PURPOSE/OBJECTIVEReliable detection of thoracic aortic dilatation (TAD) is mandatory in clinical routine. For ECG-gated CT angiography, automated deep learning (DL) algorithms are established for ...diameter measurements according to current guidelines. For non-ECG gated CT (contrast enhanced (CE) and non-CE), however, only a few reports are available. In these reports, classification as TAD is frequently unreliable with variable result quality depending on anatomic location with the aortic root presenting with the worst results. Therefore, this study aimed to explore the impact of re-training on a previously evaluated DL tool for aortic measurements in a cohort of non-ECG gated exams.METHODS & MATERIALSA cohort of 995 patients (68 ± 12 years) with CE (n = 392) and non-CE (n = 603) chest CT exams was selected which were classified as TAD by the initial DL tool. The re-trained version featured improved robustness of centerline fitting and cross-sectional plane placement. All cases were processed by the re-trained DL tool version. DL results were evaluated by a radiologist regarding plane placement and diameter measurements. Measurements were classified as correctly measured diameters at each location whereas false measurements consisted of over-/under-estimation of diameters.RESULTSWe evaluated 8948 measurements in 995 exams. The re-trained version performed 8539/8948 (95.5%) of diameter measurements correctly. 3765/8948 (42.1%) of measurements were correct in both versions, initial and re-trained DL tool (best: distal arch 655/995 (66%), worst: Aortic sinus (AS) 221/995 (22%)). In contrast, 4456/8948 (49.8%) measurements were correctly measured only by the re-trained version, in particular at the aortic root (AS: 564/995 (57%), sinotubular junction: 697/995 (70%)). In addition, the re-trained version performed 318 (3.6%) measurements which were not available previously. A total of 228 (2.5%) cases showed false measurements because of tilted planes and 181 (2.0%) over-/under-segmentations with a focus at AS (n = 137 (14%) and n = 73 (7%), respectively).CONCLUSIONRe-training of the DL tool improved diameter assessment, resulting in a total of 95.5% correct measurements. Our data suggests that the re-trained DL tool can be applied even in non-ECG-gated chest CT including both, CE and non-CE exams.
•More than half of LV-GCA patients in clinical remission show signs of active vessel wall inflammation on PET/CT and MRI.•The presence or absence of vasculitic findings on PET/CT and/or MRI did not ...predict subsequent relapse after treatment stop.•The role of PET/CT and/or MRI in guiding the decision of whether to stop or continue treatment in patients with LV-GCA seems limited.
To investigate the value of 18Ffluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) and magnetic resonance imaging (MRI) in predicting relapse after treatment discontinuation in patients with large-vessel giant cell arteritis (LV-GCA).
This study included patients with LV-GCA whose treatment was discontinued between 2018 and 2023. All patients underwent PET/CT and/or MRI at the time of treatment discontinuation in clinical remission. Qualitative and quantitative PET/CT scores, by measuring standardized uptake values (SUV), and semiquantitative MRI scores of the aorta and supraaortic vessels were compared between patients who relapsed within 4 months after treatment discontinuation and those who did not.
Forty patients were included (median age 67.4 years, interquartile range (IQR) 60.8–74.0; 77.5 % females). Eleven patients (27.5 %) relapsed after treatment discontinuation (time to relapse 1.9 months, IQR 1.4–3.3). Patients who relapsed were comparable to those who remained in remission with respect to the presence of active vasculitis on MRI and/or PET/CT (54.5% vs. 58.6 %, p = 1.0), the number of segments with vasculitic findings on MRI (0, IQR 0.0–1.5, vs. 2, IQR 0.0–3.0, p = 0.221) or the highest SUV artery/liver ratio on PET/CT (1.5, IQR 1.4–1.6, vs. 1.3, IQR 1.2–1.6, p = 0.505). The median number of vasculitic segments on PET/CT was 2.5 (IQR 0.5–4.5) in those with vs. 0 (IQR 0.0–1.5, p = 0.085) in those without relapse, and the PET/CT scores 4.5 (IQR 0.75–8.25) vs. 0 (IQR 0.0–3.0, p = 0.172).
PET/CT or MRI at treatment stop did not predict relapse and may not be suited to guide treatment decisions in patients with LV-GCA in remission.
Objectives
Time-resolved, 2D-phase-contrast MRI (2D-CINE-PC-MRI) enables in vivo blood flow analysis. However, accurate vessel contour delineation (VCD) is required to achieve reliable results. We ...sought to evaluate manual analysis (MA) compared to the performance of a deep learning (DL) application for fully-automated VCD and flow quantification and corrected semi-automated analysis (corSAA).
Methods
We included 97 consecutive patients (age = 52.9 ± 16 years, 41 female) with 2D-CINE-PC-MRI imaging on 1.5T MRI systems at sinotubular junction (STJ), and 28/97 also received 2D-CINE-PC at main pulmonary artery (PA). A cardiovascular radiologist performed MA (reference) and corSAA (built-in tool) in commercial software for all cardiac time frames (median: 20, total contours per analysis: 2358 STJ, 680 PA). DL-analysis automatically performed VCD, followed by net flow (NF) and peak velocity (PV) quantification. Contours were compared using Dice similarity coefficients (DSC). Discrepant cases (> ± 10 mL or > ± 10 cm/s) were reviewed in detail.
Results
DL was successfully applied to 97% (121/125) of the 2D-CINE-PC-MRI series (STJ: 95/97, 98%, PA: 26/28, 93%). Compared to MA, mean DSC were 0.91 ± 0.02 (DL), 0.94 ± 0.02 (corSAA) at STJ, and 0.85 ± 0.08 (DL), 0.93 ± 0.02 (corSAA) at PA; this indicated good to excellent DL-performance. Flow quantification revealed similar NF at STJ (
p
= 0.48) and PA (
p
> 0.05) between methods while PV assessment was significantly different (STJ:
p
< 0.001, PA:
p
= 0.04). A detailed review showed noisy voxels in MA and corSAA impacted PV results. Overall, DL analysis compared to human assessments was accurate in 113/121 (93.4%) cases.
Conclusions
Fully-automated DL-analysis of 2D-CINE-PC-MRI provided flow quantification at STJ and PA at expert level in > 93% of cases with results being available instantaneously.
Key Points
• Deep learning performed flow quantification on clinical 2D-CINE-PC series at the sinotubular junction and pulmonary artery at the expert level in > 93% of cases.
• Location detection and contouring of the vessel boundaries were performed fully-automatic with results being available instantaneously compared to human assessments which approximately takes three minutes per location.
• The evaluated tool indicates usability in daily practice.
Display omitted
The biplane area-length method is commonly used in cardiac magnetic resonance (CMR) to assess left atrial (LA) volume (LAV) and function. Associations between left atrial emptying ...fraction (LAEF) and clinical outcomes have been reported. However, only limited data are available on the calculation of LAEF using the biplane method compared to 3D assessment. This study aimed to compare volumetric and functional LA parameters obtained from the biplane method with 3D assessment in a large, multiethnic cohort.
158 participants of MESA (Multi-Ethnic Study of Atherosclerosis) underwent CMR that included standard two- and four-chamber steady-state free precession (SSFP) cine imaging for the biplane method. For 3D-based assessment, short-axis SSFP cine series covering the entire LA were obtained, followed by manual delineation of LA contours to create a time-resolved 3D LAV dataset. Paired t-tests and Bland-Altman plots were used to analyze the data.
Standard volumetric assessment showed that LAVmin (bias: −8.35 mL, p < 0.001), LAVmax (bias: −9.38 mL, p < 0.001) and LAVpreA (bias: −10.27 mL, p < 0.001) were significantly smaller using the biplane method compared to 3D assessment. Additionally, the biplane method reported significantly higher LAEFtotal (bias: 7.22 %, p < 0.001), LAEFactive (bias: 6.08 %, p < 0.001), and LAEFpassive (bias: 4.51 %, p < 0.001) with wide limits of agreement.
LA volumes were underestimated using the biplane method compared to 3D assessment, while LAEF parameters were overestimated. These findings demonstrate a lack of precision using the biplane method for LAEF assessment. Our results support the usage of 3D assessment in specific settings when LA volumetric and functional parameters are in focus.
