Artificial Intelligence-Based Organ Delineation for Radiation Treatment Planning of Prostate Cancer on Computed Tomography.

Purpose: Meticulous manual delineations of the prostate and the surrounding organs at risk are necessary for prostate cancer radiation therapy to avoid side effects to the latter. This process is time consuming and hampered by inter- and intraobserver variability, all of which could be alleviated by artificial intelligence (AI). This study aimed to evaluate the performance of AI compared with manual organ delineations on computed tomography (CT) scans for radiation treatment planning. Methods and Materials: Manual delineations of the prostate, urinary bladder, and rectum of 1530 patients with prostate cancer who received curative radiation therapy from 2006 to 2018 were included. Approximately 50% of those CT scans were used as a training set, 25% as a validation set, and 25% as a test set. Patients with hip prostheses were excluded because of metal artifacts. After training and fine-tuning with the validation set, automated delineations of the prostate and organs at risk were obtained for the test set. Sørensen-Dice similarity coefficient, mean surface distance, and Hausdorff distance were used to evaluate the agreement between the manual and automated delineations. Results: The median Sørensen-Dice similarity coefficient between the manual and AI delineations was 0.82, 0.95, and 0.88 for the prostate, urinary bladder, and rectum, respectively. The median mean surface distance and Hausdorff distance were 1.7 and 9.2 mm for the prostate, 0.7 and 6.7 mm for the urinary bladder, and 1.1 and 13.5 mm for the rectum, respectively. Conclusions: Automated CT-based organ delineation for prostate cancer radiation treatment planning is feasible and shows good agreement with manually performed contouring.

High prevalence of interstitial lung abnormalities in middle-aged never-smokers.

Background: Interstitial lung abnormalities (ILA) are incidental findings on chest computed tomography (CT). These patterns can present at an early stage of fibrotic lung disease. Our aim was to estimate the prevalence of ILA in the Swedish population, in particular in never-smokers, and find out its association with demographics, comorbidities and symptoms. Methods: Participants were recruited to the Swedish CArdioPulmonary BioImage Study (SCAPIS), a population-based survey including men and women aged 50-64 years performed at six university hospitals in Sweden. CT scan, spirometry and questionnaires were performed. ILA were defined as cysts, ground-glass opacities, reticular abnormality, bronchiectasis and honeycombing. Findings: Out of 29 521 participants, 14 487 were never-smokers and 14 380 were men. In the whole population, 2870 (9.7%) had ILA of which 134 (0.5%) were fibrotic. In never-smokers, the prevalence was 7.9% of which 0.3% were fibrotic. In the whole population, age, smoking history, chronic bronchitis, cancer, coronary artery calcium score and high-sensitive C-reactive protein were associated with ILA. Both ILA and fibrotic ILA were associated with restrictive spirometric pattern and impaired diffusing capacity of the lung for carbon monoxide. However, individuals with ILA did not report more symptoms compared with individuals without ILA. Interpretation: ILA are common in a middle-aged Swedish population including never-smokers. ILA may be at risk of being underdiagnosed among never-smokers since they are not a target for screening.

Radiographic airway abnormalities in untreated early rheumatoid arthritis are associated with peripheral neutrophil activation.

BACKGROUND: The role of the lung for the initiation and progression of rheumatoid arthritis (RA) is still unclear. Up to 10% of RA patients develop interstitial lung disease which remains a clinical challenge. Understanding early disease mechanisms is of great importance. The objective of this study was to determine whether there is an association between peripheral neutrophil phenotypes and presence of pulmonary abnormalities (PA) on chest high-resolution computed tomography (HRCT) in untreated early RA (ueRA). METHODS: Clinical data and blood were collected, and HRCT performed at diagnosis on 30 consecutive anti-citrullinated protein antibody (ACPA) and/or rheumatoid factor (RF) positive ueRA patients. HRCTs were evaluated for the presence of RA-associated parenchymal, airway and/or pleural abnormalities. Expression of phenotype markers on neutrophils were determined by flow cytometry. Levels of calprotectin, ACPA and RF were measured using immunoassays. RESULTS: The frequency of having any PA was 60%. Airway abnormalities were present in 50%, parenchymal nodules in 43% and interstitial lung abnormalities (ILA) in 10%. Unsupervised multivariate data analysis showed clustering of any PA with neutrophil activation, parameters of inflammation and RF titres. In univariate analysis, the patients with PA displayed significantly increased CD11b and decreased CD62L expression on neutrophils (1.2-fold, p = 0.014; 0.8-fold, p = 0.012) indicating activation and significantly increased RF IgM titre and CRP (5.7-fold, p = 0.0025; 2.3-fold, p = 0.0035) as compared to no PA. Titres of RF, but not ACPA, correlated with expression of the neutrophil activation marker CD11b. A stratified analysis demonstrated that airway involvement was the PA subtype with the strongest association with neutrophil activation. CONCLUSION: We report a strong association between radiographic airway findings and activation of circulating neutrophils in early RA supporting a role of innate immunity and the lung at disease onset. Our results also indicate different contributions of RF and ACPA in the RA pathogenesis.

Evaluation of deep-learning image reconstruction for chest CT examinations at two different dose levels.

AIMS: The aims of the present study were to, for both a full-dose protocol and an ultra-low dose (ULD) protocol, compare the image quality of chest CT examinations reconstructed using TrueFidelity (Standard kernel) with corresponding examinations reconstructed using ASIR-V (Lung kernel) and to evaluate if post-processing using an edge-enhancement filter affects the noise level, spatial resolution and subjective image quality of clinical images reconstructed using TrueFidelity. METHODS: A total of 25 patients were examined with both a full-dose protocol and an ULD protocol using a GE Revolution APEX CT system (GE Healthcare, Milwaukee, USA). Three different reconstructions were included in the study: ASIR-V 40%, DLIR-H, and DLIR-H with additional post-processing using an edge-enhancement filter (DLIR-H + E2). Five observers assessed image quality in two separate visual grading characteristics (VGC) studies. The results from the studies were statistically analyzed using VGC Analyzer. Quantitative evaluations were based on determination of two-dimensional power spectrum (PS), contrast-to-noise ratio (CNR), and spatial resolution in the reconstructed patient images. RESULTS: For both protocols, examinations reconstructed using TrueFidelity were statistically rated equal to or significantly higher than examinations reconstructed using ASIR-V 40%, but the ULD protocol benefitted more from TrueFidelity. In general, no differences in observer ratings were found between DLIR-H and DLIR-H + E2. For the three investigated image reconstruction methods, ASIR-V 40% showed highest noise and spatial resolution and DLIR-H the lowest, while the CNR was highest in DLIR-H and lowest in ASIR-V 40%. CONCLUSION: The use of TrueFidelity for image reconstruction resulted in higher ratings on subjective image quality than ASIR-V 40%. The benefit of using TrueFidelity was larger for the ULD protocol than for the full-dose protocol. Post-processing of the TrueFidelity images using an edge-enhancement filter resulted in higher image noise and spatial resolution but did not affect the subjective image quality.

Poor inter-observer agreement in anatomical classifications of infrapopliteal arterial disease due to mandatory selection of only one target artery.

BACKGROUND: Established anatomical classifications of infrapopliteal arterial lesion severity are based on assessment of only one target artery, not including all infrapopliteal arteries although multivessel revascularization is common. PURPOSE: To investigate the reproducibility of one of these classifications and a new aggregated score. MATERIAL AND METHODS: A total of 68 patients undergoing endovascular infrapopliteal revascularization at Sahlgrenska University Hospital during 2008-2016 were included. Preoperative magnetic resonance angiographies (MRA) and digital subtraction angiographies (DSA) were evaluated by three blinded observers in random order, using the infrapopliteal TransAtlantic Inter-Society Consensus (TASC) II classification. An aggregated score, the Infrapopliteal Total Atherosclerotic Burden (I-TAB) score, including all infrapopliteal arteries, was constructed and used for comparison. RESULTS: Inter-observer agreement on lesion severity for each evaluated artery was good; Krippendorff's α for MRA 0.64-0.79 and DSA 0.66-0.84. Inter-observer agreement on TASC II grade, based on the selected target artery as stipulated, was poor; Krippendorff's α 0.14 (95% confidence interval [CI]=-0.05 to 0.30) for MRA and 0.48 (95% CI=0.33-0.61) for DSA. Inter-observer agreement for the new I-TAB score was good; Krippendorff's α 0.76 (95% CI=0.70-0.81) for MRA and 0.79 (95% CI=0.74-0.84) for DSA. CONCLUSION: Reproducible assessment of infrapopliteal lesion severity can be achieved for separate arteries with both MRA and DSA using the TASC II definitions. However, poor inter-observer agreement in selecting the target artery results in low reproducibility of the overall infrapopliteal TASC II grade. An aggregated score, such as I-TAB, results in less variability and may provide a more robust evaluation tool of atherosclerotic disease severity.

Endovascular plugs to occlude proximal entries in chronic aortic dissection.

OBJECTIVES: Patients with expanding chronic aortic dissection and patent proximal entries are sometimes poor candidates for open surgery or TEVAR. Occlusion of proximal entries with endovascular plugs has previously been suggested in selected patients, but clinical results over time are unknown. This study analyses aortic remodelling and clinical outcome after proximal entry occlusion. METHODS: Between 2007 and 2016, 14 patients, with expanding chronic aortic dissection, considered poor candidates for standard treatment, were treated with endovascular plugs in proximal entries located in the arch (n = 6) or descending aorta (n = 8). The Amplatzer™ Vascular Plug II was used for entries ≤4 mm and the Amplatzer™ Septal Occluder or Amplatzer™ Muscular VSD Occluder for entries 5-16 mm. Patients were followed for 0.5-13 years (median 7.3) with clinical visits and computed tomography. Diameters and cross-sectional areas along the aorta were measured. RESULTS: Occlusion of proximal entries was achieved in 10/14 patients (71%), including 4 patients with an adjunctive reintervention needed for complete seal in the segment. Unchanged or reduced maximum thoracic aortic diameter was observed in all 10 patients with successful occlusion. In 4 patients, proximal occlusion was not achieved and early conversion to FET (n = 1), FET/TEVAR (n = 2) or TEVAR (n = 1) was performed. Two aorta-related deaths occurred during follow-up, both after early conversion. CONCLUSIONS: Endovascular occlusion of proximal dissection entries of expanding chronic aortic dissections can induce favourable aortic remodelling and may be considered in selected patients with expanding chronic aortic dissection who are poor candidates for open surgery or stent graft repair.

Artificial intelligence based automatic quantification of epicardial adipose tissue suitable for large scale population studies.

To develop a fully automatic model capable of reliably quantifying epicardial adipose tissue (EAT) volumes and attenuation in large scale population studies to investigate their relation to markers of cardiometabolic risk. Non-contrast cardiac CT images from the SCAPIS study were used to train and test a convolutional neural network based model to quantify EAT by: segmenting the pericardium, suppressing noise-induced artifacts in the heart chambers, and, if image sets were incomplete, imputing missing EAT volumes. The model achieved a mean Dice coefficient of 0.90 when tested against expert manual segmentations on 25 image sets. Tested on 1400 image sets, the model successfully segmented 99.4% of the cases. Automatic imputation of missing EAT volumes had an error of less than 3.1% with up to 20% of the slices in image sets missing. The most important predictors of EAT volumes were weight and waist, while EAT attenuation was predicted mainly by EAT volume. A model with excellent performance, capable of fully automatic handling of the most common challenges in large scale EAT quantification has been developed. In studies of the importance of EAT in disease development, the strong co-variation with anthropometric measures needs to be carefully considered.

Erratum: Reliable phase-contrast flow volume magnetic resonance measurements are feasible without adjustment of the velocity encoding parameter.

[This corrects the article DOI: 10.1117/1.JMI.7.6.063502.].

Artificial intelligence-based measurements of PET/CT imaging biomarkers are associated with disease-specific survival of high-risk prostate cancer patients.

OBJECTIVE: Artificial intelligence (AI) offers new opportunities for objective quantitative measurements of imaging biomarkers from positron-emission tomography/computed tomography (PET/CT). Clinical image reporting relies predominantly on observer-dependent visual assessment and easily accessible measures like SUVmax, representing lesion uptake in a relatively small amount of tissue. Our hypothesis is that measurements of total volume and lesion uptake of the entire tumour would better reflect the disease`s activity with prognostic significance, compared with conventional measurements. METHODS: An AI-based algorithm was trained to automatically measure the prostate and its tumour content in PET/CT of 145 patients. The algorithm was then tested retrospectively on 285 high-risk patients, who were examined using 18F-choline PET/CT for primary staging between April 2008 and July 2015. Prostate tumour volume, tumour fraction of the prostate gland, lesion uptake of the entire tumour, and SUVmax were obtained automatically. Associations between these measurements, age, PSA, Gleason score and prostate cancer-specific survival were studied, using a Cox proportional-hazards regression model. RESULTS: Twenty-three patients died of prostate cancer during follow-up (median survival 3.8 years). Total tumour volume of the prostate (p = 0.008), tumour fraction of the gland (p = 0.005), total lesion uptake of the prostate (p = 0.02), and age (p = 0.01) were significantly associated with disease-specific survival, whereas SUVmax (p = 0.2), PSA (p = 0.2), and Gleason score (p = 0.8) were not. CONCLUSION: AI-based assessments of total tumour volume and lesion uptake were significantly associated with disease-specific survival in this patient cohort, whereas SUVmax and Gleason scores were not. The AI-based approach appears well-suited for clinically relevant patient stratification and monitoring of individual therapy.

Importance of through-plane heart motion correction for the assessment of aortic regurgitation severity using phase contrast magnetic resonance imaging.

PURPOSE: To elucidate the influence of through-plane heart motion on the assessment of aortic regurgitation (AR) severity using phase contrast magnetic resonance imaging (PC-MRI). APPROACH: A patient cohort with chronic AR (n = 34) was examined with PC-MRI. The regurgitant volume (RVol) and fraction (RFrac) were extracted from the PC-MRI data before and after through-plane heart motion correction and was then used for assessment of AR severity. RESULTS: The flow volume errors were strongly correlated to aortic diameter (R = 0.80, p < 0.001) with median (IQR 25%;75%): 16 (14; 17) ml for diameter>40mm, compared with 9 (7; 10) ml for normal aortic size (p < 0.001). RVol and RFrac were underestimated (uncorrected:64 ± 37 ml and 39 ± 17%; corrected:76 ± 37 ml and 44 ± 15%; p < 0.001) and ~ 20% of the patients received lower severity grade without correction. CONCLUSION: Through-plane heart motion introduces relevant flow volume errors, especially in patients with aortic dilatation that may result in underestimation of the severity grade in patients with chronic AR.

A Reperfusion BOLD-MRI Tissue Perfusion Protocol Reliably Differentiate Patients with Peripheral Arterial Occlusive Disease from Healthy Controls.

There is no established technique that directly quantifies lower limb tissue perfusion. Blood oxygenation level-dependent magnetic resonance imaging (BOLD-MRI) is an MRI technique that can determine skeletal muscle perfusion. BOLD-MRI relies on magnetic differences of oxygenated and deoxygenated hemoglobin, and regional changes in oxy/deoxyhemoglobin ratio can be recorded by T2* weighted MRI sequences. We aimed to test whether BOLD-MRI can differentiate lower limb tissue perfusion in peripheral arterial occlusive disease (PAOD) patients and healthy controls. Twenty-two PAOD patients and ten healthy elderly volunteers underwent lower limb BOLD-MRI. Reactive hyperemia was provoked by transient cuff compression and images of the gastrocnemius and soleus muscles were continuously acquired at rest, during ischemia and reperfusion. Key BOLD parameters were baseline T2* absolute value and time to T2* peak value after cuff deflation (TTP). Correlations between imaging parameters and ankle-brachial index (ABI) was investigated. The mean TTP was considerably prolonged in PAOD patients compared to healthy controls (m. gastrocnemius: 111 ± 46 versus 48 ± 22 s, p = 0.000253; m. soleus: 100 ± 42 versus 41 ± 30 s, p = 0.000216). Both gastrocnemius and soleus TTP values correlated strongly with ABI (-0.82 and -0.78, p < 0.01). BOLD-MRI during reactive hyperemia differentiated most PAOD patients from healthy controls. TTP was the most decisive parameter and strongly correlated with the ABI.

Importance of complex blood flow in the assessment of aortic regurgitation severity using phase contrast magnetic resonance imaging.

This study aimed to investigate if and how complex flow influences the assessment of aortic regurgitation (AR) using phase contrast MRI in patients with chronic AR. Patients with moderate (n = 15) and severe (n = 28) chronic AR were categorized into non-complex flow (NCF) or complex flow (CF) based on the presence of systolic backward flow volume. Phase contrast MRI was performed repeatedly at the level of the sinotubular junction (Ao1) and 1 cm distal to the sinotubular junction (Ao2). All AR patients were assessed to have non-severe AR or severe AR (cut-off values: regurgitation volume (RVol) ≥ 60 ml and regurgitation fraction (RF) ≥ 50%) in both measurement positions. The repeatability was significantly lower, i.e. variation was larger, for patients with CF than for NCF (≥ 12 ± 12% versus ≥ 6 ± 4%, P ≤ 0.03). For patients with CF, the repeatability was significantly lower at Ao2 compared to Ao1 (≥ 21 ± 20% versus ≥ 12 ± 12%, P ≤ 0.02), as well as the assessment of regurgitation (RVol: 42 ± 34 ml versus 54 ± 42 ml, P < 0.001; RF: 30 ± 18% versus 34 ± 16%, P = 0.01). This was not the case for patients with NCF. The frequency of patients that changed in AR grade from severe to non-severe when the position of the measurement changed from Ao1 to Ao2 was higher for patients with CF compared to NCF (RVol: 5/26 (19%) versus 1/17 (6%), P = 0.2; RF: 4/26 (15%) versus 0/17 (0%), P = 0.09). Our study shows that complex flow influences the quantification of chronic AR, which can lead to underestimation of AR severity when using PC-MRI.

EVALUATION OF TWO CHEST TOMOSYNTHESIS CYSTIC FIBROSIS SCORING SYSTEMS USING HIGH-RESOLUTION COMPUTED TOMOGRAPHY BRODY SCORING AS REFERENCE.

PURPOSE: To evaluate two chest tomosynthesis (CTS) scoring systems for cystic fibrosis (CF), one system developed by Vult von Steyern et al. (VvS) and one system based on the Brody scoring system for high-resolution computed tomography (HRCT) (modified Brody (mB)). Brody scoring of HRCT was used as reference. METHODS: In conjunction with routine control HRCT at clinical follow-up, 10 consecutive adult CF patients underwent CTS for research purposes. Four radiologists scored the CTS examinations using the mB and VvS scoring systems. All scores were compared to the Brody HRCT scores. The agreement between the evaluated CTS scoring systems and the reference HRCT scoring system was determined using Spearman's rank correlation coefficient and the intraclass correlation coefficient (ICC). MAJOR FINDINGS: Spearman's rank correlation coefficient showed strong correlations between HRCT score and both the mB and the VvS CTS total scores (median rs = 0.81 and 0.85, respectively). The ICC showed strong correlation between the CTS scoring systems and the reference: 0.88 for mB and 0.85 for VvS scoring. The median time for scoring was 20 and 10 minutes for the mB and VvS scoring systems, respectively. CONCLUSIONS: Both evaluated CTS scoring systems correlate well with the reference standard Brody HRCT scoring. The VvS CTS scoring system has a shorter reading time, suggesting its advantage in clinical practice.

EXTRACOLONIC FINDINGS-IDENTIFICATION AT LOW-DOSE CTC.

In contrast to optical colonoscopy, computed tomography colonography (CTC) has the ability to reveal pathology outside of the colon. While identification of colorectal lesions at CTC requires only limited radiation dose, the detection of abnormalities in extracolonic soft tissue requires more radiation. The purpose of this study was to investigate the influence of ultra-low-dose (ULD) CTC on the detection and characterisation of extracolonic findings. In a prospective study 49 patients with colorectal symptoms were examined with CTC adding a ULD series (mean effective dose 0.9 ± 0.4 mSv) to the normal unenhanced standard dose (SD) series (mean effective dose 3.6 ± 1.2 mSv). Five radiologists individually and blindly evaluated the ULD, followed by evaluation of the SD after ≥9 weeks (median 35 weeks). A ViewDEX-based examination protocol was used, including a confidence scale and a graded assessment of need for follow-up according to the CTC Reporting and Data System (C-RADS E0-E4). The reference findings comprised the combined information from CTC (ULD, SD and contrast-enhanced CTC series) and a 4-year radiological and clinical follow-up. For the overall detection of reference findings (E2-E4) we found a statistically significant difference in favour of SD. This, however, was not the case when looking at classification of possibly important/important reference findings (E3-E4). Our results suggest that CTC with ULD (0.9 mSv) is comparable to SD (3.6 mSv) for identification of clinically relevant extracolonic pathology, but there is a large inter-observer variability.

Surveillance of small, solid pulmonary nodules at digital chest tomosynthesis: data from a cohort of the pilot Swedish CArdioPulmonary bioImage Study (SCAPIS).

BACKGROUND: Digital tomosynthesis (DTS) might be a low-dose/low-cost alternative to computed tomography (CT). PURPOSE: To investigate DTS relative to CT for surveillance of incidental, solid pulmonary nodules. MATERIAL AND METHODS: Recruited from a population study, 106 participants with indeterminate solid pulmonary nodules on CT underwent surveillance with concurrently performed CT and DTS. Nodule size on DTS was assessed by manual diameter measurements and semi-automatic nodule segmentations were independently performed on CT. Measurement agreement was analyzed according to Bland-Altman with 95% limits of agreement (LoA). Detection of nodule volume change > 25% by DTS in comparison to CT was evaluated with receiver operating characteristics (ROC). RESULTS: A total of 81 nodules (76%) were assessed as measurable on DTS by two independent observers. Inter- and intra-observer LoA regarding change in average diameter were ± 2 mm. Calculation of relative volume change on DTS resulted in wide inter- and intra-observer LoA in the order of ± 100% and ± 50%. Comparing relative volume change between DTS and CT resulted in LoA of -58% to 67%. The area under the ROC curve regarding the ability of DTS to detect volumetric changes > 25% on CT was 0.58 (95% confidence interval [CI] = 0.40-0.76) and 0.50 (95% CI = 0.35-0.66) for the two observers. CONCLUSION: The results of the present study show that measurement variability limits the agreement between DTS and CT regarding nodule size change for small solid nodules.

The Effect of Dose Reduction on Overall Image Quality in Clinical Chest Tomosynthesis.

RATIONALE AND OBJECTIVES: To evaluate the effect of reduction in effective dose on the reproduction of anatomical structures in chest tomosynthesis (CTS). MATERIALS AND METHODS: Twenty-four CTS examinations acquired at exposure settings resulting in an effective dose of 0.12 mSv for an average sized patient were included in the study. The examinations underwent simulated dose reduction to dose levels corresponding to 32%, 50%, and 70% of the original dose using a previously described and validated method. The image quality was evaluated by five thoracic radiologists who rated the fulfillment of specified image quality criteria in a visual grading study. The ratings for each image quality criterion in the dose-reduced images were compared to the corresponding ratings for the full-dose examinations using visual grading characteristics (VGC) analysis. The area under the resulting VGC curve (AUCVGC) provides a measure of the difference between the ratings, where an AUCVGC of 0.5 indicates no difference. RESULTS: The dose reductions resulted in inferior reproduction of structures compared to the original dose level (AUCVGC <0.5). Structures in the central region of the lung obtained the lowest AUCVGC for each dose level whereas the reproduction of structures in the parenchyma was least affected by the dose reduction. CONCLUSION: Although previous studies have shown that dose reduction in CTS is possible without affecting the performance of certain clinical tasks, the reproduction of normal anatomical structures is significantly degraded even at small reductions. It is therefore important to consider the clinical purpose of the CTS examinations before deciding on a permanent dose reduction.

Reliable phase-contrast flow volume magnetic resonance measurements are feasible without adjustment of the velocity encoding parameter.

Purpose: To show that adjustment of velocity encoding (VENC) for phase-contrast (PC) flow volume measurements is not necessary in modern MR scanners with effective background velocity offset corrections. Approach: The independence on VENC was demonstrated theoretically, but also experimentally on dedicated phantoms and on patients with chronic aortic regurgitation ( n = 17 ) and one healthy volunteer. All PC measurements were performed using a modern MR scanner, where the pre-emphasis circuit but also a subsequent post-processing filter were used for effective correction of background velocity offset errors. Results: The VENC level strongly affected the velocity noise level in the PC images and, hence, the estimated peak flow velocity. However, neither the regurgitant blood flow volume nor the mean flow velocity displayed any clinically relevant dependency on the VENC level. Also, the background velocity offset was shown to be close to zero ( < 0.6 cm / s ) for a VENC range of 150 to 500 cm / s , adding no significant errors to the PC flow volume measurement. Conclusions: Our study shows that reliable PC flow volume measurements are feasible without adjustment of the VENC parameter. Without the need for VENC adjustments, the scan time can be reduced for the benefit of the patient.

Comparison of Magnetic Resonance Angiography and Digital Subtraction Angiography for the Assessment of Infrapopliteal Arterial Occlusive Lesions, Based on the TASC II Classification Criteria.

This paper aimed to study the agreement and repeatability, both intra- and interobserver, of infrapopliteal lesion assessment with magnetic resonance angiography (MRA), using the TransAtlantic Inter-Society Consensus (TASC) II criteria, with perioperative digital subtraction angiography (DSA) as a reference. Sixty-eight patients with an MRA preceding an endovascular infrapopliteal revascularization were included. Preoperative MRAs and perioperative DSAs were evaluated in random order by three independent observers using the TASC II classification. The results were analyzed using visual grading characteristics (VGC) analysis and Krippendorff's α. No systematic difference was found between modalities: area under the VGC curve (AUCVGC) = 0.48 (p = 0.58) or intraobserver; AUCVGC for Observer 1 and 2 respectively, 0.49 (p = 0.85) and 0.53 (p = 0.52) for MRA compared with 0.54 (p = 0.30) and 0.49 (p = 0.81) for DSA. Interobserver differences were seen: AUCVGC of 0.63 (p < 0.01) for DSA and 0.80 (p < 0.01) for MRA. These results were confirmed using Krippendorff's α for the three observers showing 0.13 (95% confidence interval (CI) -0.07-0.31) for MRA and 0.39 (95% CI 0.23-0.53) for DSA. Poor interobserver agreement was also found in the choice of a target vessel on preoperative MRA: Krippendorff's α = 0.19 (95% CI 0.01‒0.36). In conclusion, infrapopliteal lesions can be reliably determined on preoperative MRA, but interobserver variability regarding the choice of a target vessel is a major concern that appears to affect the overall TASC II grade.

Visual and Quantitative Evaluation of Emphysema: A Case-Control Study of 1111 Participants in the Pilot Swedish CArdioPulmonary BioImage Study (SCAPIS).

RATIONALE AND OBJECTIVES: Emphysema is a hallmark of chronic obstructive pulmonary disease. The primary aim of this study was to investigate inter- and intraobserver agreement of visual assessment of mild emphysema in low-dose multidetector computed tomography of subjects in the pilot SCAPIS in order to certify consistent detection of mild emphysema. The secondary aim was to investigate the performance of quantitative densitometric measurements in the cohort. MATERIALS AND METHODS: Participants with emphysema (n = 100, 56 males and 44 females) reported in the electronic case report form of pilot SCAPIS and 100 matched controls (gender, age, height, and weight) without emphysema were included. To assess interobserver variability the randomized examinations were evaluated by two thoracic radiologists. For intraobserver variability three radiologists re-evaluated randomized examinations which they originally evaluated. The results were evaluated statistically by Krippendorff's α. The dataset was also assessed quantitively for % lung attenuation value -950 HU (LAV950), mean lung density and total lung volume by commercially available software. RESULTS: Emphysema was visually scored as mild and Krippendorff's α was ≥0.8 for both the inter- and intraobserver agreement regarding presence of emphysema and approaching 0.8 regarding presence and extent of emphysema by location in the upper lobes. Mean LAV950 was not different between the emphysematous and the nonemphysematous participants; 8.3% and 8.4%, respectively. CONCLUSION: The inter- and intraobserver agreement for visual detection of mild emphysema in low-dose multidetector computed tomography was good. Surprisingly, quantitative analysis could not reliably identify participants with mild emphysema, which hampers the use of automatic evaluation.

Deep learning-based quantification of PET/CT prostate gland uptake: association with overall survival.

AIM: To validate a deep-learning (DL) algorithm for automated quantification of prostate cancer on positron emission tomography/computed tomography (PET/CT) and explore the potential of PET/CT measurements as prognostic biomarkers. MATERIAL AND METHODS: Training of the DL-algorithm regarding prostate volume was performed on manually segmented CT images in 100 patients. Validation of the DL-algorithm was carried out in 45 patients with biopsy-proven hormone-naïve prostate cancer. The automated measurements of prostate volume were compared with manual measurements made independently by two observers. PET/CT measurements of tumour burden based on volume and SUV of abnormal voxels were calculated automatically. Voxels in the co-registered 18 F-choline PET images above a standardized uptake value (SUV) of 2·65, and corresponding to the prostate as defined by the automated segmentation in the CT images, were defined as abnormal. Validation of abnormal voxels was performed by manual segmentation of radiotracer uptake. Agreement between algorithm and observers regarding prostate volume was analysed by Sørensen-Dice index (SDI). Associations between automatically based PET/CT biomarkers and age, prostate-specific antigen (PSA), Gleason score as well as overall survival were evaluated by a univariate Cox regression model. RESULTS: The SDI between the automated and the manual volume segmentations was 0·78 and 0·79, respectively. Automated PET/CT measures reflecting total lesion uptake and the relation between volume of abnormal voxels and total prostate volume were significantly associated with overall survival (P = 0·02), whereas age, PSA, and Gleason score were not. CONCLUSION: Automated PET/CT biomarkers showed good agreement to manual measurements and were significantly associated with overall survival.