Automated anonymization of radiology reports: comparison of publicly available natural language processing and large language models.

PURPOSE: Medical reports, governed by HIPAA regulations, contain personal health information (PHI), restricting secondary data use. Utilizing natural language processing (NLP) and large language models (LLM), we sought to employ publicly available methods to automatically anonymize PHI in free-text radiology reports. MATERIALS AND METHODS: We compared two publicly available rule-based NLP models (spaCy; NLPac, accuracy-optimized; NLPsp, speed-optimized; iteratively improved on 400 free-text CT-reports (test set)) and one offline LLM approach (LLM-model, LLaMa-2, Meta-AI) for PHI-anonymization. The three models were tested on 100 randomly selected chest CT reports. Two investigators assessed the anonymization of occurring PHI entities and whether clinical information was removed. Subsequently, precision, recall, and F1 scores were calculated. RESULTS: NLPac and NLPsp successfully removed all instances of dates (n = 333), medical record numbers (MRN) (n = 6), and accession numbers (ACC) (n = 92). The LLM model removed all MRNs, 96% of ACCs, and 32% of dates. NLPac was most consistent with a perfect F1-score of 1.00, followed by NLPsp with lower precision (0.86) and F1-score (0.92) for dates. The LLM model had perfect precision for MRNs, ACCs, and dates but the lowest recall for ACC (0.96) and dates (0.52), corresponding F1 scores of 0.98 and 0.68, respectively. Names were removed completely or majorly (i.e., one first or family name non-anonymized) in 100% (NLPac), 72% (NLPsp), and 90% (LLM-model). Importantly, NLPac and NLPsp did not remove medical information, while the LLM model did in 10% (n = 10). CONCLUSION: Pre-trained NLP models can effectively anonymize free-text radiology reports, while anonymization with the LLM model is more prone to deleting medical information. KEY POINTS: Question This study compares NLP and locally hosted LLM techniques to ensure PHI anonymization without losing clinical information. Findings Pre-trained NLP models effectively anonymized radiology reports without removing clinical data, while a locally hosted LLM was less reliable, risking the loss of important information. Clinical relevance Fast, reliable, automated anonymization of PHI from radiology reports enables HIPAA-compliant secondary use, facilitating advanced applications like LLM-driven radiology analysis while ensuring ethical handling of sensitive patient data.

Advanced CT measures of coronary artery disease with intermediate stenosis in patients with severe aortic valve stenosis.

BACKGROUND: Coronary artery disease (CAD) and severe aortic valve stenosis (AS) frequently coexist. While pre-transcatheter aortic valve replacement (TAVR) computed tomography angiography (CTA) allows to rule out obstructive CAD, interpreting hemodynamic significance of intermediate stenoses is challenging. This study investigates the incremental value of CT-derived fractional flow reserve (CT-FFR), quantitative coronary plaque characteristics (e.g., stenosis degree, plaque volume, and composition), and peri-coronary adipose tissue (PCAT) density to detect hemodynamically significant lesions among those with AS and CAD. MATERIALS AND METHODS: We included patients with severe AS and intermediate coronary lesions (20-80% diameter stenosis) who underwent pre-TAVR CTA and invasive coronary angiogram (ICA) with resting full-cycle ratio (RFR) assessment between 08/16 and 04/22. CTA image analysis included assessment of CT-FFR, quantitative coronary plaque analysis, and PCAT density. Coronary lesions with RFR ≤ 0.89 indicated hemodynamic significance as reference standard. RESULTS: Overall, 87 patients (age 77.9 ± 7.4 years, 38% female) with 95 intermediate coronary artery lesions were included. CT-FFR showed good discriminatory capacity (area under receiver operator curve (AUC) = 0.89, 95% confidence interval (CI) 0.81-0.96, p < 0.001) to identify hemodynamically significant lesions, superior to anatomical assessment, plaque morphology, and PCAT density. Plaque composition and PCAT density did not differ between lesions with and without hemodynamic significance. Univariable and multivariable analyses revealed CT-FFR as the only predictor for functionally significant lesions (odds ratio 1.28 (95% CI 1.17-1.43), p < 0.001). Overall, CT-FFR ≤ 0.80 showed diagnostic accuracy, sensitivity, and specificity of 88.4% (95%CI 80.2-94.1), 78.5% (95%CI 63.2-89.7), and 96.2% (95%CI 87.0-99.5), respectively. CONCLUSION: CT-FFR was superior to CT anatomical, plaque morphology, and PCAT assessment to detect functionally significant stenoses in patients with severe AS. CLINICAL RELEVANCE STATEMENT: CT-derived fractional flow reserve in patients with severe aortic valve stenosis may be a useful tool for non-invasive hemodynamic assessment of intermediate coronary lesions, while CT anatomical, plaque morphology, and peri-coronary adipose tissue assessment have no incremental or additional benefit. These findings might help to reduce pre-transcatheter aortic valve replacement invasive coronary angiogram. KEY POINTS: • Interpreting the hemodynamic significance of intermediate coronary stenoses is challenging in pre-transcatheter aortic valve replacement CT. • CT-derived fractional flow reserve (CT-FFR) has a good discriminatory capacity in the identification of hemodynamically significant coronary lesions. • CT-derived anatomical, plaque morphology, and peri-coronary adipose tissue assessment did not improve the diagnostic capability of CT-FFR in the hemodynamic assessment of intermediate coronary stenoses.

Reduction of contrast medium for transcatheter aortic valve replacement planning using a spectral detector CT: a prospective clinical trial.

INTRODUCTION: This study investigated the use of dual-energy spectral detector computed tomography (CT) and virtual monoenergetic imaging (VMI) reconstructions in pre-interventional transcatheter aortic valve replacement (TAVR) planning. We aimed to determine the minimum required contrast medium (CM) amount to maintain diagnostic CT imaging quality for TAVR planning. METHODS: In this prospective clinical trial, TAVR candidates received a standardized dual-layer spectral detector CT protocol. The CM amount (Iohexol 350 mg iodine/mL, standardized flow rate 3 mL/s) was reduced systematically after 15 patients by 10 mL, starting at 60 mL (institutional standard). We evaluated standard, and 40- and 60-keV VMI reconstructions. For image quality, we measured signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and diameters in multiple vessel sections (i.e., aortic annulus: diameter, perimeter, area; aorta/arteries: minimal diameter). Mixed regression models (MRM), including interaction terms and clinical characteristics, were used for comparison. RESULTS: Sixty consecutive patients (mean age, 79.4 ± 7.5 years; 28 females, 46.7%) were included. In pre-TAVR CT, the CM reduction to 40 mL is possible without affecting the image quality (MRM: SNR: -1.1, p = 0.726; CNR: 0.0, p = 0.999). VMI 40-keV reconstructions showed better results than standard reconstructions with significantly higher SNR (+ 6.04, p < 0.001). Reduction to 30 mL CM resulted in a significant loss of quality (MRM: SNR: -12.9, p < 0.001; CNR: -13.9, p < 0.001), regardless of the reconstruction. Across the reconstructions, we observed no differences in the metric evaluation (p > 0.914). CONCLUSION: Among TAVR candidates undergoing pre-interventional CT at a dual-layer spectral detector system, applying 40 mL CM is sufficient to maintain diagnostic image quality. VMI 40-keV reconstructions improve the vessel attenuation and are recommended for evaluation. CLINICAL RELEVANCE STATEMENT: Contrast medium reduction to 40 mL in pre-interventional transcatheter aortic valve replacement CT using dual-energy CT maintains image quality, while 40-keV virtual monoenergetic imaging reconstructions enhance vessel attenuation. These results offer valuable recommendations for interventional transcatheter aortic valve replacement evaluation and potentially improve nephroprotection in patients with compromised renal function. KEY POINTS: • Patients undergoing transcatheter aortic valve replacement (TAVR), requiring pre-interventional CT, are often multimorbid with impaired renal function. • Using a spectral detector dual-layer CT, contrast medium reduction to 40 mL is feasible, maintaining diagnostic image quality. • The additional application of virtual monoenergetic image reconstructions with 40 keV improves vessel attenuation significantly in clinical practice.

Work expectations, their fulfillment, and exhaustion among radiologists of all career levels: what can be learned from the example of Germany.

OBJECTIVES: To evaluate work expectations of radiologists at different career levels, their fulfillment, prevalence of exhaustion, and exhaustion-associated factors. METHODS: A standardized digital questionnaire was distributed internationally to radiologists of all career levels in the hospital and in ambulatory care via radiological societies and sent manually to 4500 radiologists of the largest German hospitals between December 2020 and April 2021. Statistics were based on age- and gender-adjusted regression analyses of respondents working in Germany (510 out of 594 total respondents). RESULTS: The most frequent expectations were "joy at work" (97%) and a "good working atmosphere" (97%), which were considered fulfilled by at least 78%. The expectation of a "structured residency within the regular time interval" (79%) was more frequently judged fulfilled by senior physicians (83%, odds ratio (OR) 4.31 [95% confidence interval (95% CI) 1.95-9.52]), chief physicians (85%, 6.81 [95% CI 1.91-24.29]), and radiologists outside the hospital (88%, 7.59 [95% CI 2.40-24.03]) than by residents (68%). Exhaustion was most common among residents (physical exhaustion: 38%; emotional exhaustion: 36%), in-hospital specialists (29%; 38%), and senior physicians (30%; 29%). In contrast to paid extra hours, unpaid extra hours were associated with physical exhaustion (5-10 extra hours: OR 2.54 [95% CI 1.54-4.19]). Fewer opportunities to shape the work environment were related to a higher probability of physical (2.03 [95% CI 1.32-3.13]) and emotional (2.15 [95% CI 1.39-3.33]) exhaustion. CONCLUSIONS: While most radiologists enjoy their work, residents wish for more training structure. Ensuring payment of extra hours and employee empowerment may help preventing burnout in high-risk groups. KEY POINTS: • Most important work expectations of radiologists who work in Germany are "joy at work," a "good working atmosphere," "support for further qualification," and a "structured residency within the regular time interval," with the latter containing potential for improvement according to residents. • Physical and emotional exhaustion are common at all career levels except for chief physicians and for radiologists who work outside the hospital in ambulatory care. • Exhaustion as a major burnout criterion is associated with unpaid extra hours and reduced opportunities to shape the work environment.

Transarterial chemoembolization of colorectal cancer liver metastasis: improved tumor response by DSM-TACE versus conventional TACE, a prospective, randomized, single-center trial.

OBJECTIVES: To prospectively evaluate the therapy response of third-line TACE with DSM or lipiodol in the treatment of CRLM using MRI. METHODS: In this prospective, randomized, single-center trial, patients were randomly assigned to receive TACE therapy with either lipiodol or DSM as the embolization agent. Therapy response was evaluated using MRI. Local tumor response was determined according to RECIST 1.1, and survival data was analyzed using the Kaplan-Meier estimator. RESULTS: Fifty patients (35 male, 15 female) were randomized and included in the survival analysis, whereas 31 patients completed therapy and were considered for evaluation of tumor responses (cTACE: n = 13, DSM-TACE: n = 18). In the cTACE group, PR was observed in 23%, SD in 15%, and PD in 62%. In the DSM-TACE-group, PR was observed in 22% of patients, SD in 56%, and PD in 22% (p = 0.047). In addition, the DSM-TACE group showed statistically significant tumor volume reduction (p = 0.006). Median apparent diffusion coefficient values were not significantly different between both groups at baseline (p = 0.26) and study endpoint (p = 0.83). Median survival in the cTACE group was 13 months (95% confidence interval, range 5-40 months) compared to 16 months (95% confidence interval, range 1-48 months) in the DSM-TACE group, exhibiting no statistically significant difference (p = 0.75). CONCLUSION: DSM-TACE showed a significant difference reducing tumor volume and in tumor response according to RECIST 1.1 compared to cTACE. Thus, patients with CRLM might not only benefit from short embolization effect of DSM-TACE but also from better tumor responses. Apparent diffusion coefficients were not significantly different between both groups and cannot be used as a biomarker for monitoring for therapeutic effect of TACE. KEY POINTS: • To our knowledge, this is the first prospective study that directly compared cTACE and DSM-TACE in patients with CRLM. • DSM-TACE showed a significant difference reducing tumor volume (p = 0.006) and in tumor response according to RECIST 1.1 (p = 0.047) compared to cTACE. • Survival analysis showed a median survival of 13 months in the cTACE group compared to 16 months in the DSM-TACE group (p = 0.75).

Analysis of Lipiodol uptake in angiography and computed tomography for the diagnosis of malignant versus benign hepatocellular nodules in cirrhotic liver.

OBJECTIVES: To evaluate the diagnostic value of Lipiodol distribution in angiography and CT to differentiate between hepatocellular carcinoma (HCC) and benign nodules of LI-RADS 3 and 4 lesions observed in MRI of liver cirrhosis. METHODS: This retrospective study included all patients with liver cirrhosis who had diagnosis of LI-RADS 3 or 4 lesions by MRI who underwent a Lipiodol-based angiography and post-interventional unenhanced CT- and liver biopsy. Two independent radiologists evaluated appearance, contrast enhancement, Lipiodol uptake in angiography, and morphological parameters (size, form, and density) of the lesions in unenhanced post-angiography CT. α-Fetoprotein (AFP) levels and pre-existing liver conditions were additionally taken into consideration. Differences between HCC lesions and benign nodules were analyzed. Sensitivity and specificity were calculated. P < 0.05 was considered as statistically significant. RESULTS: Of 60 patients (men, n = 42 [70.0%]; women, 18 [30.0%]; mean age, 61 ± 9.1 years) 36 (60.0%) had HCC and 24 (40.0%) benign nodules. Clear visibility in angiography (sensitivity [se], 100%; specificity [sp], 87.5%) with homogeneous or lacunar Lipiodol enhancement (se, 86.1%; sp, 100%) in consecutive CT can be diagnosed as HCC lesions in cirrhotic liver. Lesion form (p < 0.001), round or oval, and intense contrast (p < 0.001) are minor features which can facilitate the findings. Furthermore, patients with HCC showed a larger lesion size in CT (p = 0.026). CONCLUSION: Clearly detectable lesions in Lipiodol-based angiography and a homogeneous or lacunar enhancement in post-angiographic non-contrast CT allow for differentiation of intrahepatic lesions classified as LI-RADS 3 or 4 into benign vs. malign liver lesions with high sensitivity and specificity in patients with liver cirrhosis. Definite diagnosis may not require an additional biopsy. KEY POINTS: • Combination of clear visibility in Lipiodol-based angiography and homogeneous or lacunar enhancement in following native CT scan is HCC-defining. • In lesions classified with MRI as LI-RADS 3 or 4, evaluation based on Lipiodol angiography and following plain CT performed is highly sensitive and specific for the differentiation between HCC and benign nodules in a cirrhotic liver. • The results lead to an alternative pathway in the diagnosis of HCC in cirrhotic liver without the need of an additional liver biopsy.

Deep learning analysis of epicardial adipose tissue to predict cardiovascular risk in heavy smokers.

BACKGROUND: Heavy smokers are at increased risk for cardiovascular disease and may benefit from individualized risk quantification using routine lung cancer screening chest computed tomography. We investigated the prognostic value of deep learning-based automated epicardial adipose tissue quantification and compared it to established cardiovascular risk factors and coronary artery calcium. METHODS: We investigated the prognostic value of automated epicardial adipose tissue quantification in heavy smokers enrolled in the National Lung Screening Trial and followed for 12.3 (11.9-12.8) years. The epicardial adipose tissue was segmented and quantified on non-ECG-synchronized, non-contrast low-dose chest computed tomography scans using a validated deep-learning algorithm. Multivariable survival regression analyses were then utilized to determine the associations of epicardial adipose tissue volume and density with all-cause and cardiovascular mortality (myocardial infarction and stroke). RESULTS: Here we show in 24,090 adult heavy smokers (59% men; 61 ± 5 years) that epicardial adipose tissue volume and density are independently associated with all-cause (adjusted hazard ratios: 1.10 and 1.38; P < 0.001) and cardiovascular mortality (adjusted hazard ratios: 1.14 and 1.78; P < 0.001) beyond demographics, clinical risk factors, body habitus, level of education, and coronary artery calcium score. CONCLUSIONS: Our findings suggest that automated assessment of epicardial adipose tissue from low-dose lung cancer screening images offers prognostic value in heavy smokers, with potential implications for cardiovascular risk stratification in this high-risk population.

Heavy smokers are at increased risk of poor health outcomes, particularly outcomes related to cardiovascular disease. We explore how fat surrounding the heart, known as epicardial adipose tissue, may be an indicator of the health of heavy smokers. We use an artificial intelligence system to measure the heart fat on chest scans of heavy smokers taken during a lung cancer screening trial and following their health for 12 years. We find that higher amounts and denser epicardial adipose tissue are linked to an increased risk of death from any cause, specifically from heart-related issues, even when considering other health factors. This suggests that measuring epicardial adipose tissue during lung cancer screenings could be a valuable tool for identifying heavy smokers at greater risk of heart problems and death, possibly helping to guide their medical management and improve their cardiovascular health.

German Radiological Society and the Professional Association of German Radiologists Position Paper on Coronary computed tomography: Clinical Evidence and Quality of Patient Care in Chronic Coronary Syndrome. / Positionspapier von DRG und BDR zur Computertomografie des Herzens: Klinische Evidenz und Versorgungsqualität beim chronischen Koronarsyndrom.

This position paper is a joint statement of the German Radiological Society (DRG) and the Professional Association of German Radiologists (BDR), which reflects the current state of knowledge about coronary computed tomography. It is based on preclinical and clinical studies that have investigated the clinical relevance as well as the technical requirements and fundamentals of cardiac computed tomography. CITATION FORMAT: · Langenbach MC, Sandstede J, Sieren M et al. DRG and BDR Position Paper on Coronary CT: Clinical Evidence and Quality of Patient Care in Chronic Coronary Syndrome. Fortschr Röntgenstr 2023; 195: 115 - 133.

Feasibility and Comparison of Resting Full-Cycle Ratio and Computed Tomography Fractional Flow Reserve in Patients with Severe Aortic Valve Stenosis.

Background: Computed tomography derived Fractional Flow Reserve (CT-FFR) has been shown to decrease the referral rate for invasive coronary angiography (ICA). The purpose of the study was to evaluate the diagnostic performance of CT-FFR compared to hyperemia-free index Resting Full-cycle Ratio (RFR) in patients with relevant aortic stenosis (AS) and intermediate coronary stenosis. Methods: 41 patients with 46 coronary lesions underwent ICA with quantitative coronary angiography (QCA), pressure wire assessment and routine pre-transcatheter aortic valve replacement (TAVR) computed tomography (CT). CT-FFR analysis was performed using prototype on-site software. Results: RFR showed a significant correlation with CT-FFR (Pearson's correlation, r = 0.632, p < 0.001). On a per-lesion basis, diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of CT-FFR were 82.6% (95% CI 68.6−92.2), 69.6% (95% CI 47.1−86.8), 95.7% (95% CI 78.1−99.9), 94.1% (95% CI 69.8−99.1), and 75.9% (95% CI 62.7−85.4), respectively. The optimal cutoff value of the CT-FFR for RFR ≤ 0.89 prediction was 0.815. The area under the receiver curve showed a larger area under the curve for CT-FFR (0.87; 95% CI 0.75−0.98) compared with CTA stenosis of ≥50% (0.54, 95% CI 0.38−0.71), CTA ≥ 70% (0.72, 95% CI 0.57−0.87) and QCA ≥ 50% (0.67, 95% CI 0.52−0.83). Conclusions: CT-FFR assessed by routine pre-TAVR CT is safe and feasible and shows a significant correlation with RFR in patients with AS. CT-FFR is superior to QCA ≥ 50%, CT ≥ 50% and CT ≥ 70% in assessing the hemodynamic relevance of intermediate coronary lesions. Thus, CT-FFR has the potential to guide revascularization in patients with AS.

Lipiodol as a Predictive Indicator for Therapy Response to Transarterial Chemoembolization of Hepatocellular Carcinoma.

Background: To evaluate the predictive value of Lipiodol for response evaluation of hepatocellular carcinoma (HCC) treated with conventional transarterial chemoembolization (cTACE) by analysis of the enhancement pattern during angiography and in postinterventional computed tomography (CT). Materials and Methods: This retrospective study included 30 patients (mean age 63 years, range: 36 to 82 years, 22 males) with HCC. Patients received three Lipiodol-based cTACE sessions, each followed by an unenhanced CT within 24-h. Contrast-enhanced magnetic resonance imaging (MRI) was acquired before and after the treatment to determine tumor response. Lipiodol enhancement pattern, tumor vascularization, and density were evaluated by angiography and CT. Initial tumor size and response to cTACE were analyzed by MRI according to modified response evaluation criteria in solid tumors (mRECIST) in a 4-week follow-up. Results: Analysis of HCC lesions (68 lesions in 30 patients) during cTACE revealed clear visibility and hypervascularization in angiography as a potential independent parameter able to predict tumor response. A significant correlation was found for response measurements by volume (p = 0.012), diameter (p = 0.006), and according to mRECIST (p = 0.039). The amount of Lipiodol and enhancement pattern in postinterventional CT did not correlate with therapy response. Measurements of Hounsfield unit values after cTACE do not allow sufficient prediction of the tumor response. Conclusion: Hypervascularized HCC lesions with clear visibility after Lipiodol administration in the angiography respond significantly better to cTACE compared to hypo- or nonvascularized lesions.

The use of dynamic MR imaging in patients with clinical pelvic floor disorders.

OBJECTIVES: To determine the differences and challenging aspects of dynamic magnetic resonance defecography (MRD) compared to conventional defecography (CD) in diagnostic of clinical symptomatic pelvic floor dysfunction. METHODS: Fifty patients (44 females, 6 males; mean age: 57 years) with symptomatic pelvic floor dysfunction underwent both examinations, CD and MRD. Results were retrospectively intra-individual and interindividual evaluated in this multicentre study. Visibility and accuracy in diagnosis and classification of rectal prolapse, rectocele, enterocele, sigma diverticula and Cul-de-sac phenomenon/syndrome were observed. Differences were analysed using Mann-Whitney U test. P-values < 0.05 were considered as statistically significant. RESULTS: CD was significantly superior to MRD in diagnosis and grading of rectal prolapse (p < .001), diagnosis and metric measurements of rectoceles (p = .016), diagnosis of elongated sigmoid colon (p = .008) and Cul-de-sac phenomenon and syndrome, respectively (p = .015; p = .008). MRD revealed equal results to CD in detection, localization, tendency to retention and enlargement of rectoceles (p = .337) and findings of enteroceles (p = .604) as well as sigma diverticula (p = .149). CONCLUSIONS: The complementary use of both examination methods, CD and MRD, is important to achieve a comprehensive look on every aspect of pelvic floor disorders and gain optimal results in detection and evaluation of all major disorders of the pelvic floor.

Coronary Computed Tomographic Angiography-Derived Fractional Flow Reserve for Therapeutic Decision Making.

This study investigated the performance of coronary computed tomography angiography (cCTA) with cCTA-derived fractional flow reserve (CT-FFR) compared with invasive coronary angiography (ICA) with fractional flow reserve (FFR) for therapeutic decision making in patients with suspected coronary artery disease (CAD). Seventy-four patients (62 ± 11 years, 62% men) with at least 1 coronary stenosis of ≥50% on clinically indicated dual-source cCTA, who had subsequently undergone ICA with FFR measurement, were retrospectively evaluated. CT-FFR values were computed using an on-site machine-learning algorithm to assess the functional significance of CAD. The therapeutic strategy (optimal medical therapy alone vs revascularization) and the appropriate revascularization procedure (percutaneous coronary intervention vs coronary artery bypass grafting) were selected using cCTA-CT-FFR. Thirty-six patients (49%) had a functionally significant CAD based on ICA-FFR. cCTA-CT-FFR correctly identified a functionally significant CAD and the need of revascularization in 35 of 36 patients (97%). When revascularization was deemed indicated, the same revascularization procedure (32 percutaneous coronary interventions and 3 coronary artery bypass grafting) was chosen in 35 of 35 patients (100%). Overall, identical management strategies were selected in 73 of the 74 patients (99%). cCTA-CT-FFR shows excellent performance to identify patients with and without the need for revascularization and to select the appropriate revascularization strategy. cCTA-CT-FFR as a noninvasive "one-stop shop" has the potential to change diagnostic workflows and to directly inform therapeutic decision making in patients with suspected CAD.