Development and validation of AI-derived segmentation of four-chamber cine cardiac magnetic resonance.

BACKGROUND: Cardiac magnetic resonance (CMR) in the four-chamber plane offers comprehensive insight into the volumetrics of the heart. We aimed to develop an artificial intelligence (AI) model of time-resolved segmentation using the four-chamber cine. METHODS: A fully automated deep learning algorithm was trained using retrospective multicentre and multivendor data of 814 subjects. Validation, reproducibility, and mortality prediction were evaluated on an independent cohort of 101 subjects. RESULTS: The mean age of the validation cohort was 54 years, and 66 (65%) were males. Left and right heart parameters demonstrated strong correlations between automated and manual analysis, with a ρ of 0.91-0.98 and 0.89-0.98, respectively, with minimal bias. All AI four-chamber volumetrics in repeatability analysis demonstrated high correlation (ρ = 0.99-1.00) and no bias. Automated four-chamber analysis underestimated both left ventricular (LV) and right ventricular (RV) volumes compared to ground-truth short-axis cine analysis. Two correction factors for LV and RV four-chamber analysis were proposed based on systematic bias. After applying the correction factors, a strong correlation and minimal bias for LV volumetrics were observed. During a mean follow-up period of 6.75 years, 16 patients died. On stepwise multivariable analysis, left atrial ejection fraction demonstrated an independent association with death in both manual (hazard ratio (HR) = 0.96, p = 0.003) and AI analyses (HR = 0.96, p < 0.001). CONCLUSION: Fully automated four-chamber CMR is feasible, reproducible, and has the same real-world prognostic value as manual analysis. LV volumes by four-chamber segmentation were comparable to short-axis volumetric assessment. TRIALS REGISTRATION: ClinicalTrials.gov: NCT05114785. RELEVANCE STATEMENT: Integrating fully automated AI in CMR promises to revolutionise clinical cardiac assessment, offering efficient, accurate, and prognostically valuable insights for improved patient care and outcomes. KEY POINTS: • Four-chamber cine sequences remain one of the most informative acquisitions in CMR examination. • This deep learning-based, time-resolved, fully automated four-chamber volumetric, functional, and deformation analysis solution. • LV and RV were underestimated by four-chamber analysis compared to ground truth short-axis segmentation. • Correction bias for both LV and RV volumes by four-chamber segmentation, minimises the systematic bias.

Utility of a 2D kinematic HASTE sequence in magnetic resonance imaging assessment of adjacent segment degeneration following anterior cervical discectomy and fusion.

OBJECTIVES: To evaluate a dynamic half-Fourier acquired single turbo spin echo (HASTE) sequence following anterior cervical discectomy and fusion (ACDF) at the junctional level for adjacent segment degeneration comparing dynamic listhesis to radiographs and assessing dynamic cord contact and deformity during flexion-extension METHODS: Patients with ACDF referred for cervical spine MRI underwent a kinematic flexion-extension sagittal 2D HASTE sequence in addition to routine sequences. Images were independently reviewed by three radiologists for static/dynamic listhesis, and compared to flexion-extension radiographs. Blinded assessment of the HASTE sequence was performed for cord contact/deformity between neutral, flexion, and extension, to evaluate concordance between readers and inter-modality agreement. Inter-reader agreement for dynamic listhesis and impingement grade and inter-modality agreement for dynamic listhesis on MRI and radiographs was assessed using the kappa coefficient and percentage concordance. RESULTS: A total of 28 patients, mean age 60.2 years, were included. Mean HASTE acquisition time was 42 s. 14.3% demonstrated high grade dynamic stenosis (> grade 4) at the adjacent segment. There was substantial agreement for dynamic cord impingement with 70.2% concordance (kappa = 0.62). Concordance across readers for dynamic listhesis using HASTE was 81.0% (68/84) (kappa = 0.16) compared with 71.4% (60/84) (kappa = 0.40) for radiographs. Inter-modality agreement between flexion-extension radiographs and MRI assessment for dynamic listhesis across the readers was moderate (kappa = 0.41; 95% confidence interval: 0.16 to 0.67). CONCLUSIONS: A sagittal flexion-extension HASTE cine sequence provides substantial agreement between readers for dynamic cord deformity and moderate agreement between radiographs and MRI for dynamic listhesis. CLINICAL RELEVANCE STATEMENT: Degeneration of the adjacent segment with instability and myelopathy is one of the most common causes of pain and neurological deterioration requiring re-operation following cervical fusion surgery. KEY POINTS: • A real-time kinematic 2D sagittal HASTE flexion-extension sequence can be used to assess for dynamic listhesis, cervical cord, contact and deformity. • The additional kinematic cine sequence was well tolerated and the mean acquisition time for the 2D HASTE sequence was 42 s (range 31-44 s). • A sagittal flexion-extension HASTE cine sequence provides substantial agreement between readers for dynamic cord deformity and moderate agreement between radiographs and MRI for dynamic listhesis.

Preliminary study of cine-MRI compression in MR-guided radiotherapy.

Background: Cine-magnetic resonance imaging (MRI) is currently used in real-time tumor tracking during magnetic resonance (MR)-guided radiotherapy. As a type of MRI specified for motion tracking, a few minutes' acquisition results in thousands of 2-dimensional (2D) images. For MR-guided radiotherapy consisting of multiple treatment fractions, the large number of cine-MRI images would be disproportionate to the tight clinical data storage available. To alleviate this issue, the feasibility of compression of cine-MRI via video encoders was investigated in this study. Methods: The cine-MRI images were first sorted into 3 sequences according to their plane orientations. Then, each sequence was reordered according to their acquisition times [time-based (TB)] or content similarities [similarity-based (SB)]. As a result, 3 sequences were obtained for 3 plan orientations. Next, the obtained sequences were processed by a video encoder and the corresponding 3 video files were achieved. We employed 3 popular video encoders: Motion JPEG (M-JPEG), Advanced Video Coding (AVC), and High Efficiency Video Coding (HEVC). The performances of the sequence reordering methods and video encoders were evaluated based on a total of 150 image sets. Results: The mean correlation quantities for SB sequences were higher than those for TB sequences by 3% (sagittal), 2% (coronal), and 1% (transverse), respectively. The average compression ratio (CR) yielded by the SB sequences was higher than that achieved by the TB sequences. Comparing with M-JPEG, the CRs obtained by AVC and HEVC were increased by 58% and 62% (sagittal), 16% and 23% (coronal), and 48% and 56% (transverse), respectively. Among the 3 video encoders, the highest CRs and restoration accuracy were achieved by HEVC. Conclusions: HEVC with inter-frame coding is more effective in reducing the redundant information in consecutive images. It is feasible to implement the video encoder for high-performance cine-MRI compression.

Crohn's disease: review and standardization of nomenclature.

Crohn's disease is an inflammatory bowel disease that can affect any segment of the gastrointestinal tract. It has a variable clinical course, with alternating periods of disease activity and remission. Because the incidence and prevalence of Crohn's disease have been increasing, evaluation by imaging methods has become more important. The most widely used methods are computed tomography enterography, magnetic resonance enterography (as an elective examination), and contrast-enhanced computed tomography (in the context of emergency). Computed tomography enterography and magnetic resonance enterography are useful for diagnosis, follow-up, evaluation of complications, and prognosis. Both can be used in order to evaluate the small bowel loops and the associated mesenteric findings, as well as to evaluate other abdominal organs. They both also can detect signs of disease activity, fibrosis, penetrating disease, and complications. The interpretation of such changes is essential to the multidisciplinary approach, as is the standardization of the nomenclature employed in the reports. In this paper, we review and illustrate the imaging findings of Crohn's disease, using the standardized nomenclature proposed in the multidisciplinary consensus statement issued by the Society of Abdominal Radiology, the Society of Pediatric Radiology, and the American Gastroenterology Association, with recommendations for descriptions, interpretations, and impressions related to those findings.

Doença de Crohn é uma doença inflamatória intestinal que pode acometer qualquer segmento do trato gastrointestinal, com curso clínico variado, alternando períodos de atividade de doença e remissão. Sua incidência e prevalência vêm aumentando, tornando a avaliação por métodos de imagem mais importante. Os métodos mais utilizados são enterotomografia computadorizada, enterorressonância magnética eletivamente e tomografia computadorizada com contraste no contexto da emergência. A enterotomografia computadorizada e a enterorressonância magnética são úteis para diagnóstico, seguimento, avaliação de complicações e para prognóstico. Avaliam as alças intestinais delgadas e os achados mesentéricos associados, além dos demais órgãos abdominais. Detectam sinais de atividade de doença, sinais de cronicidade e doença penetrante e complicações, importantes para a escolha do melhor tratamento. A interpretação dessas alterações é fundamental para que a equipe multidisciplinar trabalhe conjuntamente com compreensão da linguagem utilizada nos relatórios. Neste artigo, apresentamos uma revisão dos achados de imagem da doença de Crohn e ilustramos os possíveis achados dessa doença utilizando a nomenclatura padronizada proposta no consenso multidisciplinar composto pelas Sociedade de Radiologia Abdominal, Sociedade de Radiologia Pediátrica e a Associação Americana de Gastroenterologia, com recomendações de descrição, interpretação dos achados e recomendações de impressão.

Crohn's disease: review and standardization of nomenclature / Doença de Crohn: revisão e padronização da nomenclatura

Abstract Crohn's disease is an inflammatory bowel disease that can affect any segment of the gastrointestinal tract. It has a variable clinical course, with alternating periods of disease activity and remission. Because the incidence and prevalence of Crohn's disease have been increasing, evaluation by imaging methods has become more important. The most widely used methods are computed tomography enterography, magnetic resonance enterography (as an elective examination), and contrast-enhanced computed tomography (in the context of emergency). Computed tomography enterography and magnetic resonance enterography are useful for diagnosis, follow-up, evaluation of complications, and prognosis. Both can be used in order to evaluate the small bowel loops and the associated mesenteric findings, as well as to evaluate other abdominal organs. They both also can detect signs of disease activity, fibrosis, penetrating disease, and complications. The interpretation of such changes is essential to the multidisciplinary approach, as is the standardization of the nomenclature employed in the reports. In this paper, we review and illustrate the imaging findings of Crohn's disease, using the standardized nomenclature proposed in the multidisciplinary consensus statement issued by the Society of Abdominal Radiology, the Society of Pediatric Radiology, and the American Gastroenterology Association, with recommendations for descriptions, interpretations, and impressions related to those findings.

Resumo Doença de Crohn é uma doença inflamatória intestinal que pode acometer qualquer segmento do trato gastrointestinal, com curso clínico variado, alternando períodos de atividade de doença e remissão. Sua incidência e prevalência vêm aumentando, tornando a avaliação por métodos de imagem mais importante. Os métodos mais utilizados são enterotomografia computadorizada, enterorressonância magnética eletivamente e tomografia computadorizada com contraste no contexto da emergência. A enterotomografia computadorizada e a enterorressonância magnética são úteis para diagnóstico, seguimento, avaliação de complicações e para prognóstico. Avaliam as alças intestinais delgadas e os achados mesentéricos associados, além dos demais órgãos abdominais. Detectam sinais de atividade de doença, sinais de cronicidade e doença penetrante e complicações, importantes para a escolha do melhor tratamento. A interpretação dessas alterações é fundamental para que a equipe multidisciplinar trabalhe conjuntamente com compreensão da linguagem utilizada nos relatórios. Neste artigo, apresentamos uma revisão dos achados de imagem da doença de Crohn e ilustramos os possíveis achados dessa doença utilizando a nomenclatura padronizada proposta no consenso multidisciplinar composto pelas Sociedade de Radiologia Abdominal, Sociedade de Radiologia Pediátrica e a Associação Americana de Gastroenterologia, com recomendações de descrição, interpretação dos achados e recomendações de impressão.

A 72-channel receive array coil allows whole-heart cine MRI in two breath holds.

BACKGROUND: A new 72-channel receive array coil and sensitivity encoding, compressed (C-SENSE) and noncompressed (SENSE), were investigated to decrease the number of breath-holds (BHs) for cardiac magnetic resonance (CMR). METHODS: Three-T CMRs were performed using the 72-channel coil with SENSE-2/4/6 and C-SENSE-2/4/6 accelerated short-axis cine two-dimensional balanced steady-state free precession sequences. A 16-channel coil with SENSE-2 served as reference. Ten healthy subjects were included. BH-time was kept under 15 s. Data were compared in terms of image quality, biventricular function, number of BHs, and scan times. RESULTS: BHs decreased from 7 with C-SENSE-2 (scan time 70 s, 2 slices/BH) to 3 with C-SENSE-4 (scan time 42 s, 4-5 slices/BH) and 2 with C-SENSE-6 (scan time 28 s, 7 slices/BH). Compared to reference, image sharpness was similar for SENSE-2/4/6, slightly inferior for C-SENSE-2/4/6. Blood-to-myocardium contrast was unaffected. C-SENSE-4/6 was given lower qualitative median scores, but images were considered diagnostically adequate to excellent, with C-SENSE-6 suboptimal. Biventricular end-diastolic (EDV), end-systolic (ESV) and stroke volumes, ejection fractions (EF), cardiac outputs, and left ventricle (LV)-mass were similar for SENSE-2/4/6 with no systematic bias and clinically appropriate limits of agreements. C-SENSE slightly underestimated LV-EDV (-6.38 ± 6.0 mL, p < 0.047), LV-ESV (-7.94 ± 6.0 mL, p < 0.030) and overestimated LV-EF (3.16 ± 3.10%; p < 0.047) with C-SENSE-4. Bland-Altman analyses revealed minor systematic biases in these variables with C-SENSE-2/4/6 and for LV-mass with C-SENSE-6. CONCLUSIONS: Using the 72-channel coil, short-axis CMR for quantifying biventricular function was feasible in two BHs where SENSE slightly outperformed C-SENSE.

Cine phase-contrast magnetic resonance imaging evaluation of cerebrospinal fluid flow dynamics in healthy pediatric subjects / Avaliação da dinâmica do fluxo do líquido cerebrospinal por cine-ressonância magnética com contraste de fase em crianças saudáveis

Abstract Objective: To evaluate cerebrospinal fluid dynamics, using cine phase-contrast magnetic resonance imaging (cine-PC MRI), in healthy pediatric subjects, determining the normal flow values in this population, as well as identifying differences related to age, sex, and body surface area. Materials and Methods: This was a descriptive cross-sectional study involving 32 healthy children and adolescents, in whom the flow of cerebrospinal fluid through the cerebral aqueduct was evaluated quantitatively with cine-PC MRI. We used specialized software to analyze the images obtained with cine-PC MRI, drawing a region of interest on the aqueduct. A flow-time curve was obtained, as were automated measurements of the various parameters. Results: The following normal (mean) values were obtained: net flow, 1.10 ± 0.99 mL/m; stroke volume, 12.2 ± 10.1 μL/cycle; mean velocity, 0.72 ± 1.00 cm/s; peak systolic velocity, 5.28 ± 2.30 cm/s; peak diastolic velocity, 4.51 ± 1.77 cm/s. These values were not affected by age or sex. In addition, body surface area was not found to correlate significantly with mean velocity or stroke volume. Conclusion: In children and adolescents, the basic cerebrospinal fluid flow parameters, as determined by cine-PC MRI, appear to be independent of age and sex.

Resumo Objetivo: Avaliar a dinâmica do fluxo do líquido cerebrospinal por cine-ressonância magnética com contraste de fase em crianças saudáveis, para determinar os valores normais de fluxo nesta população, bem como a diferença entre medições distintas de acordo com idade, sexo ou área da superfície corporal. Materiais e Métodos: Convocamos 32 crianças saudáveis em uma análise descritiva de prevalência para a avaliação quantitativa do fluxo do líquido cerebrospinal pelo aqueduto de Sylvius. A análise foi realizada por meio de software especializado, desenhando uma região de interesse no aqueduto. Uma curva de fluxo-tempo e medições automáticas de diversos parâmetros foram obtidas. Resultados: Os seguintes valores normais foram obtidos: fluxo efetivo de 1,10 ± 0,99 mL/m; volume médio de 12,2 ± 10,1 μL/ciclo; velocidade média de 0,72 ± 1,00 cm/s; pico de velocidade sistólica de 5,28 ± 2,30 cm/s; pico de velocidade diastólica de 4,51 ± 1,77 cm/s. Esses valores não foram afetados pela idade ou sexo das crianças. Além disso, não foi encontrada correlação significativa entre a área corporal, a velocidade média e o volume sistólico. Conclusão: De modo geral, os parâmetros básicos do fluxo do líquido cerebrospinal independem de idade e sexo em crianças.

Assessment of hepatic arterial hemodynamics with 4D flow MRI: in vitro analysis of motion and spatial resolution related error and in vivo feasibility study in 20 volunteers.

OBJECTIVES: To assess the ability of four-dimensional (4D) flow MRI to measure hepatic arterial hemodynamics by determining the effects of spatial resolution and respiratory motion suppression in vitro and its applicability in vivo with comparison to two-dimensional (2D) phase-contrast MRI. METHODS: A dynamic hepatic artery phantom and 20 consecutive volunteers were scanned. The accuracies of Cartesian 4D flow sequences with k-space reordering and navigator gating at four spatial resolutions (0.5- to 1-mm isotropic) and navigator acceptance windows (± 8 to ± 2 mm) and one 2D phase-contrast sequence (0.5-mm in -plane) were assessed in vitro at 3 T. Two sequences centered on gastroduodenal and hepatic artery branches were assessed in vivo for intra - and interobserver agreement and compared to 2D phase-contrast. RESULTS: In vitro, higher spatial resolution led to a greater decrease in error than narrower navigator window (30.5 to -4.67% vs -6.64 to -4.67% for flow). In vivo, hepatic and gastroduodenal arteries were more often visualized with the higher resolution sequence (90 vs 71%). Despite similar interobserver agreement (κ = 0.660 and 0.704), the higher resolution sequence had lower variability for area (CV = 20.04 vs 30.67%), flow (CV = 34.92 vs 51.99%), and average velocity (CV = 26.47 vs 44.76%). 4D flow had lower differences between inflow and outflow at the hepatic artery bifurcation (11.03 ± 5.05% and 15.69 ± 6.14%) than 2D phase-contrast (28.77 ± 21.01%). CONCLUSION: High-resolution 4D flow can assess hepatic artery anatomy and hemodynamics with improved accuracy, greater vessel visibility, better interobserver reliability, and internal consistency. KEY POINTS: • Motion-suppressed Cartesian four-dimensional (4D) flow MRI with higher spatial resolution provides more accurate measurements even when accepted respiratory motion exceeds voxel size. • 4D flow MRI with higher spatial resolution provides substantial interobserver agreement for visualization of hepatic artery branches. • Lower peak and average velocities and a trend toward better internal consistency were observed with 4D flow MRI as compared to 2D phase-contrast.

The prognostic value of global myocardium strain by CMR-feature tracking in immune checkpoint inhibitor-associated myocarditis.

OBJECTIVES: Immune checkpoint inhibitor (ICI)-associated myocarditis is a potentially fatal complication. Sparse published researches evaluated the prognostic value of cardiovascular magnetic resonance feature tracking (CMR-FT) for ICI-associated myocarditis. METHODS: In the single-center retrospective study, 52 patients with ICI-associated myocarditis and CMR were included from August 2018 to July 2021. The ICI-associated myocarditis was diagnosed by using the clinical criteria of the European Society of Cardiology guidelines. Major adverse cardiovascular events (MACE) were comprised of cardiovascular death, cardiogenic shock, cardiac arrest, and complete heart block. RESULTS: During a median follow-up of 171 days, 14 (27%) patients developed MACE. For patients with MACE, the global circumferential strain (GCS), global radial strain (GRS), global longitudinal strain (GLS), and left ventricular ejection fraction (LVEF) were significantly worse and native T1 values and late gadolinium enhancement (LGE) extent were significantly increased, compared with patients without MACE (p < 0.05). The GLS remained the independent factor associated with a higher risk of MACE (hazard ratio (HR): 2.115; 95% confidence interval (CI): 1.379-3.246; p = 0.001) when adjusting for LVEF, LGE extent, age, sex, body mass index, steroid treatment, and prior cardiotoxic chemotherapy or radiation. After adjustment for LVEF, the GLS remained the independent risk factor associated with a higher rate of MACE among patients with a preserved LVEF (HR: 1.358; 95% CI: 1.007-1.830; p = 0.045). CONCLUSIONS: GLS could provide independent prognostic value over GCS, GRS, traditional CMR features, and clinical features in patients with ICI-associated myocarditis. KEY POINTS: • The global circumferential strain (GCS), global radial strain (GRS), and global longitudinal strain (GLS) by cardiovascular magnetic resonance feature tracking were significantly impaired in patients with an immune checkpoint inhibitor (ICI)-associated myocarditis. • GLS was still significantly impaired in patients with preserved left ventricular ejection fraction. • The worse GLS was an independent risk factor over GCS, GRS, traditional CMR features, and clinical features for predicting major adverse cardiovascular events in patients with ICI-associated myocarditis.

Acute impact of an endurance race on biventricular and biatrial myocardial strain in competitive male and female triathletes evaluated by feature-tracking CMR.

OBJECTIVES: Cardiac adaptation in endurance athletes is a well-known phenomenon, but the acute impact of strenuous exercise is rarely reported on. The aim of this study was to analyze the alterations in biventricular and biatrial function in triathletes after an endurance race using novel feature-tracking cardiac magnetic resonance (FT-CMR). METHODS: Fifty consecutive triathletes (45 ± 10 years; 80% men) and twenty-eight controls were prospectively recruited, and underwent 1.5-T CMR. Biventricular and biatrial volumes, left ventricular ejection fraction (LVEF), FT-CMR analysis, and late gadolinium imaging (LGE) were performed. Global systolic longitudinal (GLS), circumferential (GCS), and radial strain (GRS) were assessed. CMR was performed at baseline and following an endurance race. High-sensitive troponin T and NT-proBNP were determined. The time interval between race completion and CMR was 2.3 ± 1.1 h (range 1-5 h). RESULTS: Post-race troponin T (p < 0.0001) and NT-proBNP (p < 0.0001) were elevated. LVEF remained constant (62 ± 6 vs. 63 ± 7%, p = 0.607). Post-race LV GLS decreased by tendency (- 18 ± 2 vs. - 17 ± 2%, p = 0.054), whereas GCS (- 16 ± 4 vs. - 18 ± 4%, p < 0.05) and GRS increased (39 ± 11 vs. 44 ± 11%, p < 0.01). Post-race right ventricular GLS (- 19 ± 3 vs. - 19 ± 3%, p = 0.668) remained constant and GCS increased (- 7 ± 2 vs. - 8 ± 3%, p < 0.001). Post-race left atrial GLS (30 ± 8 vs. 24 ± 6%, p < 0.0001) decreased while right atrial GLS remained constant (25 ± 6 vs. 24 ± 6%, p = 0.519). CONCLUSIONS: The different alterations of post-race biventricular and biatrial strain might constitute an intrinsic compensatory mechanism following an acute bout of endurance exercise. The combined use of strain parameters may allow a better characterization of ventricular and atrial function in endurance athletes. KEY POINTS: • Triathletes demonstrate a decrease of LV global longitudinal strain by tendency and constant RV global longitudinal strain following an endurance race. • Post-race LV and RV global circumferential and radial strains increase, possibly indicating a compensatory mechanism after an acute endurance exercise bout. • Subgroup analyses of male triathletes with focal myocardial fibrosis did not demonstrate alterations in biventricular and biatrial strain after an endurance race.

Ultrafast Computation of Left Ventricular Ejection Fraction by Using Temporal Intensity Variation in Cine Cardiac Magnetic Resonance.

Cardiac magnetic resonance enables comprehensive cardiac evaluation; however, intense time and labor requirements for data acquisition and processing have discouraged many clinicians from using it. We have developed an alternative image-processing algorithm that requires minimal user interaction: an ultrafast algorithm that computes left ventricular ejection fraction (LVEF) by using temporal intensity variation in cine balanced steady-state free precession (bSSFP) short-axis images, with or without contrast medium. We evaluated the algorithm's performance against an expert observer's analysis for segmenting the LV cavity in 65 study participants (LVEF range, 12%-70%). In 12 instances, contrast medium was administered before cine imaging. Bland-Altman analysis revealed quantitative effects of LV basal, midcavity, and apical morphologic variation on the algorithm's accuracy. Total computation time for the LV stack was <2.5 seconds. The algorithm accurately delineated endocardial boundaries in 1,132 of 1,216 slices (93%). When contours in the extreme basal and apical slices were not adequate, they were replaced with manually drawn contours. The Bland-Altman mean differences were <1.2 mL (0.8%) for end-diastolic volume, <5 mL (6%) for end-systolic volume, and <3% for LVEF. Standard deviation of the difference was ≤4.1% of LV volume for all sections except the midcavity in end-systole (8.3% of end-systolic volume). We conclude that temporal intensity variation-based ultrafast LVEF computation is clinically accurate across a range of LV shapes and wall motions and is suitable for postcontrast cine SSFP imaging. Our algorithm enables real-time processing of cine bSSFP images on a commercial scanner console within 3 seconds in an unobtrusive automated process.

Feature tracking myocardial strain analysis in patients with bileaflet mitral valve prolapse: relationship with LGE and arrhythmias.

OBJECTIVES: Anatomical substrate and mechanical trigger co-act in arrhythmia's onset in patients with bileaflet mitral valve prolapse (bMVP). Feature tracking (FT) may improve risk stratification provided by cardiac magnetic resonance (CMR). The aim was to investigate differences in CMR and FT parameters in bMVP patients with and without complex arrhythmias (cVA and no-cVA). METHODS: In this retrospective study, 52 patients with bMVP underwent 1.5 T CMR and were classified either as no-cVA (n = 32; 12 males; 49.6 ± 17.4 years) or cVA (n = 20; 3 males; 44.7 ± 11.2 years), the latter group including 6 patients (1 male; 45.7 ± 12.7 years) with sustained ventricular tachycardia or ventricular fibrillation (SVT-FV). Twenty-four healthy volunteers (11 males, 36.2 ± 12.5 years) served as control. Curling, prolapse distance, mitral annulus disjunction (MAD), and late gadolinium enhancement (LGE) were recorded and CMR-FT analysis performed. Statistical analysis included non-parametric tests and binary logistic regression. RESULTS: LGE and MAD distance were associated with cVA with an odds ratio (OR) of 8.51 for LGE (95% CI 1.76, 41.28; p = 0.008) and of 1.25 for MAD (95% CI 1.02, 1.54; p = 0.03). GLS 2D (- 11.65 ± 6.58 vs - 16.55 ± 5.09 1/s; p = 0.04), PSSR longitudinal 2D (0.04 ± 1.62 1/s vs - 1.06 ± 0.35 1/s; p = 0.0001), and PSSR radial 3D (3.95 ± 1.97 1/s vs 2.64 ± 1.03 1/s; p = 0.0001) were different for SVT-VF versus the others. PDSR circumferential 2D (1.10 ± 0.54 vs. 0.84 ± 0.34 1/s; p = 0.04) and 3D (0.94 ± 0.42 vs. 0.69 ± 0.17 1/s; p = 0.04) differed between patients with and without papillary muscle LGE. CONCLUSIONS: CMR-FT allowed identifying subtle myocardial deformation abnormalities in bMVP patients at risk of SVT-VF. LGE and MAD distance were associated with cVA. KEY POINTS: • CMR-FT allows identifying several subtle myocardial deformation abnormalities in bMVP patients, especially those involving the papillary muscle. • CMR-FT allows identifying subtle myocardial deformation abnormalities in bMVP patients at risk of SVT and VF. • In patients with bMVP, the stronger predictor of cVA is LGE (OR = 8.51; 95% CI 1.76, 41.28; p = 0.008), followed by MAD distance (OR = 1.25; 95% CI 1.02, 1.54; p = 0.03).

Simultaneous assessment of colon motility in children with functional constipation by cine-MRI and colonic manometry: a feasibility study.

BACKGROUND: Colonic manometry is the current reference standard for assessing colonic neuromuscular function in children with intractable functional constipation (FC). Recently, cine magnetic resonance imaging (cine-MRI) has been proposed as a non-invasive alternative. We compared colonic motility patterns on cine-MRI with those obtained by manometry in children, by stimulating high-amplitude propagating contractions (HAPCs) with bisacodyl under manometric control while simultaneously acquiring cine-MRI. METHODS: After Institutional Review Board approval, adolescents with FC scheduled to undergo colonic manometry were included. A water-perfused 8-lumen catheter was used for colonic manometry recordings. After an intraluminal bisacodyl infusion, cine-MRI sequences of the descending colon were acquired for about 30 min simultaneously with colonic manometry. Manometry recordings were analysed for HAPCs. MRI images were processed with spatiotemporal motility MRI techniques. The anonymised motility results of both techniques were visually compared for the identification of HAPCs in the descending colon. RESULTS: Data regarding six patients (three males) were analysed (median age 14 years, range 12-17). After bisacodyl infusion, three patients showed a total of eleven HAPCs with colonic manometry. Corresponding cine-MRI recorded high colonic activity during two of these HAPCs, minimal activity during seven HAPCs, while two HAPCs were not recorded. In two of three patients with absent HAPCs on manometry, colonic activity was recorded with cine-MRI. CONCLUSIONS: Simultaneous acquisition of colonic cine-MRI and manometry in children with FC is feasible. Their motility results did not completely overlap in the identification of HAPCs. Research is needed to unravel the role of cine-MRI in this setting.

Impact of chest wall deformity on cardiac function by CMR and feature-tracking strain analysis in paediatric patients with Marfan syndrome.

OBJECTIVES: To evaluate systolic cardiac dysfunction in paediatric MFS patients with chest wall deformity using cardiac magnetic resonance (CMR) imaging and feature-tracking strain analysis. METHODS: Forty paediatric MFS patients (16 ± 3 years, range 8-22 years) and 20 age-matched healthy controls (16 ± 4 years, range 11-24 years) were evaluated retrospectively. Biventricular function and volumes were determined using cine sequences. Feature-tracking CMR was used to assess global systolic longitudinal (GLS), circumferential (GCS) and radial strain (GRS). A dedicated balanced turbo field echo sequence was used to quantify chest wall deformity by measuring the Haller index (HI). RESULTS: LV volumes and ejection fraction (EF) were similar in MFS patients and controls. There was a trend for lower right ventricular (RV) volume (75 ± 17 vs. 81 ± 10 ml/m2, p = 0.08), RV stroke volume (41 ± 12 vs. 50 ± 5 ml/m2, p < 0.001) and RVEF (55 ± 10 vs. 62 ± 6%, p < 0.01) in MFS patients. A subgroup of MFS patients had an increased HI compared to controls (4.6 ± 1.7 vs. 2.6 ± 0.3, p < 0.001). They demonstrated a reduced RVEF compared to MFS patients without chest wall deformity (50 ± 11% vs. 58 ± 8%, p = 0.01) and controls (p < 0.001). LV GLS was attenuated when HI ≥ 3.25 (- 16 ± 2 vs. - 18 ± 3%, p = 0.03), but not GCS and GRS. LV GLS (p < 0.01) and GCS (p < 0.0001) were attenuated in MFS patients compared to controls, but not GRS (p = 0.31). RV GLS was attenuated in MFS patients compared to controls (- 21 ± 3 vs. - 23 ± 3%, p < 0.05). CONCLUSION: Chest wall deformity in paediatric MFS patients is associated with reduced RV volume, ejection fraction and GLS. Feature-tracking CMR also indicates impairment of systolic LV function in paediatric MFS patients. KEY POINTS: • Paediatric Marfan patients demonstrate reduced RV volume and ejection fraction compared to healthy controls. • A concordant attenuation in RV global longitudinal strain was observed in Marfan patients, while the RV global circumferential strain was increased, indicating a possible compensatory mechanism. • Subgroup analyses demonstrated alterations in RV ejection fraction and RV/LV global strain parameters, indicating a possible association of severe chest wall deformity with biventricular dysfunction in paediatric Marfan patients.

A Multicenter, Scan-Rescan, Human and Machine Learning CMR Study to Test Generalizability and Precision in Imaging Biomarker Analysis.

BACKGROUND: Automated analysis of cardiac structure and function using machine learning (ML) has great potential, but is currently hindered by poor generalizability. Comparison is traditionally against clinicians as a reference, ignoring inherent human inter- and intraobserver error, and ensuring that ML cannot demonstrate superiority. Measuring precision (scan:rescan reproducibility) addresses this. We compared precision of ML and humans using a multicenter, multi-disease, scan:rescan cardiovascular magnetic resonance data set. METHODS: One hundred ten patients (5 disease categories, 5 institutions, 2 scanner manufacturers, and 2 field strengths) underwent scan:rescan cardiovascular magnetic resonance (96% within one week). After identification of the most precise human technique, left ventricular chamber volumes, mass, and ejection fraction were measured by an expert, a trained junior clinician, and a fully automated convolutional neural network trained on 599 independent multicenter disease cases. Scan:rescan coefficient of variation and 1000 bootstrapped 95% CIs were calculated and compared using mixed linear effects models. RESULTS: Clinicians can be confident in detecting a 9% change in left ventricular ejection fraction, with greater than half of coefficient of variation attributable to intraobserver variation. Expert, trained junior, and automated scan:rescan precision were similar (for left ventricular ejection fraction, coefficient of variation 6.1 [5.2%-7.1%], P=0.2581; 8.3 [5.6%-10.3%], P=0.3653; 8.8 [6.1%-11.1%], P=0.8620). Automated analysis was 186× faster than humans (0.07 versus 13 minutes). CONCLUSIONS: Automated ML analysis is faster with similar precision to the most precise human techniques, even when challenged with real-world scan:rescan data. Assessment of multicenter, multi-vendor, multi-field strength scan:rescan data (available at www.thevolumesresource.com) permits a generalizable assessment of ML precision and may facilitate direct translation of ML to clinical practice.

Blood Flow Lateralization and Collateral Compensatory Mechanisms in Patients With Carotid Artery Stenosis.

Background and Purpose- Four-dimensional phase-contrast magnetic resonance imaging enables quantification of blood flow rate (BFR; mL/min) in multiple cerebral arteries simultaneously, making it a promising technique for hemodynamic investigation in patients with stroke. The aim of this study was to quantify the hemodynamic disturbance and the compensatory pattern of collateral flow in patients with symptomatic carotid stenosis. Methods- Thirty-eight patients (mean, 72 years; 27 men) with symptomatic carotid stenosis (≥50%) or occlusion were investigated using 4-dimensional phase-contrast magnetic resonance imaging. For each patient, BFR was measured in 19 arteries/locations. The ipsilateral side to the symptomatic carotid stenosis was compared with the contralateral side. Results- Internal carotid artery BFR was lower on the ipsilateral side (134±87 versus 261±95 mL/min; P<0.001). BFR in anterior cerebral artery (A1 segment) was lower on ipsilateral side (35±58 versus 119±72 mL/min; P<0.001). Anterior cerebral artery territory bilaterally was primarily supplied by contralateral internal carotid artery. The ipsilateral internal carotid artery mainly supplied the ipsilateral middle cerebral artery (MCA) territory. MCA was also supplied by a reversed BFR found in the ophthalmic and the posterior communicating artery routes on the ipsilateral side (-5±28 versus 10±28 mL/min, P=0.001, and -2±12 versus 6±6 mL/min, P=0.03, respectively). Despite these compensations, BFR in MCA was lower on the ipsilateral side, and this laterality was more pronounced in patients with severe carotid stenosis (≥70%). Although comparing ipsilateral MCA BFR between stenosis groups (<70% and ≥70%), there was no difference ( P=0.95). Conclusions- With a novel approach using 4-dimensional phase-contrast magnetic resonance imaging, we could simultaneously quantify and rank the importance of collateral routes in patients with carotid stenosis. An important observation was that contralateral internal carotid artery mainly secured the bilateral anterior cerebral artery territory. Because of the collateral recruitment, compromised BFR in MCA is not necessarily related to the degree of carotid stenosis. These findings highlight the importance of simultaneous investigation of the hemodynamics of the entire cerebral arterial tree.

Quantification of myocardial deformation by deformable registration-based analysis of cine MRI: validation with tagged CMR.

OBJECTIVES: To validate deformable registration algorithms (DRAs) for cine balanced steady-state free precession (bSSFP) assessment of global longitudinal strain (GLS) and global circumferential strain (GCS) using harmonic phase (HARP) cardiovascular magnetic resonance as standard of reference (SoR). METHODS: Seventeen patients and 17 volunteers underwent short axis stack and 2-/4-chamber cine bSSFP imaging with matching slice long-axis and mid-ventricular spatial modulation of magnetization (SPAMM) myocardial tagging. Inverse DRA was applied on bSSFP data for assessment of GLS and GCS while myocardial tagging was processed using HARP. Intra- and inter-observer variability assessment was based on repeated analysis by a single observer and analysis by a second observer, respectively. Standard semi-automated short axis stack segmentation was performed for analysis of left ventricular (LV) volumes and ejection fraction (EF). RESULTS: DRA demonstrated strong relationships to HARP for myocardial GLS (R2 = 0.75; p < 0.0001) and endocardial GLS (R2 = 0.61; p < 0.0001). GCS result comparison also demonstrated significant relationships between DRA and HARP for myocardial strain (R2 = 0.61; p < 0.0001) and endocardial strain (R2 = 0.51; p < 0.0001). Both methods demonstrated small systematic errors for intra- and inter-observer variability but DRA demonstrated consistently lower CV. Global LVEF was significantly lower (p = 0.0099) in patients (53.7%; IQR 43.9/64.0%) than in healthy volunteers (62.6%; IQR 61.1/66.2%). DRA and HARP strain data demonstrated significant relationships to LVEF. CONCLUSIONS: Non-rigid deformation method-based DRA provides a reliable measure of peak systolic GCS and GLS based on cine bSSFP with superior intra- and inter-observer reproducibility compared to HARP. KEY POINT: • Myocardial strain can be reliably analyzed using inverse deformable registration algorithms (DRAs) on cine CMR. • Inverse DRA-derived strain shows higher reproducibility than tagged CMR. • DRA and tagged CMR-based myocardial strain demonstrate strong relationships to global left ventricular function.

Deep learning cardiac motion analysis for human survival prediction.

Motion analysis is used in computer vision to understand the behaviour of moving objects in sequences of images. Optimising the interpretation of dynamic biological systems requires accurate and precise motion tracking as well as efficient representations of high-dimensional motion trajectories so that these can be used for prediction tasks. Here we use image sequences of the heart, acquired using cardiac magnetic resonance imaging, to create time-resolved three-dimensional segmentations using a fully convolutional network trained on anatomical shape priors. This dense motion model formed the input to a supervised denoising autoencoder (4Dsurvival), which is a hybrid network consisting of an autoencoder that learns a task-specific latent code representation trained on observed outcome data, yielding a latent representation optimised for survival prediction. To handle right-censored survival outcomes, our network used a Cox partial likelihood loss function. In a study of 302 patients the predictive accuracy (quantified by Harrell's C-index) was significantly higher (p = .0012) for our model C=0.75 (95% CI: 0.70 - 0.79) than the human benchmark of C=0.59 (95% CI: 0.53 - 0.65). This work demonstrates how a complex computer vision task using high-dimensional medical image data can efficiently predict human survival.