Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Document Type
- Journal article (2)
Language
- English (2) (remove)
Keywords
- diagnosis (2) (remove)
Institute
- Physikalisches Institut (2) (remove)
Background: Cystic fibrosis (CF) patients would benefit from a safe and effective tool to detect early-stage, regional lung disease to allow for early intervention. Magnetic Resonance Imaging (MRI) is a safe, non-invasive procedure capable of providing quantitative assessments of disease without ionizing radiation. We developed a rapid normalized T1 MRI technique to detect regional lung disease in early-stage CF patients.
Materials and Methods: Conventional multislice, pulmonary T1 relaxation time maps were obtained for 10 adult CF patients with normal spirometry and 5 healthy non-CF control subjects using a rapid Look-Locker MRI acquisition (5 seconds/imaging slice). Each lung absolute T1 map was separated into six regions of interest (ROI) by manually selecting upper, central, and lower lung regions in the left and right lungs. In order to reduce the effects of subject-to-subject variation, normalized T1 maps were calculated by dividing each pixel in the absolute T1 maps by the mean T1 time in the central lung region. The primary outcome was the differences in mean normalized T1 values in the upper lung regions between CF patients with normal spirometry and healthy volunteers.
Results: Normalized T1 (nT1) maps showed visibly reduced subject-to-subject variation in comparison to conventional absolute T1 maps for healthy volunteers. An ROI analysis showed that the variation in the nT1 values in all regions was <= 2% of the mean. The primary outcome, the mean (SD) of the normalized T1 values in the upper right lung regions, was significantly lower in the CF subjects [.914 (.037)] compared to the upper right lung regions of the healthy subjects [.983 (.003)] [difference of .069 (95% confidence interval .032-.105); p=.001). Similar results were seen in the upper left lung region.
Conclusion: Rapid normalized T1 MRI relaxometry obtained in 5 seconds/imaging slice may be used to detect regional early-stage lung disease in CF patients.
Automated analysis of the inner ear anatomy in radiological data instead of time-consuming manual assessment is a worthwhile goal that could facilitate preoperative planning and clinical research. We propose a framework encompassing joint semantic segmentation of the inner ear and anatomical landmark detection of helicotrema, oval and round window. A fully automated pipeline with a single, dual-headed volumetric 3D U-Net was implemented, trained and evaluated using manually labeled in-house datasets from cadaveric specimen (N = 43) and clinical practice (N = 9). The model robustness was further evaluated on three independent open-source datasets (N = 23 + 7 + 17 scans) consisting of cadaveric specimen scans. For the in-house datasets, Dice scores of 0.97 and 0.94, intersection-over-union scores of 0.94 and 0.89 and average Hausdorf distances of 0.065 and 0.14 voxel units were achieved. The landmark localization task was performed automatically with an average localization error of 3.3 and 5.2 voxel units. A robust, albeit reduced performance could be
attained for the catalogue of three open-source datasets. Results of the ablation studies with 43 mono-parametric variations of the basal architecture and training protocol provided task-optimal parameters for both categories. Ablation studies against single-task variants of the basal architecture showed a clear performance beneft of coupling landmark localization with segmentation and a dataset-dependent performance impact on segmentation ability.