Optimal radiological gallbladder lesion characterization by combining visual assessment with CT-based radiomics.

OBJECTIVES: Differentiating benign gallbladder diseases from gallbladder cancer (GBC) remains a radiological challenge because they can appear very similar on imaging. This study aimed at investigating whether CT-based radiomic features of suspicious gallbladder lesions analyzed by machine learning algorithms could adequately discriminate benign gallbladder disease from GBC. In addition, the added value of machine learning models to radiological visual CT-scan interpretation was assessed. METHODS: Patients were retrospectively selected based on confirmed histopathological diagnosis and available contrast-enhanced portal venous phase CT-scan. The radiomic features were extracted from the entire gallbladder, then further analyzed by machine learning classifiers based on Lasso regression, Ridge regression, and XG Boosting. The results of the best-performing classifier were combined with radiological visual CT diagnosis and then compared with radiological visual CT assessment alone. RESULTS: In total, 127 patients were included: 83 patients with benign gallbladder lesions and 44 patients with GBC. Among all machine learning classifiers, XG boosting achieved the best AUC of 0.81 (95% CI 0.72-0.91) and the highest accuracy rate of 73% (95% CI 65-80%). When combining radiological visual interpretation and predictions of the XG boosting classifier, the highest diagnostic performance was achieved with an AUC of 0.98 (95% CI 0.96-1.00), a sensitivity of 91% (95% CI 86-100%), a specificity of 93% (95% CI 90-100%), and an accuracy of 92% (95% CI 90-100%). CONCLUSIONS: Machine learning analysis of CT-based radiomic features shows promising results in discriminating benign from malignant gallbladder disease. Combining CT-based radiomic analysis and radiological visual interpretation provided the most optimal strategy for GBC and benign gallbladder disease differentiation. KEY POINTS: Radiomic-based machine learning algorithms are able to differentiate benign gallbladder disease from gallbladder cancer. Combining machine learning algorithms with a radiological visual interpretation of gallbladder lesions at CT increases the specificity, compared to visual interpretation alone, from 73 to 93% and the accuracy from 85 to 92%. Combined use of machine learning algorithms and radiological visual assessment seems the most optimal strategy for GBC and benign gallbladder disease differentiation.

Incidental imaging findings referred to a specialized sarcoma center: Frequency, determinants, and downstream healthcare costs.

OBJECTIVE: To determine the frequency and factors associated with incidental imaging findings (incidentalomas) that are referred to a specialized sarcoma center and that eventually turn out to be benign or of low-risk malignant potential, and to assess their downstream healthcare costs. MATERIALS AND METHODS: This study included all consecutive new patients that were referred to a specialized sarcoma center within a 7-month period. RESULTS: Of 221 patients that were included, 28 had an incidentaloma. Of these 28 incidentalomas, 23 were benign (n = 11) or of low-risk malignant potential (n = 12), corresponding to a frequency of 10.4% Utilization of conventional radiography (odds ratio [OR] = 6.538, P = 0.018) and CT (OR = 8.167, P = 0.012) was significantly more associated with the detection of benign or low-risk malignant potential incidentalomas than ultrasonography. The likelihood of detecting benign or low-risk malignant potential incidentalomas after MRI utilization was not significantly different from that after ultrasonography (P = 0.174). All other variables (including patient age and gender, history of malignancy, specialty by whom the lesion was initially detected, and lesion location) were not significantly associated with these incidentalomas. The 23 cases with an incidentaloma that turned out to be benign or of low-risk malignant potential resulted in a total of €42,707 ($49,552) downstream healthcare costs, with an average of €1857 ($2155) per case. CONCLUSION: Incidentalomas that are referred to a specialized sarcoma center and that eventually prove to be benign or of low-risk malignant potential are common, are more frequently detected on conventional radiographs and CT, and cause relevant subsequent healthcare costs.

Radiologist-patient communication of musculoskeletal ultrasonography results: a choice between added value and costs.

BACKGROUND: Literature on radiologist-patient communication of musculoskeletal ultrasonography (US) results is currently lacking. PURPOSE: To investigate the patient's view on receiving the results from a radiologist after a musculoskeletal US examination, and the additional time required to provide such a service. MATERIAL AND METHODS: This prospective study included 106 outpatients who underwent musculoskeletal US, and who were equally randomized to either receive or not receive the results from the radiologist directly after the examination. RESULTS: In both randomization groups, all quality performance metrics (radiologist's friendliness, explanation, skill, concern for comfort, concern for patient questions/worries, overall rating of the examination, and likelihood of recommending the examination) received median scores of good/high to very good/very high. Patients who had received their US results from the radiologist rated the radiologist's explanation and concern for patient questions/worries as significantly higher (P = 0.009 and P = 0.002) than patients who had not. In both randomization groups, there were no significant differences between anxiety levels before and after the US examination (P = 0.222 and P = 1.000). Of the 48 responding patients, 46 (95.8%) rated a radiologist-patient discussion of US findings as important. US examinations with a radiologist-patient communication regarding US findings (median = 11.29 min) were significantly longer (P < 0.0001) than those without (median = 8.08 min). CONCLUSION: Even without communicating musculoskeletal US results directly to patients, radiologists can still achieve high ratings from patients for their communication and empathy. Nevertheless, patient experience can be further enhanced if a radiologist adds this communication to the examination. However, this increases total examination time and therefore costs.

Patient safety incidents in radiology: frequency and distribution of incident types.

BACKGROUND: Patient safety incidents may be a valuable source of information to learn from and to prevent future errors. PURPOSE: To determine the distribution of patient safety incident types in radiology according to the International Classification for Patient Safety (ICPS), and to comprehensively review those incidents that were either harmful or serious in terms of risk of patient harm and reoccurrence. MATERIAL AND METHODS: The most recent five-year database (2014-2019) of a radiology incident reporting system was evaluated. RESULTS: A total of 480 patient safety incidents were included. Top three ICPS incident types were clinical administration (119/480, 24.8%), resources/organizational management (112/480, 23.3%), and clinical process/procedure (91/480, 19.0%). Harm severities were none in 457 (95.2%) cases, mild in 14 (2.9%), moderate in 4 (0.8%), severe in 3 (0.6%), and unknown in one case. Subsequent Prevention Recovery Information System for Monitoring and Analysis (PRISMA) reviews were performed in 4 (0.8%) cases. The three patient safety incidents that caused severe harm (of which one underwent PRISMA review) involved resources/organizational management (n = 1), clinical process/procedure (n = 1), and medication/IV fluids (n = 1). Three other cases (with no harm in two cases and moderate harm in one case) that underwent PRISMA review involved resources/organizational management (n = 2) and medical device/equipment/property (n = 1). CONCLUSION: Radiology-related patient safety incidents predominantly occur in three ICPS domains (clinical administration, resources/organizational management, and clinical process/procedure). Harmful/serious incidents are relatively rare. The standardly and transparently reported findings from this study may be used for healthcare quality improvement, benchmarking purposes, and as a primer for future studies.

Patient safety in nuclear medicine: identification of key strategic areas for vigilance and improvement.

OBJECTIVE: To determine the types of patient safety incidents and associated harm in nuclear medicine practice. METHODS: This study included 147 patient safety incidents related to nuclear medicine practice and submitted to the incident reporting system of a tertiary care nuclear medicine department between 2014 and 2019. RESULTS: The top-three incident types according to the International Classification for Patient Safety (ICPS) were medication/IV fluids (36/147, 24.5%), clinical administration (28/147, 19.0%), and clinical process/procedure (27/147, 18.4%), altogether comprising 61.9% of incidents. Within the medication/IV fluids domain, half of incident subtypes were attributable to supply/ordering, omitted medicine or dose, and wrong dose/strength of frequency. Within the clinical administration domain, appointment and wrong patient represented the majority of incident subtypes. Within the clinical process/procedure domain, the majority of incident subtypes fell in the categories: specimens/results and incomplete/inadequate. There was no patient harm in 145 (98.6%) of cases, mild patient harm in 1 (0.7%) case, and in 1 (0.7%) case, it remained unclear if there was patient harm. In 4 (2.7%) cases, a Prevention Recovery Information System for Monitoring and Analysis evaluation was performed because of the high risk of reoccurrence and patient harm. CONCLUSIONS: The majority of patient safety incidents in nuclear medicine occur in three main ICPS categories (medication/IV fluids, clinical administration, and clinical process/procedure, in order of decreasing frequency). These can be considered as key strategic areas for incident prevention and patient safety improvement. Nevertheless, the rate of actual patient harm was very low in our series.

Carbon footprint of the RSNA annual meeting.

PURPOSE: To determine the airplane travel-related carbon footprint of the Radiological Society of North America (RSNA) annual meeting, the associated health burden, and the costs to offset these greenhouse gas emissions (i.e. compensation of emissions by funding an equivalent CO2 saving elsewhere). METHODS: The RSNA's website was used to determine the reported country of origin of attendees to the 2017 meeting that took place in Chicago from November 26 to December 1. It was assumed that attendees had traveled from the airport nearest to the largest city in their country or state to Chicago's O'Hare international airport. The total amount of air travel-related CO2-equivalent emission (based on round-trip economy class travel), the imposed health burden in terms of disability-adjusted life years (DALYs) in the global population, the total CO2 offsets costs, and the CO2 offsets costs per DALY were calculated. RESULTS: The calculated airplane travel-related CO2-equivalent emissions of 11,223 attendees from the United States and 10,684 attendees from other countries were 7,067,618 kg and 32,438,420 kg, totaling 39,506,038 kg. This caused an estimated 51.4-79.0 DALYs. The calculated amount of Total CO2 offset costs were calculated to be $474,072, which corresponds to $6,001-9,223 per DALY averted. CONCLUSIONS: The airplane travel-related carbon footprint of the RSNA annual meeting and the associated disease burden are relevant, and potential attendees and organizers should take measures to overcome this undesired side effect. Offsetting this carbon footprint is cost-effective and this initiative should be taken by the radiological community.

Patients' views on the implementation of artificial intelligence in radiology: development and validation of a standardized questionnaire.

OBJECTIVES: The patients' view on the implementation of artificial intelligence (AI) in radiology is still mainly unexplored territory. The aim of this article is to develop and validate a standardized patient questionnaire on the implementation of AI in radiology. METHODS: Six domains derived from a previous qualitative study were used to develop a questionnaire, and cognitive interviews were used as pretest method. One hundred fifty-five patients scheduled for CT, MRI, and/or conventional radiography filled out the questionnaire. To find underlying latent variables, we used exploratory factor analysis with principal axis factoring and oblique promax rotation. Internal consistency of the factors was measured with Cronbach's alpha and composite reliability. RESULTS: The exploratory factor analysis revealed five factors on AI in radiology: (1) distrust and accountability (overall, patients were moderately negative on this subject), (2) procedural knowledge (patients generally indicated the need for their active engagement), (3) personal interaction (overall, patients preferred personal interaction), (4) efficiency (overall, patients were ambiguous on this subject), and (5) being informed (overall, scores on these items were not outspoken within this factor). Internal consistency was good for three factors (1, 2, and 3), and acceptable for two (4 and 5). CONCLUSIONS: This study yielded a viable questionnaire to measure acceptance among patients of the implementation of AI in radiology. Additional data collection with confirmatory factor analysis may provide further refinement of the scale. KEY POINTS: • Although AI systems are increasingly developed, not much is known about patients' views on AI in radiology. • Since it is important that newly developed questionnaires are adequately tested and validated, we did so for a questionnaire measuring patients' views on AI in radiology, revealing five factors. • Successful implementation of AI in radiology requires assessment of social factors such as subjective norms towards the technology.

Recommendations for additional imaging of abdominal imaging examinations: frequency, benefit, and cost.

OBJECTIVES: To investigate the frequency, determinants, clinical implications, and costs of recommendations for additional imaging (RAIs) in secondary interpretations of abdominal imaging examinations. METHODS: This retrospective study included 2225 abdominal imaging examinations from outside institutions that were reinterpreted as part of standard clinical care at a tertiary care center in a one-year time frame. RESULTS: Two hundred forty-six RAIs were present in 231 of 2225 reports (10.4%) of secondary abdominal imaging interpretations. Patient age and experience of the radiologist who performed the secondary interpretation were independently significantly associated with the presence of an RAI (both p = 0.002), with odds ratios of 0.99 per year increase in patient age (95% confidence interval [CI], 0.98-1.00) and 1.06 per year increase in experience of the radiologist (95% CI, 1.02-1.10). If followed, RAIs changed clinical management in 31.2%. Total costs of all 246 RAIs, whether performed or not by the referring physicians, amounted to €71,032.21, thus resulting in €31.92 per secondary abdominal imaging interpretation. Total costs of the 140 RAIs that were actually performed by the referring physicians amounted to €42,683.08, resulting in €19.18 per secondary abdominal imaging interpretation. CONCLUSIONS: The frequency of RAIs in reports of secondary interpretations of abdominal imaging examinations (which appear to be affected by patients' age and radiologists' experience) and associated costs are non-negligible. However, RAIs not infrequently change clinical management. The presented data may be helpful to radiology departments and healthcare policy makers to make well-informed decisions on the value and facilitation of the practice of secondary interpretations. KEY POINTS: • Frequency of recommendations for additional imaging (RAIs) in secondary interpretations of abdominal imaging examinations at a tertiary care center is approximately 10.4%. • RAIs appear to be more frequently issued in younger patients and by more experienced radiologists, and if followed by referring clinicians, change clinical management in about one third of cases. • RAI costs per secondary interpretation in the Dutch Healthcare system are €31.92 (considering all RAIs) or €19.18 (considering only those RAIs that are actually performed).

Frequency, Determinants, and Costs of Recommendations for Additional Imaging in Clinical 18F-FDG PET/CT Reports.

Our purpose was to determine the frequency, determinants, and costs of recommendations for additional imaging (RAIs) in clinical 18F-FDG PET/CT reports. Methods: This retrospective study included a random sample of 2,643 18F-FDG PET/CT scans that were performed for various clinical reasons at a tertiary-care academic medical center without financial incentives for self-referral, within a 1.5-y period. Results: Ninety-eight (3.7%) of 2,643 18F-FDG PET/CT reports contained an RAI. None of the investigated variables (patient age, hospital status [inpatient or outpatient], indication for 18F-FDG PET/CT scanning [oncologic, infection/inflammation, or miscellaneous], type of 18F-FDG PET/CT scan [low-dose 18F-FDG PET/CT or low-dose 18F-FDG PET/CT combined with diagnostic CT of any body region], or years of experience of the [most senior] signing author) was univariately associated with the presence of an RAI in the 18F-FDG PET/CT report. The hypothesis that RAIs more frequently occur when the anatomic area to which the RAI relates is not covered by a diagnostic CT scan (as part of the 18F-FDG PET/CT examination) was also rejected (P = 0.419). The total costs of all RAIs (regardless of whether they were actually performed by the referring clinicians) were €23,922.21 ($27,065.47), which corresponds to an average of €9.08 ($10.27) RAI costs per 18F-FDG PET/CT exam. The total costs of all RAIs that were actually performed by the referring clinicians were €16,498.62 ($18,666.46), which corresponds to an average of €6.26 ($7.08) RAI costs per 18F-FDG PET/CT exam. Conclusion: RAIs in 18F-FDG PET/CT reports in a European tertiary-care academic medical center without financial incentives for self-referral are infrequent, cannot be anticipated, and result in relatively low overall costs.

In-Bore MR-Guided Biopsy Systems and Utility of PI-RADS.

A diagnostic dilemma exists in cases wherein a patient with clinical suspicion for prostate cancer has a negative transrectal ultrasound-guided biopsy session. Although transrectal ultrasound-guided biopsy is the standard of care, a paradigm shift is being observed. In biopsy-naive patients and patients with at least 1 negative biopsy session, multiparametric magnetic resonance imaging (MRI) is being utilized for tumor detection and subsequent targeting. Several commercial devices are now available for targeted prostate biopsy ranging from transrectal ultrasound-MR fusion biopsy to in bore MR-guided biopsy. In this review, we will give an update on the current status of in-bore MRI-guided biopsy systems and discuss value of prostate imaging-reporting and data system (PIRADS).

Complementary Prognostic Value of Pelvic Magnetic Resonance Imaging and Whole-Body Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography in the Pretreatment Assessment of Patients With Cervical Cancer.

OBJECTIVE: The aim of this study was to evaluate the incremental prognostic value of pelvic magnetic resonance imaging (MRI) and whole-body F-fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) findings compared with clinical-histopathologic factors in patients with newly diagnosed cervical cancer. METHODS: The institutional review board approved this retrospective study of 114 patients (median age, 40.6 years) with International Federation of Gynecology and Obstetrics (FIGO) stage I-IVB cervical cancer who underwent pretreatment MRI and PET/CT. All scans were reviewed for locoregional tumor extent, pelvic or/and para-aortic lymphadenopathy, and distant metastases. Univariate Cox proportional hazard regression was performed to evaluate associations between clinical-histopathologic factors, imaging findings, and progression-free survival (PFS). Multivariate models were built using independent predictors for PFS. Harrell C was used to measure concordance (C index). RESULTS: Forty patients progressed within a median time of 10.4 months (range, 0.4-40.3 months). At univariate analysis, age, FIGO stage, tumor histology, tumor grade, and all MRI and PET/CT features were significantly associated with PFS (P < 0.0001 to P = 0.0474). A multivariate model including clinical and imaging parameters (parametrial invasion on MRI and para-aortic lymphadenopathy/distant metastases on PET/CT) had significantly higher concordance for predicting PFS than a model including clinical parameters only (C index: 0.81 [95% confidence interval, 0.75-0.87] vs 0.68 [95% confidence interval, 0.59-0.78]; P < 0.001). The comparison of C indices for the combined clinical and imaging model approached significance when compared with a FIGO stage model (C index: 0.81 [95% confidence interval, 0.75-0.87] vs 0.75 [95% confidence interval, 0.69-0.82]; P = 0.058). CONCLUSIONS: In patients with newly diagnosed cervical cancer, a prognostic model including combined MRI and PET/CT findings provides information that complements clinical and histopathologic factors.

Predictive value of MRI in the localization, staging, volume estimation, assessment of aggressiveness, and guidance of radiotherapy and biopsies in prostate cancer.

Multiparametric magnetic resonance imaging (MRI) has the potential of being the ideal prostate cancer (PCa) assessment tool. Information gathered with multiparametric MRI can serve therapy choice, guidance of interventions, and treatments. The purpose of this review is to discuss the potential role of multiparametric MRI in focal therapy with respect to patient selection and directing (robot-guided) biopsies and intensity-modulated radiation therapy (IMRT). Multiparametric MRI is a versatile and promising technique. It appears to be the best available imaging technique at the moment in localizing, staging (primary as well as recurrent disease, and local as well as distant disease), determining aggressiveness, and volume of PCa. However, larger study populations in multicenter settings have to confirm these promising results. However, before such studies can be performed more research is needed in order to achieve standardized imaging protocols.