Artificial intelligence support in MR imaging of incidental renal masses: an early health technology assessment.

OBJECTIVE: This study analyzes the potential cost-effectiveness of integrating an artificial intelligence (AI)-assisted system into the differentiation of incidental renal lesions as benign or malignant on MR images during follow-up. MATERIALS AND METHODS: For estimation of quality-adjusted life years (QALYs) and lifetime costs, a decision model was created, including the MRI strategy and MRI + AI strategy. Model input parameters were derived from recent literature. Willingness to pay (WTP) was set to $100,000/QALY. Costs of $0 for the AI were assumed in the base-case scenario. Model uncertainty and costs of the AI system were assessed using deterministic and probabilistic sensitivity analysis. RESULTS: Average total costs were at $8054 for the MRI strategy and $7939 for additional use of an AI-based algorithm. The model yielded a cumulative effectiveness of 8.76 QALYs for the MRI strategy and of 8.77 for the MRI + AI strategy. The economically dominant strategy was MRI + AI. Deterministic and probabilistic sensitivity analysis showed high robustness of the model with the incremental cost-effectiveness ratio (ICER), which represents the incremental cost associated with one additional QALY gained, remaining below the WTP for variation of the input parameters. If increasing costs for the algorithm, the ICER of $0/QALY was exceeded at $115, and the defined WTP was exceeded at $667 for the use of the AI. CONCLUSIONS: This analysis, rooted in assumptions, suggests that the additional use of an AI-based algorithm may be a potentially cost-effective alternative in the differentiation of incidental renal lesions using MRI and needs to be confirmed in the future. CLINICAL RELEVANCE STATEMENT: These results hint at AI's the potential impact on diagnosing renal masses. While the current study urges careful interpretation, ongoing research is essential to confirm and seamlessly integrate AI into clinical practice, ensuring its efficacy in routine diagnostics. KEY POINTS: • This is a model-based study using data from literature where AI has been applied in the diagnostic workup of incidental renal lesions. • MRI + AI has the potential to be a cost-effective alternative in the differentiation of incidental renal lesions. • The additional use of AI can reduce costs in the diagnostic workup of incidental renal lesions.

Economic potential of abbreviated breast MRI for screening women with dense breast tissue for breast cancer.

OBJECTIVES: Abbreviated breast MRI (AB-MRI) was introduced to reduce both examination and image reading times and to improve cost-effectiveness of breast cancer screening. The aim of this model-based economic study was to analyze the cost-effectiveness of full protocol breast MRI (FB-MRI) vs. AB-MRI in screening women with dense breast tissue for breast cancer. METHODS: Decision analysis and a Markov model were designed to model the cumulative costs and effects of biennial screening in terms of quality-adjusted life years (QALYs) from a US healthcare system perspective. Model input parameters for a cohort of women with dense breast tissue were adopted from recent literature. The impact of varying AB-MRI costs per examination as well as specificity on the resulting cost-effectiveness was modeled within deterministic sensitivity analyses. RESULTS: At an assumed cost per examination of $ 263 for AB-MRI (84% of the cost of a FB-MRI examination), the discounted cumulative costs of both MR-based strategies accounted comparably. Reducing the costs of AB-MRI below $ 259 (82% of the cost of a FB-MRI examination, respectively), the incremental cost-effectiveness ratio of FB-MRI exceeded the willingness to pay threshold and the AB-MRI-strategy should be considered preferable in terms of cost-effectiveness. CONCLUSIONS: Our preliminary findings indicate that AB-MRI may be considered cost-effective compared to FB-MRI for screening women with dense breast tissue for breast cancer, as long as the costs per examination do not exceed 82% of the cost of a FB-MRI examination. KEY POINTS: • Cost-effectiveness of abbreviated breast MRI is affected by reductions in specificity and resulting false positive findings and increased recall rates. • Abbreviated breast MRI may be cost-effective up to a cost per examination of 82% of the cost of a full protocol examination. • Abbreviated breast MRI could be an economically preferable alternative to full protocol breast MRI in screening women with dense breast tissue.

Computed Tomography Perfusion Deficit Volumes Predict Functional Outcome in Patients With Basilar Artery Occlusion.

Background and Purpose: Basilar artery occlusion is associated with high morbidity and mortality. Optimal imaging and treatment strategy are still controversial and prognosis estimation challenging. We, therefore, aimed to determine the predictive value of computed tomography perfusion (CTP) parameters for functional outcome in patients with basilar artery occlusion in the context of endovascular treatment. Methods: Patients with basilar artery occlusion who underwent endovascular treatment were selected from a prospectively acquired cohort. Ischemic changes were assessed with the posterior-circulation Acute Stroke Prognosis Early Computed Tomography Score on noncontrast computed tomography, computed tomography angiography (CTA) source images, and CTP maps. Basilar artery on CTA score, posterior-circulation CTA score, and posterior-circulation collateral score were evaluated on CTA. Perfusion deficit volumes were quantified on CTP maps. Good functional outcome was defined as modified Rankin Scale score ≤3 at 90 days. Statistical analysis included binary logistic regressions and receiver operating characteristics analyses. Results: Among 49 patients who matched the inclusion criteria, 24 (49.0%) achieved a good outcome. In univariate analysis, age, National Institutes of Health Stroke Scale score on admission, posterior cerebral artery involvement, absence of or hypoplastic posterior communicating arteries, basilar artery on CTA score, posterior-circulation Acute Stroke Prognosis Early Computed Tomography Score, and perfusion deficit volumes on all CTP parameter maps presented significant association with functional outcome (P<0.05). In multivariate analyses, Basilar artery on CTA score, posterior-circulation Acute Stroke Prognosis Early Computed Tomography Score (odds ratio range, 1.31­2.10 [95% CI, 1.00­7.24]), and perfusion deficit volumes on all CTP maps (odds ratio range, 0.77­0.98 [95% CI, 0.63­1.00]) remained as independent outcome predictors. Cerebral blood flow deficit volume yielded the best performance for the classification of good clinical outcome with an area under the curve of 0.92 (95% CI, 0.84­0.99). Age and admission National Institutes of Health Stroke Scale had lower discriminatory power (area under the curve, <0.7). Conclusions: CTP imaging parameters contain prognostic information for functional outcome in patients with stroke due to basilar artery occlusion and may identify patients with higher risk of disability at an early stage of hospitalization.

18F FDG PET/MRI with hepatocyte-specific contrast agent for M staging of rectal cancer: a primary economic evaluation.

PURPOSE: Rectal cancer is one of the most frequent causes of cancer-related morbidity and mortality in the world. Correct identification of the TNM state in primary staging of rectal cancer has critical implications on patient management. Initial evaluations revealed a high sensitivity and specificity for whole-body PET/MRI in the detection of metastases allowing for metastasis-directed therapy regimens. Nevertheless, its cost-effectiveness compared with that of standard-of-care imaging (SCI) using pelvic MRI + chest and abdominopelvic CT is yet to be investigated. Therefore, the aim of this study was to analyze the cost-effectiveness of whole-body 18F FDG PET/MRI as an alternative imaging method to standard diagnostic workup for initial staging of rectal cancer. METHODS: For estimation of quality-adjusted life years (QALYs) and lifetime costs of diagnostic modalities, a decision model including whole-body 18F FDG PET/MRI with a hepatocyte-specific contrast agent and pelvic MRI + chest and abdominopelvic CT was created based on Markov simulations. For obtaining model input parameters, review of recent literature was performed. Willingness to pay (WTP) was set to $100,000/QALY. Deterministic sensitivity analysis of diagnostic parameters and costs was applied, and probabilistic sensitivity was determined using Monte Carlo modeling. RESULTS: In the base-case scenario, the strategy whole-body 18F FDG PET/MRI resulted in total costs of $52,186 whereas total costs of SCI were at $51,672. Whole-body 18F FDG PET/MRI resulted in an expected effectiveness of 3.542 QALYs versus 3.535 QALYs for SCI. This resulted in an incremental cost-effectiveness ratio of $70,291 per QALY for PET/MRI. Thus, from an economic point of view, whole-body 18F FDG PET/MRI was identified as an adequate diagnostic alternative to SCI with high robustness of results to variation of input parameters. CONCLUSION: Based on the results of the analysis, use of whole-body 18F FDG PET/MRI was identified as a feasible diagnostic strategy for initial staging of rectal cancer from a cost-effectiveness perspective.

Evaluation of patients with respiratory infections during the first pandemic wave in Germany: characteristics of COVID-19 versus non-COVID-19 patients.

BACKGROUND: Characteristics of COVID-19 patients have mainly been reported within confirmed COVID-19 cohorts. By analyzing patients with respiratory infections in the emergency department during the first pandemic wave, we aim to assess differences in the characteristics of COVID-19 vs. Non-COVID-19 patients. This is particularly important regarding the second COVID-19 wave and the approaching influenza season. METHODS: We prospectively included 219 patients with suspected COVID-19 who received radiological imaging and RT-PCR for SARS-CoV-2. Demographic, clinical and laboratory parameters as well as RT-PCR results were used for subgroup analysis. Imaging data were reassessed using the following scoring system: 0 - not typical, 1 - possible, 2 - highly suspicious for COVID-19. RESULTS: COVID-19 was diagnosed in 72 (32,9%) patients. In three of them (4,2%) the initial RT-PCR was negative while initial CT scan revealed pneumonic findings. 111 (50,7%) patients, 61 of them (55,0%) COVID-19 positive, had evidence of pneumonia. Patients with COVID-19 pneumonia showed higher body temperature (37,7 ± 0,1 vs. 37,1 ± 0,1 °C; p = 0.0001) and LDH values (386,3 ± 27,1 vs. 310,4 ± 17,5 U/l; p = 0.012) as well as lower leukocytes (7,6 ± 0,5 vs. 10,1 ± 0,6G/l; p = 0.0003) than patients with other pneumonia. Among abnormal CT findings in COVID-19 patients, 57 (93,4%) were evaluated as highly suspicious or possible for COVID-19. In patients with negative RT-PCR and pneumonia, another third was evaluated as highly suspicious or possible for COVID-19 (14 out of 50; 28,0%). The sensitivity in the detection of patients requiring isolation was higher with initial chest CT than with initial RT-PCR (90,4% vs. 79,5%). CONCLUSIONS: COVID-19 patients show typical clinical, laboratory and imaging parameters which enable a sensitive detection of patients who demand isolation measures due to COVID-19.

Safe and pivotal approaches using contrast-enhanced ultrasound for the diagnostic workup of non-obstetric conditions during pregnancy, a single-center experience.

PURPOSE: Conventional ultrasound is the main imaging modality in obstetrics for assessing the maternal and fetal status. Up to date, contrast-enhanced ultrasound (CEUS) has not found widespread use in gynecology and obstetrics, but recent studies demonstrate promising results. The aim of the present study is to assess safe and valuable application of CEUS during pregnancy to investigate non-obstetric conditions. METHODS: Five pregnant patients on whom CEUS was performed between 2019 and 2020 were included in this retrospective single-center study. A total of six CEUS examinations were performed including one CEUS-guided biopsy (mean age: 31 years, mean weeks of pregnancy: 18 weeks). CEUS examinations were performed by a consultant radiologist (EFSUMB level 3). RESULTS: All included pregnant women safely underwent CEUS. Neither maternal nor fetal adverse effects were detected. CEUS critically helped in the diagnostic workup of a desmoid tumor of the abdominal wall, hepatic hemangioma, amebic hepatic abscess, uncomplicated renal cyst and post-inflammatory alteration of the renal cortex and for excluding active abdominal bleeding. In addition, CEUS-guided biopsy was performed to prevent intratumoral hemorrhage. Findings from CEUS prompted immediate treatment in two women, whereas in three women regular obstetric monitoring of the women could be conducted. CONCLUSION: Our results demonstrate safe and crucial application of off-label CEUS in pregnant women to assess different non-obstetric conditions allowing to prevent additional ionizing CT or application of (gadolinium-based) contrast agent in MRI. Hence, CEUS might add pivotal value for evaluating obstetric and non-obstetric conditions and thereby directing clinical management of pregnant women in the future.

Tuberculous perihepatic abscess and neurosarcoidosis: report of 2 uncommon manifestations of 2 common granulomatous diseases in 1 patient.

Infections caused by pathogens of the Mycobacterium tuberculosis complex, i. e., tuberculosis (TB), and the non-infectious, autoimmune disease sarcoidosis are among the most common granulomatous diseases worldwide. Typically, the lung is the primary site of infection and manifestation, respectively which makes the two diseases important differential diagnoses. Both diseases can affect virtually all organ systems, albeit with significantly lower incidence. CASE PRESENTATION: We report the case of a 50-year-old Indian man presenting with a tuberculous perihepatic abscess and a systemic inflammatory response after being diagnosed with neurosarcoidosis presenting as a single granuloma in the frontal lobe with lymphadenopathy in 2014. On day of admission the patient presented with right upper abdominal pain and fever for two weeks. With increased inflammatory parameters in serum and after finding of external CT images, a perihepatic abscess was suspected. This encapsulated cave was drained percutaneously under CT control. A high concentration of acid-fast rods was detected using ZN, PCR was positive for M. tuberculosis. Several samples of sputum and urine were microscopically negative but yielded growth of Mycobacteria after four weeks. DISCUSSION: This is a case presenting with two different granulomatous diseases, each of which manifested itself in an atypical form. The tuberculous liver abscess might either be explained as a flare-up of latent tuberculosis under azathioprine therapy or as a reinfection acquired during one of several visits in the high-prevalence country India. In addition, it must be discussed whether the cerebral granuloma in 2014 could have been an early stage of tuberculous granuloma. Sensitivity of ZN staining is significantly reduced in cerebral samples, and negative PCR-results might be due to low germ load or methodical issues, e. g., decreased sensitivity in formalin fixated samples.

Evaluation of the Diagnostic Value of Contrast-Enhanced Voiding Urosonography with Regard to the Further Therapy Regime and Patient Outcome-A Single-Center Experience in an Interdisciplinary Uroradiological Setting.

Background and Objectives: Vesicoureteral reflux (VUR) describes a common pediatric anomaly in pediatric urology with a prevalence of 1-2%. In diagnostics, in addition to the gold standard of voiding cystourethrography (VCUG), contrast-enhanced urosonography (ceVUS) offers a radiation-free procedure, which, despite its advantages, is not yet widely used. In the present single-center study, subsequent therapeutic procedures and outcomes after ceVUS of 49 patients were investigated. The aim of the study is to investigate the efficacy of ceVUS with the intention of broader clinical implementation. Materials and Methods: Between 2016 and 2020, 49 patients were retrospectively included and received a ceVUS to evaluate VUR. With a distribution of 47:2 (95.9%), a clear female predominance was present. The age of the patients varied between 5 months and 60 years at the time of ceVUS. All examinations were all performed and subsequently interpreted by a single experienced radiologist (EFSUMB level 3). Results: Compared to intraoperative findings, ceVUS shows a sensitivity of 95.7% with a specificity of 100%. Allergic reactions to the contrast medium could not be observed. Conclusion: With its high sensitivity and intraoperative validation, ceVUS offers an excellent alternative to VCUG, the gold standard in the diagnosis of VUR. In addition, ceVUS is a radiation-free examination method with a low risk profile that offers an exceptional diagnostic tool in the diagnostic clarification of recurrent urinary tract infections with the suspected diagnosis of VUR and should also be included in the consideration of a diagnosis next to the established VCUG, especially in younger children.

Overview of ultrasound applications for assessing scrotal disorders.

The scrotum may be affected by a plethora of different disorders such as infections, vasculopathies, trauma, and manifestations of primary and secondary malignant masses. In addition to the patient's medical history and clinical examination, ultrasound represents the imaging modality of choice to assess scrotal disorders. Time-consuming contrast-enhanced ultrasound and elastography can provide further information to distinguish between benign and malignant testicular mass lesions. The following invited Special Communication gives a comprehensive overview of differential diagnoses of the scrotum and their corresponding sonomorphologic correlates based on representative cases of the Interdisciplinary Ultrasound Center of the University Hospital Munich.

Single-Center Study: Evaluating the Diagnostic Performance and Safety of Contrast-Enhanced Ultrasound (CEUS) in Pregnant Women to Assess Hepatic Lesions.

BACKGROUND: Ultrasound is an essential imaging tool for evaluating physiological and pathological fetal or maternal conditions during pregnancy. Published data is limited with respect to the application of CEUS during pregnancy. CEUS has already been safely applied for assessing uteroplacental blood flow, cesarean scar pregnancy and invasive placenta percreta. CT and MRI scans during pregnancy must be thoroughly evaluated due to harmful ionizing radiation and cerebral gadolinium deposition, respectively. PURPOSE: The aim of the present retrospective single-center study is to assess the diagnostic performance and safety of CEUS during pregnancy to evaluate hepatic lesions of unknown entity. METHODS: 6 pregnant patients who underwent CEUS between 2005 and 2014 (mean age: 32 years; mean weeks of pregnancy: 28 weeks) were included in this study. The applied contrast agent was a second-generation blood-pool agent (SonoVue®, Bracco, Milan, Italy). CEUS examinations were performed and interpreted by a single radiologist with experience since 2000 (EFSUMB Level 3). RESULTS: CEUS was safely performed on all included pregnant women without the occurrence of adverse fetal or maternal events. In the context of the present study, CEUS helped to safely differentiate hepatic metastases, focal nodular hyperplasia, atypical hemangioma, hepatic arteriovenous malformation and cystic echinococcosis. In two patients CEUS determined immediate therapy. CONCLUSION: Although not clinically approved in obstetrics so far, CEUS is a safe imaging modality which, in addition to B-mode and color Doppler ultrasonography, may be applied during pregnancy for further medical indications and to provide helpful information.

Contrast-Enhanced Ultrasound for Assessing Abdominal Conditions in Pregnancy.

Background and objectives: Native ultrasound is the most common imaging modality in obstetrics. The use of contrast-enhanced ultrasound (CEUS) during pregnancy has not been officially approved by leading societies for obstetrics and ultrasound. The present study aims to monitor the safety and diagnostic performance of CEUS for assessing abdominal issues in five pregnant women. Materials and Methods: Five pregnant patients who underwent a total of 11 CEUS examinations between June 2020 and October 2020 were included (mean age: 34 years; mean time of pregnancy: 21 weeks). All CEUS scans were interpreted by one experienced consultant radiologist (EFSUMB Level 3). Results: Upon contrast application, no maternal nor fetal adverse effects were observed. Moreover, no fetal contrast enhancement was observed in any patient. CEUS helped to diagnose renal angiomyolipoma, pyelonephritis, necrotic uterine fibroid, gallbladder polyp, and superior mesenteric vein thrombosis. Conclusions: In our study, off-label use of CEUS showed an excellent safety profile allowing the avoidance of ionizing radiation exposure as well as contrast agents in case of CT or use of gadolinium-based contrast agents in case of MRI. CEUS is a promising diagnostic instrument for facilitating clinical decision-making and improving the management of pregnant women.

Diagnostic Performance of Contrast-Enhanced Ultrasound (CEUS) in the Evaluation of Solid Renal Masses.

BACKGROUND: The present study aims to evaluate the diagnostic performance of contrast-enhanced ultrasound (CEUS) for discriminating between benign and malignant solid renal masses. METHODS: 18 patients with histopathologically confirmed benign solid renal masses (11 oncocytomas, seven angiomyolipomas) as well as 96 patients with confirmed renal cell carcinoma (RCC) who underwent CEUS followed by radical or partial nephrectomy were included in this single-center study. CEUS examinations were performed by an experienced radiologist (EFSUMB Level 3) and included the application of a second-generation contrast agent. RESULTS: Renal angiomyolipomas, oncocytomas, and renal cell carcinomas showed varying sonomorphological characteristics in CEUS. Angiomyolipomas showed heterogeneous echogenicity (57% hypo-, 43% hyperechoic), while all lesions showed rapid contrast-enhancement with two lesions also showing venous wash-out (29%). Notably, 9/11 oncocytomas could be detected in conventional ultrasound (64% hypo-, 9% hyper-, 9% isoechoic) and 2/11 only demarcated upon intravenous application of contrast agent (18%). All oncocytomas showed hyperenhancement in CEUS, venous wash-out was registered in 7/11 lesions (64%). CONCLUSIONS: In line with the current state of knowledge, no specific sonomorphological characteristics allowing for accurate distinction between benign and malignant solid renal masses in CEUS could be detected in our study.

Contrast-Enhanced Ultrasound (CEUS) for the Evaluation of Bosniak III Complex Renal Cystic Lesions-A 10-Year Specialized European Single-Center Experience with Histopathological Validation.

Background and objectives: The aim of the present retrospective single-center study is to evaluate the diagnostic performance of contrast-enhanced ultrasound (CEUS) for assessing Bosniak III complex renal cystic lesions with histopathological validation. Materials and Methods: 49 patients with CEUS-categorized Bosniak III renal cystic lesions were included in this retrospective study. All patients underwent native B-mode, Color Doppler, contrast-enhanced ultrasound (CEUS) between 2010-2020. Eight and five patients underwent computed tomography (CT) and magnetic resonance imaging (MRI), respectively. Twenty-nine underwent (partial) nephrectomy allowing for histopathological analysis. The applied contrast agent for CEUS was a second-generation blood pool agent. Ultrasonography examinations were performed and interpreted by a single experienced radiologist with more than 15 years of experience (EFSUMB Level 3). Results: CEUS examinations were successfully performed in all included patients without registering any adverse effects. The malignancy rate of CEUS-categorized Bosniak III renal lesions accounted for 66%. Initially, cystic complexity was visualized in native B-mode. In none of the renal lesions hypervascularization was detected in Color Doppler. CEUS allowed for detection of contrast enhancement patterns in all included Bosniak III renal lesions. Delayed wash-out could be detected in 6/29 renal lesions. In two cases of histopathologically confirmed clear-cell RCC, appropriate up-grading from Bosniak IIF to III was achieved by CEUS. Conclusions: CEUS depicts a promising imaging modality for the precise diagnostic workup and stratification of renal cystic lesions according to the Bosniak classification system, thereby helping guidance of adequate clinical management in the future.

Ultrasound and contrast enhanced ultrasound imaging in the diagnosis of acute aortic pathologies.

Conventional ultrasound is worldwide the first-line imaging modality for the prompt diagnosis in the daily practice because it is a cost-effective and easy to perform technique. The additional application of contrast media has been used to enhance the intravascular contrast and to improve the imaging diagnostic accuracy in the detection, classification and follow-up of vascular pathologies. Contrast-enhanced ultrasound has the advantage of being a safe, fast and dynamic non-invasive imaging tool with excellent results in the diagnosis of acute aortic pathologies, especially the detection of endoleaks after endovascular aneurysm repair. This review describes the diagnostic and therapeutic roles of ultrasound and contrast-enhanced ultrasound imaging in the most common vascular pathologies such as aortic dissections, aneurysms and endoleaks. Keywords: Endoleak, contrast media, ultrasonography, aorta.

The IL-33/ST2 axis augments effector T-cell responses during acute GVHD.

Interleukin (IL)-33 binding to the receptor suppression of tumorigenicity 2 (ST2) produces pro-inflammatory and anti-inflammatory effects. Increased levels of soluble ST2 (sST2) are a biomarker for steroid-refractory graft-versus-host disease (GVHD) and mortality. However, whether sST2 has a role as an immune modulator or only as a biomarker during GVHD was unclear. We show increased IL-33 production by nonhematopoietic cells in the gastrointestinal (GI) tract in mice post-conditioning and patients during GVHD. Exogenous IL-33 administration during the peak inflammatory response worsened GVHD. Conversely, GVHD lethality and tumor necrosis factor-α production was significantly reduced in il33(-/-) recipients. ST2 was upregulated on murine and human alloreactive T cells and sST2 increased as experimental GVHD progressed. Concordantly, st2(-/-) vs wild-type (WT) donor T cells had a marked reduction in GVHD lethality and GI histopathology. Alloantigen-induced IL-18 receptor upregulation was lower in st2(-/-) T cells, and linked to reduced interferon-γ production by st2(-/-) vs WT T cells during GVHD. Blockade of IL-33/ST2 interactions during allogeneic-hematopoietic cell transplantation by exogenous ST2-Fc infusions had a marked reduction in GVHD lethality, indicating a role of ST2 as a decoy receptor modulating GVHD. Together, these studies point to the IL-33/ST2 axis as a novel and potent target for GVHD therapy.

Nonradiology Health Care Professionals Significantly Benefit From AI Assistance in Emergency-Related Chest Radiography Interpretation.

BACKGROUND: Chest radiographs (CXRs) are still of crucial importance in primary diagnostics, but their interpretation poses difficulties at times. RESEARCH QUESTION: Can a convolutional neural network-based artificial intelligence (AI) system that interprets CXRs add value in an emergency unit setting? STUDY DESIGN AND METHODS: A total of 563 CXRs acquired in the emergency unit of a major university hospital were retrospectively assessed twice by three board-certified radiologists, three radiology residents, and three emergency unit-experienced nonradiology residents (NRRs). They used a two-step reading process: (1) without AI support; and (2) with AI support providing additional images with AI overlays. Suspicion of four suspected pathologies (pleural effusion, pneumothorax, consolidations suspicious for pneumonia, and nodules) was reported on a five-point confidence scale. Confidence scores of the board-certified radiologists were converted into four binary reference standards of different sensitivities. Performance by radiology residents and NRRs without AI support/with AI support were statistically compared by using receiver-operating characteristics (ROCs), Youden statistics, and operating point metrics derived from fitted ROC curves. RESULTS: NRRs could significantly improve performance, sensitivity, and accuracy with AI support in all four pathologies tested. In the most sensitive reference standard (reference standard IV), NRR consensus improved the area under the ROC curve (mean, 95% CI) in the detection of the time-critical pathology pneumothorax from 0.846 (0.785-0.907) without AI support to 0.974 (0.947-1.000) with AI support (P < .001), which represented a gain of 30% in sensitivity and 2% in accuracy (while maintaining an optimized specificity). The most pronounced effect was observed in nodule detection, with NRR with AI support improving sensitivity by 53% and accuracy by 7% (area under the ROC curve without AI support, 0.723 [0.661-0.785]; with AI support, 0.890 [0.848-0.931]; P < .001). Radiology residents had smaller, mostly nonsignificant gains in performance, sensitivity, and accuracy with AI support. INTERPRETATION: We found that in an emergency unit setting without 24/7 radiology coverage, the presented AI solution features an excellent clinical support tool to nonradiologists, similar to a second reader, and allows for a more accurate primary diagnosis and thus earlier therapy initiation.

Therapeutic Outcome of MR-Guided High-Intensity Focused Ultrasound (MR-HIFU) in Solitary versus Multiple Uterine Fibroids.

MR-guided high-intensity focused ultrasound (MR-HIFU) is an effective method for treating symptomatic uterine fibroids, especially solitary lesions. The aim of our study was to compare the clinical and morphological outcomes of patients who underwent MR-HIFU due to solitary fibroid (SF) or multiple fibroids (MFs) in a prospective clinical trial. We prospectively included 21 consecutive patients with SF (10) and MF (11) eligible for MR-guided HIFU. The morphological data were assessed using mint Lesion™ for MRI. The clinical data were determined using the Uterine Fibroid Symptom and Quality of Life (UFS-QOL) questionnaire before and 6 months after treatment. Unpaired and paired Wilcoxon-test and t-tests were applied, and Pearson's coefficient was used for correlation analysis. A p-value of 0.05 was considered statistically significant. The volume of treated fibroids significantly decreased in both the SF (mean baseline: 118.6 cm3; mean 6-month follow-up: 64.6 cm3) and MF (107.2 cm3; 55.1 cm3) groups. The UFS-QOL showed clinical symptoms significantly improved for patients in both the SF and MF groups regarding concern, activities, energy/mood, and control. The short-term outcome for the treatment of symptomatic fibroids in myomatous uterus by MR-guided HIFU is clinically similar to that of solitary fibroids.

Clinically focused multi-cohort benchmarking as a tool for external validation of artificial intelligence algorithm performance in basic chest radiography analysis.

Artificial intelligence (AI) algorithms evaluating [supine] chest radiographs ([S]CXRs) have remarkably increased in number recently. Since training and validation are often performed on subsets of the same overall dataset, external validation is mandatory to reproduce results and reveal potential training errors. We applied a multicohort benchmarking to the publicly accessible (S)CXR analyzing AI algorithm CheXNet, comprising three clinically relevant study cohorts which differ in patient positioning ([S]CXRs), the applied reference standards (CT-/[S]CXR-based) and the possibility to also compare algorithm classification with different medical experts' reading performance. The study cohorts include [1] a cohort, characterized by 563 CXRs acquired in the emergency unit that were evaluated by 9 readers (radiologists and non-radiologists) in terms of 4 common pathologies, [2] a collection of 6,248 SCXRs annotated by radiologists in terms of pneumothorax presence, its size and presence of inserted thoracic tube material which allowed for subgroup and confounding bias analysis and [3] a cohort consisting of 166 patients with SCXRs that were evaluated by radiologists for underlying causes of basal lung opacities, all of those cases having been correlated to a timely acquired computed tomography scan (SCXR and CT within < 90 min). CheXNet non-significantly exceeded the radiology resident (RR) consensus in the detection of suspicious lung nodules (cohort [1], AUC AI/RR: 0.851/0.839, p = 0.793) and the radiological readers in the detection of basal pneumonia (cohort [3], AUC AI/reader consensus: 0.825/0.782, p = 0.390) and basal pleural effusion (cohort [3], AUC AI/reader consensus: 0.762/0.710, p = 0.336) in SCXR, partly with AUC values higher than originally published ("Nodule": 0.780, "Infiltration": 0.735, "Effusion": 0.864). The classifier "Infiltration" turned out to be very dependent on patient positioning (best in CXR, worst in SCXR). The pneumothorax SCXR cohort [2] revealed poor algorithm performance in CXRs without inserted thoracic material and in the detection of small pneumothoraces, which can be explained by a known systematic confounding error in the algorithm training process. The benefit of clinically relevant external validation is demonstrated by the differences in algorithm performance as compared to the original publication. Our multi-cohort benchmarking finally enables the consideration of confounders, different reference standards and patient positioning as well as the AI performance comparison with differentially qualified medical readers.