Refine
Year of publication
- 2021 (18) (remove)
Document Type
- Article (18)
Language
- English (18)
Has Fulltext
- yes (18)
Is part of the Bibliography
- no (18)
Keywords
- Bone density (2)
- CT (2)
- Magnetic resonance imaging (2)
- Osteoporosis (2)
- Spine (2)
- Tomography (x-ray computed) (2)
- Algorithms (1)
- Anemia (1)
- Artificial intelligence (1)
- Blood (1)
Institute
- Medizin (18)
- Informatik und Mathematik (1)
Background: To assess the potential of radiomic features to quantify components of blood in intraaortic vessels to non-invasively predict moderate-to-severe anemia in non-contrast enhanced CT scans. Methods: One hundred patients (median age, 69 years; range, 19–94 years) who received CT scans of the thoracolumbar spine and blood-testing for hemoglobin and hematocrit levels ± 24 h between 08/2018 and 11/2019 were retrospectively included. Intraaortic blood was segmented using a spherical volume of interest of 1 cm diameter with consecutive radiomic analysis applying PyRadiomics software. Feature selection was performed applying analysis of correlation and collinearity. The final feature set was obtained to differentiate moderate-to-severe anemia. Random forest machine learning was applied and predictive performance was assessed. A decision-tree was obtained to propose a cut-off value of CT Hounsfield units (HU). Results: High correlation with hemoglobin and hematocrit levels was shown for first-order radiomic features (p < 0.001 to p = 0.032). The top 3 features showed high correlation to hemoglobin values (p) and minimal collinearity (r) to the top ranked feature Median (p < 0.001), Energy (p = 0.002, r = 0.387), Minimum (p = 0.032, r = 0.437). Median (p < 0.001) and Minimum (p = 0.003) differed in moderate-to-severe anemia compared to non-anemic state. Median yielded superiority to the combination of Median and Minimum (p(AUC) = 0.015, p(precision) = 0.017, p(accuracy) = 0.612) in the predictive performance employing random forest analysis. A Median HU value ≤ 36.5 indicated moderate-to-severe anemia (accuracy = 0.90, precision = 0.80). Conclusions: First-order radiomic features correlate with hemoglobin levels and may be feasible for the prediction of moderate-to-severe anemia. High dimensional radiomic features did not aid augmenting the data in our exemplary use case of intraluminal blood component assessment.
Diagnostic value of dynamic magnetic resonance imaging of temporomandibular joint dysfunction
(2021)
Background: To estimate the diagnostic value of dynamic magnetic resonance imaging (MRI) for the assessment of the temporomandibular joint (TMJ) compared to standard static MRI sequences in patients with TMJ dysfunction (TMD).
Methods and materials: This retrospective study included 71 patients with clinical diagnose of TMD. We acquired 5 static T1- and T2-weighted sequences in parasagittal and paracoronal views and one dynamic sequence (trueFISP) in parasagittal view for each TMJ. Image analysis included evaluation of morphology and function of intra-articular structures and rating of the dynamic images as more, equally, or less informative compared to static MRI sequences.
Results: Mean age was 35.0 ± 14.7 years and 50/71 (70.4%) were female. 127/142 (89.4%) TMJs were of diagnostic quality. 42/127 (33.1%) TMJs showed no disc displacement (DD), 56 (44.1%) had DD with disc reduction (DDwR), and 29 (22.8%) had DD without disc reduction (DDwoR). In 38/127 (29.9%) TMJs, dynamic images were rated “more informative”, in 84/127 (66.2%) “equally informative”, and in 5/127 (3.9%) “less informative” compared to solely static images. Overall, 27/71 (38.0%) patients benefited from additional dynamic sequences compared to solely static images. Dynamic images were “more informative” in TMJs with DDwR (23/56 [41.1%], p < 0.001) and in TMJs with DDwoR (13/29 [44.8%], p = 0.007), while it had no beneficial value for TMJ without DD. For evaluation of joint effusion, static T2-weighted images were rated better in 102/127 (80.3%) TMJs compared to dynamic images (<0.001).
Conclusion: Dynamic MRI sequences are beneficial for the evaluation of morphology and function of the TMJ compared to static sequences, especially in patients with temporomandibular disc displacement.
Background: Various studies have been made about the most effective and safest type of treatment for vertebral compression fractures (VCFs). Long-term results are needed for qualitative evaluation.
Purpose: The purpose of the study is to evaluate the effectiveness of percutaneous vertebroplasty (PVP) and percutaneous kyphoplasty (PKP) procedures for VCFs.
Materials and Methods: Forty-nine patients who received either PVP or PKP between 2002 and 2015 returned a specially developed questionnaire and were included in a cross-sectional outcome analysis. The questionnaire assessed pain development by use of a visual analog scale (VAS). Imaging data (CT scans) were retrospectively analyzed for identification of cement leakage.
Results: Patients’ VAS scores significantly decreased after treatment (7.0 ± 3.4 => 3.7 ± 3.4), (p < 0.001). The average pain reduction in patients treated with PVP was −3.3 ± 3.8 (p < 0.001) (median −3.5) and −4.0 ± 3.9 (p < 0.001) (median −4.5) in patients treated with PKP. Fifteen Patients (41.7%) receiving PVP and four patients (30.7%) receiving PKP experienced recurrence of pain. Cement leakage occurred in 10 patients (22.73%). Patients with cement leakage showed comparable VAS scores after treatment (6.8 ± 3.5 => 1.4 ± 1.6), (p = 0.008). Thirty-nine patients reported an increase in mobility (79.6%) and 41 patients an improvement in quality of life (83.7%).
Conclusion: Pain reduction by means of PVP or PKP in patients with VCFs was discernible over the period of observation. Percutaneous vertebroplasty and PKP contribute to the desired treatment results. However, the level of low pain may not remain constant.
Our purpose was to analyze the robustness and reproducibility of magnetic resonance imaging (MRI) radiomic features. We constructed a multi-object fruit phantom to perform MRI acquisition as scan-rescan using a 3 Tesla MRI scanner. We applied T2-weighted (T2w) half-Fourier acquisition single-shot turbo spin-echo (HASTE), T2w turbo spin-echo (TSE), T2w fluid-attenuated inversion recovery (FLAIR), T2 map and T1-weighted (T1w) TSE. Images were resampled to isotropic voxels. Fruits were segmented. The workflow was repeated by a second reader and the first reader after a pause of one month. We applied PyRadiomics to extract 107 radiomic features per fruit and sequence from seven feature classes. We calculated concordance correlation coefficients (CCC) and dynamic range (DR) to obtain measurements of feature robustness. Intraclass correlation coefficient (ICC) was calculated to assess intra- and inter-observer reproducibility. We calculated Gini scores to test the pairwise discriminative power specific for the features and MRI sequences. We depict Bland Altmann plots of features with top discriminative power (Mann–Whitney U test). Shape features were the most robust feature class. T2 map was the most robust imaging technique (robust features (rf), n = 84). HASTE sequence led to the least amount of rf (n = 20). Intra-observer ICC was excellent (≥ 0.75) for nearly all features (max–min; 99.1–97.2%). Deterioration of ICC values was seen in the inter-observer analyses (max–min; 88.7–81.1%). Complete robustness across all sequences was found for 8 features. Shape features and T2 map yielded the highest pairwise discriminative performance. Radiomics validity depends on the MRI sequence and feature class. T2 map seems to be the most promising imaging technique with the highest feature robustness, high intra-/inter-observer reproducibility and most promising discriminative power.