Purpose: To determine the optimal trigger threshold with bolus-tracking technique for DECT angiography (DECTA) in a phantom study and assess the feasibility of an optimized threshold for bolus-tracking technique in DECTA at 40 keV with a 50% reduced iodine dose in human participants. Materials and Methods:A phantom study with rapid kilovoltage-switching DECT was performed to determine the optimal threshold for each kiloelectron-volt VMI. In a prospective study, consecutive participants who underwent whole-body CT angiography (CTA) from August 2018 to July 2019 were randomized into three groups: single-energy CTA (SECTA) with standard iodine dose (600 mg of iodine per kilogram), DECTA with 50% reduced iodine dose (300 mg of iodine per kilogram) by using a conventional threshold, and DECTA with 300 mg of iodine per kilogram by using an optimized threshold. A trigger threshold of 100 HU at 120 kVp was used as a reference for comparison. Injected iodine doses and aortic CT numbers were compared among the three groups using Kruskal-Wallis test.Results: Ninety-six participants (mean age 6 standard deviation, 72 years 6 9; 80 men) were evaluated (32 participants in each group). The optimized threshold for VMIs at ...

show abstract

Challenges and solutions for introducing artificial intelligence (AI) in daily clinical workflow

Cited by 49 publications

References 6 publications

Current practical experience with artificial intelligence in clinical radiology: a survey of the European Society of Radiology

Current practical experience with artificial intelligence in clinical radiology: a survey of the European Society of Radiology

Deep Learning in Prostate Cancer Diagnosis Using Multiparametric Magnetic Resonance Imaging With Whole-Mount Histopathology Referenced Delineations

Optimized Bolus Threshold for Dual-Energy CT Angiography with Monoenergetic Images: A Randomized Clinical Trial

Contact Info

Product

Resources

About