Purpose: The compartmental nature of brain tissue microstructure is typically studied by diffusion MRI, MR relaxometry or their correlation. Diffusion MRI relies on signal representations or biophysical models, while MR relaxometry and correlation studies are based on regularized inverse Laplace transforms (ILTs). Here we introduce a general framework for characterizing microstructure that does not depend on diffusion modeling and replaces ill‐posed ILTs with blind source separation (BSS). This framework yields proton density, relaxation times, volume fractions, and signal disentanglement, allowing for separation of the free‐water component.Theory and Methods: Diffusion experiments repeated for several different echo times, contain entangled diffusion and relaxation compartmental information. These can be disentangled by BSS using a physically constrained nonnegative matrix factorization.Results: Computer simulations, phantom studies, together with repeatability and reproducibility experiments demonstrated that BSS is capable of estimating proton density, compartmental volume fractions and transversal relaxations. In vivo results proved its potential to correct for free‐water contamination and to estimate tissue parameters.Conclusion: Formulation of the diffusion‐relaxation dependence as a BSS problem introduces a new framework for studying microstructure compartmentalization, and a novel tool for free‐water elimination.

Many limitations of diffusion MRI are due to the instability of the model fitting procedure. Major shortcomings of the model-based approach are a partial information loss due to model simplicity, long scan time requirements due to fitting instability, and the lack of knowledge about how the parameters of a given model would respond to previously unseen microstructural changes, possibly failing to detect certain previously unseen pathologies. Here we show that diffusion MRI pathology detection is feasible without any models and without any prior knowledge of specific pathological changes whatsoever. Instead, raw q-space measurements are used directly without a model, only healthy population data is used for reference, and any deviations in a patient dataset from the healthy reference database are detected using novelty detection methods. This is done in each voxel independently, i.e. without spatial bias.

Reliable 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. A 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. We 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). Re-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.

Background: To validate the automated quantification of cardiac chamber volumes and myocardial mass on non-contrast chest CT using cardiac MR (CMR) as a reference. Methods: We retrospectively included 53 consecutive patients who received non-contrast chest CT and CMR within three weeks. A deep learning model created cardiac segmentations on axial soft-tissue reconstructions from CT, covering all four cardiac chambers and the left ventricular myocardium. Segmentations on CMR cine short-axis and long-axis images served as a reference. Standard estimates of diagnostic accuracy were calculated for ventricular volumes at end-diastole and end-systole (LVEDV, LVESV, RVEDV, RVESV), left ventricular mass (LVM), and atrial volumes (LA, RA) at ventricular end-diastole. A qualitative assessment noted segmentation issues. Results: The deep learning model generated CT measurements for 52 of the 53 patients (98%). Based on CMR measurements, the average LVEDV was 166 ± 64 mL, RVEDV was 144 ± 51 mL, and LVM was 115 ± 39 g. The CT measurements correlated well with CMR measurements for LVEDV, LVESV, and LVM (ICC = 0.85, ICC = 0.84, and ICC = 0.91; all p < 0.001) and RVEDV and RVESV (ICC = 0.79 and ICC= 0.78; both p < 0.001), and moderately well with LA and RA (ICC = 0.74 and ICC = 0.61; both p < 0.001). Absolute agreements likewise favored LVEDV, LVM, and RVEDV. ECG-gating did not relevantly influence the results. The CT results correctly identified 7/15 LV and 1/1 RV as dilated (one and six false positives, respectively). Major qualitative issues were found in three cases (6%). Conclusions: Automated cardiac chamber volume and myocardial mass quantification on non-contrast chest CT produced viable measurements in this retrospective sample. Relevance Statement: An automated cardiac assessment on non-contrast chest CT provides quantitative morphological data on the heart, enabling a preliminary organ evaluation that aids in incidentally identifying at-risk patients who may benefit from a more targeted diagnostic workup.

OBJECTIVES: To assess the accuracy of a deep learning-based algorithm for fully automated detection of thoracic aortic calcifications in chest computed tomography (CT) with a focus on the aortic clamping zone.METHODS: We retrospectively included 100 chest CT scans from 91 patients who were examined on second- or third-generation dual-source scanners. Subsamples comprised 47 scans with an electrocardiogram-gated aortic angiography and 53 unenhanced scans. A deep learning model performed aortic landmark detection and aorta segmentation to derive 8 vessel segments. Associated calcifications were detected and their volumes measured using a mean-based density thresholding. Algorithm parameters (calcium cluster size threshold, aortic mask dilatation) were varied to determine optimal performance for the upper ascending aorta that encompasses the aortic clamping zone. A binary visual rating served as a reference. Standard estimates of diagnostic accuracy and inter-rater agreement using Cohen’s Kappa were calculated.RESULTS: Thoracic aortic calcifications were observed in 74% of patients with a prevalence of 27–70% by aorta segment. Using different parameter combinations, the algorithm provided binary ratings for all scans and segments. The best performing parameter combination for the presence of calcifications in the aortic clamping zone yielded a sensitivity of 93% and a specificity of 82%, with an area under the receiver operating characteristic curve of 0.874. Using these parameters, the inter-rater agreement ranged from κ 0.66 to 0.92 per segment.CONCLUSIONS: Fully automated segmental detection of thoracic aortic calcifications in chest CT performs with high accuracy. This includes the critical preoperative assessment of the aortic clamping zone.