Refine
Has Fulltext
- yes (4)
Is part of the Bibliography
- yes (4)
Document Type
- Journal article (3)
- Doctoral Thesis (1)
Keywords
- lung (4) (remove)
Institute
- Institut für diagnostische und interventionelle Radiologie (Institut für Röntgendiagnostik) (4) (remove)
Background
Functional lung MRI techniques are usually associated with time-consuming post-processing, where manual lung segmentation represents the most cumbersome part. The aim of this study was to investigate whether deep learning-based segmentation of lung images which were scanned by a fast UTE sequence exploiting the stack-of-spirals trajectory can provide sufficiently good accuracy for the calculation of functional parameters.
Methods
In this study, lung images were acquired in 20 patients suffering from cystic fibrosis (CF) and 33 healthy volunteers, by a fast UTE sequence with a stack-of-spirals trajectory and a minimum echo-time of 0.05 ms. A convolutional neural network was then trained for semantic lung segmentation using 17,713 2D coronal slices, each paired with a label obtained from manual segmentation. Subsequently, the network was applied to 4920 independent 2D test images and results were compared to a manual segmentation using the Sørensen–Dice similarity coefficient (DSC) and the Hausdorff distance (HD). Obtained lung volumes and fractional ventilation values calculated from both segmentations were compared using Pearson’s correlation coefficient and Bland Altman analysis.
To investigate generalizability to patients outside the CF collective, in particular to those exhibiting larger consolidations inside the lung, the network was additionally applied to UTE images from four patients with pneumonia and one with lung cancer.
Results
The overall DSC for lung tissue was 0.967 ± 0.076 (mean ± standard deviation) and HD was 4.1 ± 4.4 mm. Lung volumes derived from manual and deep learning based segmentations as well as values for fractional ventilation exhibited a high overall correlation (Pearson’s correlation coefficent = 0.99 and 1.00). For the additional cohort with unseen pathologies / consolidations, mean DSC was 0.930 ± 0.083, HD = 12.9 ± 16.2 mm and the mean difference in lung volume was 0.032 ± 0.048 L.
Conclusions
Deep learning-based image segmentation in stack-of-spirals based lung MRI allows for accurate estimation of lung volumes and fractional ventilation values and promises to replace the time-consuming step of manual image segmentation in the future.
Purpose
The aim of this study was to compare the wave‐CAIPI (controlled aliasing in parallel imaging) trajectory to the Cartesian sampling for accelerated free‐breathing 4D lung MRI.
Methods
The wave‐CAIPI k‐space trajectory was implemented in a respiratory self‐gated 3D spoiled gradient echo pulse sequence. Trajectory correction applying the gradient system transfer function was used, and images were reconstructed using an iterative conjugate gradient SENSE (CG SENSE) algorithm. Five healthy volunteers and one patient with squamous cell carcinoma in the lung were examined on a clinical 3T scanner, using both sampling schemes. For quantitative comparison of wave‐CAIPI and standard Cartesian imaging, the normalized mutual information and the RMS error between retrospectively accelerated acquisitions and their respective references were calculated. The SNR ratios were investigated in a phantom study.
Results
The obtained normalized mutual information values indicate a lower information loss due to acceleration for the wave‐CAIPI approach. Average normalized mutual information values of the wave‐CAIPI acquisitions were 10% higher, compared with Cartesian sampling. Furthermore, the RMS error of the wave‐CAIPI technique was lower by 19% and the SNR was higher by 14%. Especially for short acquisition times (down to 1 minute), the undersampled Cartesian images showed an increased artifact level, compared with wave‐CAIPI.
Conclusion
The application of the wave‐CAIPI technique to 4D lung MRI reduces undersampling artifacts, in comparison to a Cartesian acquisition of the same scan time. The benefit of wave‐CAIPI sampling can therefore be traded for shorter examinations, or enhancing image quality of undersampled 4D lung acquisitions, keeping the scan time constant.
Background
Among the modalities for lung imaging, proton magnetic resonance imaging (MRI) has been the latest to be introduced into clinical practice. Its value to replace X-ray and computed tomography (CT) when radiation exposure or iodinated contrast material is contra-indicated is well acknowledged: i.e. for paediatric patients and pregnant women or for scientific use. One of the reasons why MRI of the lung is still rarely used, except in a few centres, is the lack of consistent protocols customised to clinical needs.
Methods
This article makes non-vendor-specific protocol suggestions for general use with state-of-the-art MRI scanners, based on the available literature and a consensus discussion within a panel of experts experienced in lung MRI.
Results
Various sequences have been successfully tested within scientific or clinical environments. MRI of the lung with appropriate combinations of these sequences comprises morphological and functional imaging aspects in a single examination. It serves in difficult clinical problems encountered in daily routine, such as assessment of the mediastinum and chest wall, and even might challenge molecular imaging techniques in the near future.
Conclusion
This article helps new users to implement appropriate protocols on their own MRI platforms.
Main Messages
• MRI of the lung can be readily performed on state-of-the-art 1.5-T MRI scanners.
• Protocol suggestions based on the available literature facilitate its use for routine
• MRI offers solutions for complicated thoracic masses with atelectasis and chest wall invasion.
• MRI is an option for paediatrics and science when CT is contra-indicated
Das Ziel dieser Arbeit war die Evaluierung von morphologischen und funktionellen Techniken zur Untersuchung der Lunge am Niederfeld MRT bei Patienten mit Mukoviszidose. Patienten mit Mukoviszidose und lungengesunde Probanden wurden an einem Niederfeld-MRT (0,2 Tesla) mittels coronaren TrueFISP, FLASH 2D und FLASH 3D Sequenzen untersucht. T1 und T2*-Messungen wurden während Atmung von Raumluft und Atmung von 100 % Sauerstoff durchgeführt und die Parameterkarten pixelweise berechnet. Die für die Lungenbildgebung am Niederfeld-MRT optimierten 2D und 3D FLASH Sequenzen zeigten ein signifikant besseres Signalverhalten als die Standardsequenz TrueFISP. Zur Beurteilung der Parenchymveränderungen wurde ein MR-Score in Anlehnung an den Chrispin-Norman-Score angewandt. Es zeigte sich eine gute Korrelation zwischen dem MR-Score der FLASH-Sequenzen und dem etablierten CN-Score der konventionellen Bildgebung mit einer geringen Interobservariabiliät für die 2D und 3D FLASH Sequenzen. Schließlich konnte eine O2-gestütze funktionelle Bildgebung der Lunge bei Patienten mit Mukoviszidose am offenen Niederfeld-MRT etabliert werden. Es zeigten sich gute Korrelationen zwischen der relativen Änderung der T1 Relaxationszeit und der spirometrisch bestimmten Lungenfunktion. Ein solcher Zusammenhang konnte für die T2*-Messungen nicht hergestellt werden. Aufgrund der Patientenfreundlichkeit ist diese Technik insbesondere für die Untersuchung von Kindern geeignet.