Skin color influences transcutaneous bilirubin measurements: a systematic in vitro evaluation.

OBJECTIVE: Concerns have been raised about the effect of skin color on the accuracy of transcutaneous bilirubin (TcB) measurements, a widely used method for hyperbilirubinemia diagnosis in newborns. Literature is inconclusive, with both reported under- and overestimations of the TcB with increasing skin pigmentation. Therefore, the influence of skin color on TcB measurements was systematically evaluated in a controlled, in vitro setting. METHODS: A bilirubin meter (JM-105) was evaluated on layered phantoms that mimic neonatal skin with varying dermal bilirubin concentrations (0-250 µmol/L) and varying epidermal melanosome volume fractions (0-40%; light-dark skin color). RESULTS: TcB measurements were influenced by skin pigmentation. Larger mimicked melanosome volume fractions and higher bilirubin levels led to larger underestimations of the measured TcB, compared to an unpigmented epidermis. In the in vitro setting of this study, these underestimations amounted to 26-132 µmol/L at a TcB level of 250 µmol/L. CONCLUSION: This in vitro study provides insight into the effect of skin color on TcB measurements: the TcB is underestimated as skin pigmentation increases and this effect becomes more pronounced at higher bilirubin levels. Our results highlight the need for improved TcB meter design and cautious interpretation of TcB readings on newborns with dark skin. IMPACT: Key message: Skin color influences transcutaneous bilirubin measurements: the darker the skin, the larger the underestimation. What this study adds to existing literature: Existing literature is inconclusive regarding the influence of skin color on transcutaneous bilirubin measurements. This study systematically evaluates and clarifies the influence of skin color on transcutaneous bilirubin measurements in a controlled, in vitro setting. IMPACT: This study aids to better interpret the measured TcB level in patients with varying skin colors, and is particularly important when using TcB meters on patients with dark skin colors.

Added value of an artificial intelligence algorithm in reducing the number of missed incidental acute pulmonary embolism in routine portal venous phase chest CT.

OBJECTIVES: The purpose of this study was to evaluate the incremental value of artificial intelligence (AI) compared to the diagnostic accuracy of radiologists alone in detecting incidental acute pulmonary embolism (PE) on routine portal venous contrast-enhanced chest computed tomography (CT). METHODS: CTs of 3089 consecutive patients referred to the radiology department for a routine contrast-enhanced chest CT between 27-5-2020 and 31-12-2020, were retrospectively analysed by a CE-certified and FDA-approved AI algorithm. The diagnostic performance of the AI was compared to the initial report. To determine the reference standard, discordant findings were independently evaluated by two readers. In case of disagreement, another experienced cardiothoracic radiologist with knowledge of the initial report and the AI output adjudicated. RESULTS: The prevalence of acute incidental PE in the reference standard was 2.2% (67 of 3089 patients). In 25 cases, AI detected initially unreported PE. This included three cases concerning central/lobar PE. Sensitivity of the AI algorithm was significantly higher than the outcome of the initial report (respectively 95.5% vs. 62.7%, p < 0.001), whereas specificity was very high for both (respectively 99.6% vs 99.9%, p = 0.012). The AI algorithm only showed a slightly higher amount of false-positive findings (11 vs. 2), resulting in a significantly lower PPV (85.3% vs. 95.5%, p = 0.047). CONCLUSION: The AI algorithm showed high diagnostic accuracy in diagnosing incidental PE, detecting an additional 25 cases of initially unreported PE, accounting for 37.3% of all positive cases. CLINICAL RELEVANCE STATEMENT: Radiologist support from AI algorithms in daily practice can prevent missed incidental acute PE on routine chest CT, without a high burden of false-positive cases. KEY POINTS: • Incidental pulmonary embolism is often missed by radiologists in non-diagnostic scans with suboptimal contrast opacification within the pulmonary trunk. • An artificial intelligence algorithm showed higher sensitivity detecting incidental pulmonary embolism on routine portal venous chest CT compared to the initial report. • Implementation of artificial intelligence support in routine daily practice will reduce the number of missed incidental pulmonary embolism.

An artificial intelligence algorithm for pulmonary embolism detection on polychromatic computed tomography: performance on virtual monochromatic images.

OBJECTIVES: Virtual monochromatic images (VMI) are increasingly used in clinical practice as they improve contrast-to-noise ratio. However, due to their different appearances, the performance of artificial intelligence (AI) trained on conventional CT images may worsen. The goal of this study was to assess the performance of an established AI algorithm trained on conventional polychromatic computed tomography (CT) images (CPI) to detect pulmonary embolism (PE) on VMI. METHODS: Paired 60 kiloelectron volt (keV) VMI and CPI of 114 consecutive patients suspected of PE, obtained with a detector-based spectral CT scanner, were retrospectively analyzed by an established AI algorithm. The CT pulmonary angiography (CTPA) were classified as positive or negative for PE on a per-patient level. The reference standard was established using a comprehensive method that combined the evaluation of the attending radiologist and three experienced cardiothoracic radiologists aided by two different detection tools. Sensitivity, specificity, positive and negative predictive values and likelihood ratios of the algorithm on VMI and CPI were compared. RESULTS: The prevalence of PE according to the reference standard was 35.1% (40 patients). None of the diagnostic accuracy measures of the algorithm showed a significant difference between CPI and VMI. Sensitivity was 77.5% (95% confidence interval (CI) 64.6-90.4%) and 85.0% (73.9-96.1%) (p = 0.08) on CPI and VMI respectively and specificity 96.0% (91.4-100.0%) and 94.6% (89.4-99.7%) (p = 0.32). CONCLUSIONS: Diagnostic performance of the AI algorithm that was trained on CPI did not drop on VMI, which is reassuring for its use in clinical practice. CLINICAL RELEVANCE STATEMENT: A commercially available AI algorithm, trained on conventional polychromatic CTPA, could be safely used on virtual monochromatic images. This supports the sustainability of AI-aided detection of PE on CT despite ongoing technological advances in medical imaging, although monitoring in daily practice will remain important. KEY POINTS: • Diagnostic accuracy of an AI algorithm trained on conventional polychromatic images to detect PE did not drop on virtual monochromatic images. • Our results are reassuring as innovations in hardware and reconstruction in CT are continuing, whilst commercial AI algorithms that are trained on older generation data enter healthcare.

Diagnostic accuracy of an artificial intelligence algorithm versus radiologists for fracture detection on cervical spine CT.

OBJECTIVES: To compare diagnostic accuracy of a deep learning artificial intelligence (AI) for cervical spine (C-spine) fracture detection on CT to attending radiologists and assess which undetected fractures were injuries in need of stabilising therapy (IST). METHODS: This single-centre, retrospective diagnostic accuracy study included consecutive patients (age ≥18 years; 2007-2014) screened for C-spine fractures with CT. To validate ground truth, one radiologist and three neurosurgeons independently examined scans positive for fracture. Negative scans were followed up until 2022 through patient files and two radiologists reviewed negative scans that were flagged positive by AI. The neurosurgeons determined which fractures were ISTs. Diagnostic accuracy of AI and attending radiologists (index tests) were compared using McNemar. RESULTS: Of the 2368 scans (median age, 48, interquartile range 30-65; 1441 men) analysed, 221 (9.3%) scans contained C-spine fractures with 133 IST. AI detected 158/221 scans with fractures (sensitivity 71.5%, 95% CI 65.5-77.4%) and 2118/2147 scans without fractures (specificity 98.6%, 95% CI 98.2-99.1). In comparison, attending radiologists detected 195/221 scans with fractures (sensitivity 88.2%, 95% CI 84.0-92.5%, p < 0.001) and 2130/2147 scans without fracture (specificity 99.2%, 95% CI 98.8-99.6, p = 0.07). Of the fractures undetected by AI 30/63 were ISTs versus 4/26 for radiologists. AI detected 22/26 fractures undetected by the radiologists, including 3/4 undetected ISTs. CONCLUSION: Compared to attending radiologists, the artificial intelligence has a lower sensitivity and a higher miss rate of fractures in need of stabilising therapy; however, it detected most fractures undetected by the radiologists, including fractures in need of stabilising therapy. Clinical relevance statement The artificial intelligence algorithm missed more cervical spine fractures on CT than attending radiologists, but detected 84.6% of fractures undetected by radiologists, including fractures in need of stabilising therapy. KEY POINTS: The impact of artificial intelligence for cervical spine fracture detection on CT on fracture management is unknown. The algorithm detected less fractures than attending radiologists, but detected most fractures undetected by the radiologists including almost all in need of stabilising therapy. The artificial intelligence algorithm shows potential as a concurrent reader.

Intravoxel incoherent motion (IVIM)-derived perfusion fraction mapping for the visual evaluation of MR-guided high intensity focused ultrasound (MR-HIFU) ablation of uterine fibroids.

BACKGROUND: A method for periprocedural contrast agent-free visualization of uterine fibroid perfusion could potentially shorten magnetic resonance-guided high intensity focused ultrasound (MR-HIFU) treatment times and improve outcomes. Our goal was to test feasibility of perfusion fraction mapping by intravoxel incoherent motion (IVIM) modeling using diffusion-weighted MRI as method for visual evaluation of MR-HIFU treatment progression. METHODS: Conventional and T2-corrected IVIM-derived perfusion fraction maps were retrospectively calculated by applying two fitting methods to diffusion-weighted MRI data (b = 0, 50, 100, 200, 400, 600 and 800 s/mm2 at 1.5 T) from forty-four premenopausal women who underwent MR-HIFU ablation treatment of uterine fibroids. Contrast in perfusion fraction maps between areas with low perfusion fraction and surrounding tissue in the target uterine fibroid immediately following MR-HIFU treatment was evaluated. Additionally, the Dice similarity coefficient (DSC) was calculated between delineated areas with low IVIM-derived perfusion fraction and hypoperfusion based on CE-T1w. RESULTS: Average perfusion fraction ranged between 0.068 and 0.083 in areas with low perfusion fraction based on visual assessment, and between 0.256 and 0.335 in surrounding tissues (all p < 0.001). DSCs ranged from 0.714 to 0.734 between areas with low perfusion fraction and the CE-T1w derived non-perfused areas, with excellent intraobserver reliability of the delineated areas (ICC 0.97). CONCLUSION: The MR-HIFU treatment effect in uterine fibroids can be visualized using IVIM perfusion fraction mapping, in moderate concordance with contrast enhanced MRI. IVIM perfusion fraction mapping has therefore the potential to serve as a contrast agent-free imaging method to visualize the MR-HIFU treatment progression in uterine fibroids.

Quantification of cephalocaudal progression of jaundice in preterm infants.

BACKGROUND: The cephalocaudal progression (CCP) of neonatal jaundice is a well-known phenomenon, but quantitative information on CCP in preterm infants is absent. In this study, CCP was quantified in preterm infants as a function of postnatal age and body location. METHODS: 5.693 transcutaneous bilirubin (TcB) measurements were performed in 101 preterm infants from birth until postnatal day seven at five body locations (forehead, sternum, hipbone, tibia, ankle). Multi-level linear regression analysis was performed to evaluate the CCP as a function of body location and postnatal age. TcB measurements at all body locations and postnatal days were compared to total serum bilirubin (TSB) levels (N = 1.113). RESULTS: The overall average change in ratio of TcB compared to forehead was for sternum +0.04 [95% CI -0.02;0.09]; hipbone +0.05 [0.00;0.01]; tibia -0.33 [-0.38;-0.27] and ankle -0.62 [-0.68;-0.57]. No effect modification of CCP by sex, gestational age, birthweight, phototherapy, and TSB was found. The TcB maximally underestimated the TSB at the ankle -79.5 µmol [-0.1;159.2]. CONCLUSIONS: CCP is present in preterm infants and is relatively stable over time. Since TcB measurements on the tibia and ankle underestimate TSB significantly, we advise to use only measurement locations cephalic from the tibia; i.e., hipbone, sternum, and forehead. IMPACT: Cephalocaudal progression (CCP) of jaundice in preterm infants, assessed by transcutaneous bilirubin (TcB) measurements, is substantial and rather stable over postnatal day 0 to 7. To the best of our knowledge, this study is the first to investigate CCP of jaundice in preterm infants as a function of postnatal age in preterm infants. Our results demonstrate that TcB measurements at the tibia and ankle differ from the TSB beyond the clinically used TcB safety margins. We advise to perform TcB measurements only at locations cephalic from the tibia; i.e., hipbone, forehead, and sternum.

Diffusion-weighted MRI with deep learning for visualizing treatment results of MR-guided HIFU ablation of uterine fibroids.

OBJECTIVES: No method is available to determine the non-perfused volume (NPV) repeatedly during magnetic resonance-guided high-intensity focused ultrasound (MR-HIFU) ablations of uterine fibroids, as repeated acquisition of contrast-enhanced T1-weighted (CE-T1w) scans is inhibited by safety concerns. The objective of this study was to develop and test a deep learning-based method for translation of diffusion-weighted imaging (DWI) into synthetic CE-T1w scans, for monitoring MR-HIFU treatment progression. METHODS: The algorithm was retrospectively trained and validated on data from 33 and 20 patients respectively who underwent an MR-HIFU treatment of uterine fibroids between June 2017 and January 2019. Postablation synthetic CE-T1w images were generated by a deep learning network trained on paired DWI and reference CE-T1w scans acquired during the treatment procedure. Quantitative analysis included calculation of the Dice coefficient of NPVs delineated on synthetic and reference CE-T1w scans. Four MR-HIFU radiologists assessed the outcome of MR-HIFU treatments and NPV ratio based on the synthetic and reference CE-T1w scans. RESULTS: Dice coefficient of NPVs was 71% (± 22%). The mean difference in NPV ratio was 1.4% (± 22%) and not statistically significant (p = 0.79). Absolute agreement of the radiologists on technical treatment success on synthetic and reference CE-T1w scans was 83%. NPV ratio estimations on synthetic and reference CE-T1w scans were not significantly different (p = 0.27). CONCLUSIONS: Deep learning-based synthetic CE-T1w scans derived from intraprocedural DWI allow gadolinium-free visualization of the predicted NPV, and can potentially be used for repeated gadolinium-free monitoring of treatment progression during MR-HIFU therapy for uterine fibroids. KEY POINTS: • Synthetic CE-T1w scans can be derived from diffusion-weighted imaging using deep learning. • Synthetic CE-T1w scans may be used for visualization of the NPV without using a contrast agent directly after MR-HIFU ablations of uterine fibroids.

Effect of bladder outlet procedures on urodynamic assessments in men with an acontractile or underactive detrusor: A systematic review and meta-analysis.

OBJECTIVE: To review the effect of bladder outlet procedures on urodynamic outcomes and symptom scores in males with detrusor underactivity (DU) or acontractile detrusors (AD). MATERIALS AND METHODS: We performed a systematic review and meta-analysis of research publications derived from PubMed, Embase, Web of Science, and Ovid Medline to identify clinical studies of adult men with non-neurogenic DU or AD who underwent any bladder outlet procedure. Outcomes comprised the detrusor pressure at maximum flow (Pdet Qmax ), maximum flow rate (Qmax ), international prostate symptom score (IPSS), and quality of life (QoL). This study is registered under PROSPERO CRD42020215832. RESULTS: We included 13 studies of bladder outlet procedures, of which 6 reported decreased and 7 reported improved Pdet Qmax after the procedure. Meta-analysis revealed an increase in the pooled mean Pdet Qmax of 5.99 cmH2 0 after surgery (95% CI: 0.59-11.40; p = 0.03; I2 95%). Notably, the Pdet Qmax improved in all subgroups with a preoperative bladder contractility index (BCI) <50 and decreased in all subgroups with a BCI ≥50. All studies reported an improved Qmax after surgery, with a pooled mean difference of 5.87 mL/s (95% CI: 4.25-7.49; I2 93%). Only three studies reported QoL, but pooling suggested significant improvements after surgery (mean, -2.41 points; 95% CI: -2.81 to -2.01; p = 0.007). All seven studies reporting IPSS demonstrated improvement (mean, -12.82; 95% CI: -14.76 to -10.88; p < 0.001). CONCLUSIONS: This review shows that Pdet Qmax and Qmax increases after surgical bladder outlet procedures in men with DU and AD. Bladder outlet procedures should be discussed as part of the shared decision-making process for this group. The evidence was of low to very low certainty.

Foot orthoses for flexible flatfeet in children and adults: a systematic review and meta-analysis of patient-reported outcomes.

BACKGROUND: This systematic review and meta-analysis examined the effectiveness of orthoses for flexible flatfeet in terms of patient-reported outcomes in children and adults. METHODS: EMBASE, Medline (OvidSP), Web-of-Science, Scopus, CINAHL, Cochrane Central Register of Controlled Clinical Trials, i.e., Cochrane Central and Pubmed were searched to identify relevant studies since their inception up to February 2021. We included randomized controlled trials (RCT) and prospective studies in which patient reported outcomes at baseline and follow-up in an orthoses group were compared with a no orthoses or sham sole group. Methodological quality of the studies was assessed using the Revised Cochrane risk-of-bias tool for randomized trials (RoB 2) and the Risk Of Bias In Non-Randomized Studies of Interventions (ROBINS-I). A meta-analysis was performed where there were multiple studies with the same outcome measures, which was the case for the Visual Analogue Scale (VAS) for pain in adults. RESULTS: In total nine studies were included: four RCT in children (N = 353) and four RCT and one prospective study in adults (N = 268) were included. There was considerable heterogeneity between studies. A meta-analysis demonstrated that pain reduction between baseline and follow-up was significantly larger in the orthoses (N = 167) than in the control groups in adults (N = 157; - 4.76, 95% CI [- 9.46, - 0.06], p0.05). CONCLUSION: Due to heterogeneity in study designs, we cannot conclude that foot orthoses are useful for flexible flatfoot in children and adults. However, based on the meta-analysis orthoses might be useful in decreasing pain in adults. The authors did not receive support from any organization for the submitted work.

The Focused Ultrasound Myoma Outcome Study (FUMOS); a retrospective cohort study on long-term outcomes of MR-HIFU therapy.

OBJECTIVES: Since 2004, uterine fibroids have been treated with MR-HIFU, but there are persevering doubts on long-term efficacy to date. In the Focused Ultrasound Myoma Outcome Study (FUMOS), we evaluated long-term outcomes after MR-HIFU therapy, primarily to assess the reintervention rate. METHODS: Data was retrospectively collected from 123 patients treated with MR-HIFU at our hospital from 2010 to 2017. Follow-up duration and baseline (MRI) characteristics were retrieved from medical records. Treatment failures, adverse events, and the nonperfused volume percentage (NPV%) were determined. Patients received a questionnaire about reinterventions, recovery time, satisfaction, and pregnancy outcomes. Restrictive treatment protocols were compared with unrestrictive (aiming for complete ablation) treatments. Subgroups were analyzed based on the achieved NPV < 50 or ≥ 50%. RESULTS: Treatment failures occurred in 12.1% and the number of adverse events was 13.7%. Implementation of an unrestrictive treatment protocol significantly (p = 0.006) increased the mean NPV% from 37.4% [24.3-53.0] to 57.4% [33.5-76.5]. At 63.5 ± 29.0 months follow-up, the overall reintervention rate was 33.3% (n = 87). All reinterventions were performed within 34 months follow-up, but within 21 months in the unrestrictive group. The reintervention rate significantly (p = 0.002) decreased from 48.8% in the restrictive group (n = 43; follow-up 87.5 ± 7.3 months) to 18.2% in the unrestrictive group (n = 44; follow-up 40.0 ± 22.1 months). The median recovery time was 2.0 [1.0-7.0] days. Treatment satisfaction rate was 72.4% and 4/11 women completed family planning after MR-HIFU. CONCLUSIONS: The unrestrictive treatment protocol significantly increased the NPV%. Unrestrictive MR-HIFU treatments led to acceptable reintervention rates comparable to other reimbursed uterine-sparing treatments, and no reinterventions were reported beyond 21 months follow-up. KEY POINTS: • All reinterventions were performed within 34 months follow-up, but in the unrestrictive treatment protocol group, no reinterventions were reported beyond 21 months follow-up. • The NPV% was negatively associated with the risk of reintervention; thus, operators should aim for complete ablation during MR-guided HIFU therapy of uterine fibroids. • Unrestrictive treatments have led to acceptable reintervention rates after MR-guided HIFU therapy compared to other reimbursed uterine-sparing treatments.

Use of multiparametric MRI to characterize uterine fibroid tissue types.

BACKGROUND: Although the biological characteristics of uterine fibroids (UF) have implications for therapy choice and effectiveness, there is limited MRI data about these characteristics. Currently, the Funaki classification and Scaled Signal Intensity (SSI) are used to predict treatment outcome but both screening-tools appear to be suboptimal. Therefore, multiparametric and quantitative MRI was studied to evaluate various biological characteristics of UF. METHODS: 87 patients with UF underwent an MRI-examination. Differences between UF tissues and myometrium were investigated using T2-mapping, Apparent Diffusion Coefficient (ADC) maps with different b-value combinations, contrast-enhanced T1-weighted and T2-weighted imaging. Additionally, the Funaki classification and SSI were calculated. RESULTS: Significant differences between myometrium and UF tissue in T2-mapping (p = 0.001), long-TE ADC low b-values (p = 0.002), ADC all b-values (p < 0.001) and high b-values (p < 0.001) were found. Significant differences between Funaki type 3 versus type 1 and 2 were observed in SSI (p < 0.001) and T2-values (p < 0.001). Significant correlations were found between SSI and T2-mapping (p < 0.001; ρs = 0.82), ADC all b-values (p = 0.004; ρs = 0.31), ADC high b-values (p < 0.001; ρs = 0.44) and long-TE ADC low b-values (p = 0.004; ρs = 0.31). CONCLUSIONS: Quantitative MR-data allowed us to distinguish UF tissue from myometrium and to discriminate different UF tissue types and may, therefore, be a useful tool to predict treatment outcome/determine optimal treatment modality.

Reliability of residents' assessments of their postgraduate medical education learning environment: an observational study.

BACKGROUND: Even in anonymous evaluations of a postgraduate medical education (PGME) program, residents may be reluctant to provide an honest evaluation of their PGME program, because they fear embarrassment or repercussions from their supervisors if their anonymity as a respondent is endangered. This study was set up to test the hypothesis that current residents in a PGME program provide more positive evaluations of their PGME program than residents having completed it. We therefore compared PGME learning environment evaluations of current residents in the program to leaving residents having completed it. METHODS: This observational study used data gathered routinely in the quality cycle of PGME programs at two Dutch teaching hospitals to test our hypothesis. At both hospitals, all current PGME residents are requested to complete the Scan of Postgraduate Education Environment Domains (SPEED) annually. Residents leaving the hospital after completion of the PGME program are also asked to complete the SPEED after an exit interview with the hospital's independent residency coordinator. All SPEED evaluations are collected and analysed anonymously. We compared the residents' grades (on a continuous scale ranging from 0 (poor) to 10 (excellent)) on the three SPEED domains (content, atmosphere, and organization of the program) and their mean (overall department grade) between current and leaving residents. RESULTS: Mean (SD) overall SPEED department grades were 8.00 (0.52) for 287 current residents in 39 PGME programs and 8.07 (0.48) for 170 leaving residents in 39 programs. Neither the overall SPEED department grades (t test, p = 0.53, 95% CI for difference - 0.16 to 0.31) nor the department SPEED domain grades (MANOVA, F(3, 62) = 0.79, p = 0.51) were significantly different between current and leaving residents. CONCLUSIONS: Residents leaving the program did not provide more critical evaluations of their PGME learning environment than current residents in the program. This suggests that current residents' evaluations of their postgraduate learning environment were not affected by social desirability bias or fear of repercussions from faculty.

Magnetic Resonance-Guided Focused Ultrasound Surgery for Gynecologic Indications.

Magnetic resonance-guided focused ultrasound surgery (MRgFUS) appears to be an effective and safe treatment for uterine fibroids and adenomyosis, particularly in women who wish to preserve fertility. In abdominal wall endometriosis and painful recurrent gynecologic malignancies, MRgFUS can relieve pain, but more research is needed. There is no widespread reimbursement due to the lack of large prospective or randomized controlled trials comparing MRgFUS with standard therapy.

[How well does artificial intelligence detect fractures in the cervical spine on CT?] / Hoe goed detecteert AI fracturen van de cervicale wervelkolom op CT?

OBJECTIVE: To compare diagnostic accuracy of artificial intelligence (AI) for cervical spine (C-spine) fracture detection on CT with attending radiologists. DESIGN: Retrospective, diagnostic accuracy study. METHODS: AI analyzed 2368 scans from patients screened for C-spine fracture with CT (2007-2014, fracture prevalence 9.3%). With the use of a validated reference standard, which includes information on injuries in need of stabilizing therapy (IST), diagnostic accuracy of AI and radiologists was calculated and subsequently compared. RESULTS: Median age was 48 years. AI detected 158/221 fractures and radiologists 195/221, with a sensitivity of respectively 71.5% and 88.2% (p<0.001). Specificity of the AI and the radiologists was comparable: 98.6% and 99.2% (p=0.07). Of the fractures undetected by AI, 30/63 were an IST versus 4/26 for radiologists. AI detected 22/26 scans with fractures undetected by radiologists. CONCLUSION: Compared to attending radiologists, AI has a lower sensitivity and misses more ISTs; however, it detected most fractures undetected by the radiologists, including ISTs.

Development and validation of a deep learning-based method for automatic measurement of uterus, fibroid, and ablated volume in MRI after MR-HIFU treatment of uterine fibroids.

INTRODUCTION: The non-perfused volume divided by total fibroid load (NPV/TFL) is a predictive outcome parameter for MRI-guided high-intensity focused ultrasound (MR-HIFU) treatments of uterine fibroids, which is related to long-term symptom relief. In current clinical practice, the MR-HIFU outcome parameters are typically determined by visual inspection, so an automated computer-aided method could facilitate objective outcome quantification. The objective of this study was to develop and evaluate a deep learning-based segmentation algorithm for volume measurements of the uterus, uterine fibroids, and NPVs in MRI in order to automatically quantify the NPV/TFL. MATERIALS AND METHODS: A segmentation pipeline was developed and evaluated using expert manual segmentations of MRI scans of 115 uterine fibroid patients, screened for and/or undergoing MR-HIFU treatment. The pipeline contained three separate neural networks, one per target structure. The first step in the pipeline was uterus segmentation from contrast-enhanced (CE)-T1w scans. This segmentation was subsequently used to remove non-uterus background tissue for NPV and fibroid segmentation. In the following step, NPVs were segmented from uterus-only CE-T1w scans. Finally, fibroids were segmented from uterus-only T2w scans. The segmentations were used to calculate the volume for each structure. Reliability and agreement between manual and automatic segmentations, volumes, and NPV/TFLs were assessed. RESULTS: For treatment scans, the Dice similarity coefficients (DSC) between the manually and automatically obtained segmentations were 0.90 (uterus), 0.84 (NPV) and 0.74 (fibroid). Intraclass correlation coefficients (ICC) were 1.00 [0.99, 1.00] (uterus), 0.99 [0.98, 1.00] (NPV) and 0.98 [0.95, 0.99] (fibroid) between manually and automatically derived volumes. For manually and automatically derived NPV/TFLs, the mean difference was 5% [-41%, 51%] (ICC: 0.66 [0.32, 0.85]). CONCLUSION: The algorithm presented in this study automatically calculates uterus volume, fibroid load, and NPVs, which could lead to more objective outcome quantification after MR-HIFU treatments of uterine fibroids in comparison to visual inspection. When robustness has been ascertained in a future study, this tool may eventually be employed in clinical practice to automatically measure the NPV/TFL after MR-HIFU procedures of uterine fibroids.

Waste analysis and energy use estimation during MR-HIFU treatment: first steps towards calculating total environmental impact.

OBJECTIVES: To assess the environmental impact of the non-invasive Magnetic Resonance image-guided High-Intensity Focused Ultrasound (MR-HIFU) treatment of uterine fibroids, we aimed to perform a full Life Cycle Assessment (LCA). However, as a full LCA was not feasible at this time, we evaluated the CO2 (carbon dioxide) emission from the MRI scanner, MR-HIFU device, and the medication used, and analyzed solid waste produced during treatment. METHODS: Our functional unit was one uterine fibroid MR-HIFU treatment. The moment the patient entered the day care-unit until she left, defined our boundaries of investigation. We retrospectively collected data from 25 treatments to assess the CO2 emission based on the energy used by the MRI scanner and MR-HIFU device and the amount and type of medication administered. Solid waste was prospectively collected from five treatments. RESULTS: During an MR-HIFU treatment, the MRI scanner and MR-HIFU device produced 33.2 ± 8.7 kg of CO2 emission and medication administered 0.13 ± 0.04 kg. A uterine fibroid MR-HIFU treatment produced 1.2 kg (range 1.1-1.4) of solid waste. CONCLUSIONS: Environmental impact should ideally be analyzed for all (new) medical treatments. By assessing part of the CO2 emission and solid waste produced, we have taken the first steps towards analyzing the total environmental impact of the MR-HIFU treatment of uterine fibroids. These data can contribute to future studies comparing the results of MR-HIFU LCAs with LCAs of other uterine fibroid therapies. CRITICAL RELEVANCE STATEMENT: In addition to (cost-) effectiveness, the environmental impact of new treatments should be assessed. We took the first steps towards analyzing the total environmental impact of uterine fibroid MR-HIFU. KEY POINTS: • Life Cycle Assessments (LCAs) should be performed for all (new) medical treatments. • We took the first steps towards analyzing the environmental impact of uterine fibroid MR-HIFU. • Energy used by the MRI scanner and MR-HIFU device corresponded to 33.2 ± 8.7 kg of CO2 emission.

Image-guided point-shear-wave elastography: a valid and reliable technique for liver fibrotic staging.

PURPOSE: Despite progressive implementation of image-guided point-shear wave elastography (pSWE) in guidelines as an alternative to transient elastography for the staging of fibrotic liver disease, pSWE is not widely adopted in clinical workflow. More information on reliability and validity of pSWE systems is needed. Therefore, we performed a phantom study to evaluate the validity and reliability of pSWE with ultrasound systems. METHODS: Validity and reliability of pSWE measurements from three ultrasound systems were evaluated. Measurements were performed on an elasticity phantom with reference elasticities of 7 ± 1 (low) (median ± interquartile range (IQR)), 14 ± 2 (medium) and 26 ± 3 (high) kPa. Measurements were repeated in tenfold for each reference at 2, 3 and 4 cm depth. Results were considered valid when median elasticity ± IQR was between the uncertainty limits (IQR) for each reference elasticity value and reliable when IQR/median < 0.30. RESULTS: pSWE with the systems provided valid results for all reference elasticities and focal depths, except for overestimation of high reference elasticity at 2 and 4 cm depth for one system (41.5 ± 4.3 and 39.0 ± 1.2 kPa, respectively). Measurements were reliable with a maximum IQR/median of 0.13, well below the guideline of IQR/median < 0.30. DISCUSSION: The results support the use of pSWE as an alternative to invasive or non-image guided noninvasive techniques for liver fibrotic staging. CONCLUSIONS: pSWE with ultrasound systems from different vendors is valid and reliable and can therefore be implemented to optimize clinical workflow by performing imaging and elastography simultaneously.

External validation of the RSNA 2020 pulmonary embolism detection challenge winning deep learning algorithm.

PURPOSE: To evaluate the diagnostic performance and generalizability of the winning DL algorithm of the RSNA 2020 PE detection challenge to a local population using CTPA data from two hospitals. MATERIALS AND METHODS: Consecutive CTPA images from patients referred for suspected PE were retrospectively analysed. The winning RSNA 2020 DL algorithm was retrained on the RSNA-STR Pulmonary Embolism CT (RSPECT) dataset. The algorithm was tested in hospital A on multidetector CT (MDCT) images of 238 patients and in hospital B on spectral detector CT (SDCT) and virtual monochromatic images (VMI) of 114 patients. The output of the DL algorithm was compared with a reference standard, which included a consensus reading by at least two experienced cardiothoracic radiologists for both hospitals. Areas under the receiver operating characteristic curve (AUCs) were calculated. Sensitivity and specificity were determined using the maximum Youden index. RESULTS: According to the reference standard, PE was present in 73 patients (30.7%) in hospital A and 33 patients (29.0%) in hospital B. For the DL algorithm the AUC was 0.96 (95% CI 0.92-0.98) in hospital A, 0.89 (95% CI 0.81-0.94) for conventional reconstruction in hospital B and 0.87 (95% CI 0.80-0.93) for VMI. CONCLUSION: The RSNA 2020 pulmonary embolism detection on CTPA challenge winning DL algorithm, retrained on the RSPECT dataset, showed high diagnostic accuracy on MDCT images. A somewhat lower performance was observed on SDCT images, which suggest additional training on novel CT technology may improve generalizability of this DL algorithm.