Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution.

PURPOSE: The purpose of this study was to propose a deep learning-based approach to detect pulmonary embolism and quantify its severity using the Qanadli score and the right-to-left ventricle diameter (RV/LV) ratio on three-dimensional (3D) computed tomography pulmonary angiography (CTPA) examinations with limited annotations. MATERIALS AND METHODS: Using a database of 3D CTPA examinations of 1268 patients with image-level annotations, and two other public datasets of CTPA examinations from 91 (CAD-PE) and 35 (FUME-PE) patients with pixel-level annotations, a pipeline consisting of: (i), detecting blood clots; (ii), performing PE-positive versus negative classification; (iii), estimating the Qanadli score; and (iv), predicting RV/LV diameter ratio was followed. The method was evaluated on a test set including 378 patients. The performance of PE classification and severity quantification was quantitatively assessed using an area under the curve (AUC) analysis for PE classification and a coefficient of determination (R²) for the Qanadli score and the RV/LV diameter ratio. RESULTS: Quantitative evaluation led to an overall AUC of 0.870 (95% confidence interval [CI]: 0.850-0.900) for PE classification task on the training set and an AUC of 0.852 (95% CI: 0.810-0.890) on the test set. Regression analysis yielded R² value of 0.717 (95% CI: 0.668-0.760) and of 0.723 (95% CI: 0.668-0.766) for the Qanadli score and the RV/LV diameter ratio estimation, respectively on the test set. CONCLUSION: This study shows the feasibility of utilizing AI-based assistance tools in detecting blood clots and estimating PE severity scores with 3D CTPA examinations. This is achieved by leveraging blood clots and cardiac segmentations. Further studies are needed to assess the effectiveness of these tools in clinical practice.

Synthetic MR image generation of macrotrabecular-massive hepatocellular carcinoma using generative adversarial networks.

PURPOSE: The purpose of this study was to develop a method for generating synthetic MR images of macrotrabecular-massive hepatocellular carcinoma (MTM-HCC). MATERIALS AND METHODS: A set of abdominal MR images including fat-saturated T1-weighted images obtained during the arterial and portal venous phases of enhancement and T2-weighted images of 91 patients with MTM-HCC, and another set of MR abdominal images from 67 other patients were used. Synthetic images were obtained using a 3-step pipeline that consisted in: (i), generating a synthetic MTM-HCC tumor on a neutral background; (ii), randomly selecting a background among the 67 patients and a position inside the liver; and (iii), merging the generated tumor in the background at the specified location. Synthetic images were qualitatively evaluated by three radiologists and quantitatively assessed using a mix of 1-nearest neighbor classifier metric and Fréchet inception distance. RESULTS: A set of 1000 triplets of synthetic MTM-HCC images with consistent contrasts were successfully generated. Evaluation of selected synthetic images by three radiologists showed that the method gave realistic, consistent and diversified images. Qualitative and quantitative evaluation led to an overall score of 0.64. CONCLUSION: This study shows the feasibility of generating realistic synthetic MR images with very few training data, by leveraging the wide availability of liver backgrounds. Further studies are needed to assess the added value of those synthetic images for automatic diagnosis of MTM-HCC.

3D variable-density SPARKLING trajectories for high-resolution T2*-weighted magnetic resonance imaging.

We have recently proposed a new optimization algorithm called SPARKLING (Spreading Projection Algorithm for Rapid K-space sampLING) to design efficient compressive sampling patterns for magnetic resonance imaging (MRI). This method has a few advantages over conventional non-Cartesian trajectories such as radial lines or spirals: i) it allows to sample the k-space along any arbitrary density while the other two are restricted to radial densities and ii) it optimizes the gradient waveforms for a given readout time. Here, we introduce an extension of the SPARKLING method for 3D imaging by considering both stacks-of-SPARKLING and fully 3D SPARKLING trajectories. Our method allowed to achieve an isotropic resolution of 600 µm in just 45 seconds for T2∗-weighted ex vivo brain imaging at 7 Tesla over a field-of-view of 200 × 200 × 140 mm3 . Preliminary in vivo human brain data shows that a stack-of-SPARKLING is less subject to off-resonance artifacts than a stack-of-spirals.

SPARKLING: variable-density k-space filling curves for accelerated T2* -weighted MRI.

PURPOSE: To present a new optimition-driven design of optimal k-space trajectories in the context of compressed sensing: Spreading Projection Algorithm for Rapid K-space sampLING (SPARKLING). THEORY: The SPARKLING algorithm is a versatile method inspired from stippling techniques that automatically generates optimized sampling patterns compatible with MR hardware constraints on maximum gradient amplitude and slew rate. These non-Cartesian sampling curves are designed to comply with key criteria for optimal sampling: a controlled distribution of samples (e.g., variable density) and a locally uniform k-space coverage. METHODS: Ex vivo and in vivo prospective T2* -weighted acquisitions were performed on a 7-Tesla scanner using the SPARKLING trajectories for various setups and target densities. Our method was compared to radial and variable-density spiral trajectories for high-resolution imaging. RESULTS: Combining sampling efficiency with compressed sensing, the proposed sampling patterns allowed up to 20-fold reductions in MR scan time (compared to fully sampled Cartesian acquisitions) for two-dimensional T2* -weighted imaging without deterioration of image quality, as demonstrated by our experimental results at 7 Tesla on in vivo human brains for a high in-plane resolution of 390 µm. In comparison to existing non-Cartesian sampling strategies, the proposed technique also yielded superior image quality. CONCLUSIONS: The proposed optimization-driven design of k-space trajectories is a versatile framework that is able to enhance MR sampling performance in the context of compressed sensing.

An empirical study of the maximum degree of undersampling in compressed sensing for T2*-weighted MRI.

Magnetic Resonance Imaging (MRI) is one of the most dynamic and safe imaging modalities used in clinical routine today. Yet, one major limitation to this technique resides in its long acquisition times. Over the last decade, Compressed Sensing (CS) has been increasingly used to address this issue and offers to shorten MR scans by reconstructing images from undersampled Fourier data. Nevertheless, a quantitative guide on the degree of acceleration applicable to a given acquisition scenario is still lacking today, leading in practice to a trial-and-error approach in the selection of the appropriate undersampling factor. In this study, we shortly point out the existing theoretical sampling results in CS and their limitations which motivate the focus of this work: an empirical and quantitative analysis of the maximum degree of undersampling allowed by CS in the specific context of T2*-weighted MRI. We make use of a generic method based on retrospective undersampling to quantitatively deduce the maximum acceleration factor Rmax which preserves a desired image quality as a function of the image resolution and the available signal-to-noise ratio (SNR). Our results quantify how larger acceleration factors can be applied to higher resolution images as long as a minimum SNR is guaranteed. In practice however, the maximum acceleration factor for a given resolution appears to be constrained by the available SNR inherent to the considered acquisition. Our analysis enables to take this a priori knowledge into account, allowing to derive a sequence-specific maximum acceleration factor adapted to the intrinsic SNR of any MR pipeline. These results obtained on an analytical T2*-weighted phantom image were corroborated by prospective experiments performed on MR data collected with radial trajectories on a 7 T scanner with the same contrast. The proposed framework allows to study other sequence weightings and therefore better optimize sequences when accelerated using CS.

Clustering dynamics of microbubbles exposed to low-pressure 1-MHz ultrasound.

Ultrasound-driven microbubbles have been used in therapeutic applications to deliver drugs across capillaries and into cells or to dissolve blood clots. Yet the performance and safety of these applications have been difficult to control. Microbubbles exposed to ultrasound not only volumetrically oscillate, but also move due to acoustic radiation, or Bjerknes, forces. The purpose of this work was to understand the extent to which microbubbles moved and clustered due to secondary Bjerknes forces. A microbubble population was exposed to a 1-MHz ultrasound pulse with a peak-rarefactional pressure of 50-100 kPa and a pulse length of 20 ms. Microbubbles exposed to low-pressure therapeutic ultrasound were observed to cluster at clustering rates of 0.01-0.02 microbubbles per duration (in ms) per initial average inter-bubble distance (in µm), resulting in 1 to 3 clustered microbubbles per initial average inter-bubble distance (in µm). Higher pressures caused faster clustering rates and a larger number of clustered microbubbles. Experimental data revealed clustering time scales, cluster localizations, and cluster sizes that were in reasonable agreement with simulations using a time-averaged model at low pressures. This study demonstrates that clustering of microbubbles occurs within a few milliseconds and is likely to influence the distribution of stimuli produced in therapeutic applications.

Torsional behavior of axonal microtubule bundles.

Axonal microtubule (MT) bundles crosslinked by microtubule-associated protein (MAP) tau are responsible for vital biological functions such as maintaining mechanical integrity and shape of the axon as well as facilitating axonal transport. Breaking and twisting of MTs have been previously observed in damaged undulated axons. Such breaking and twisting of MTs is suggested to cause axonal swellings that lead to axonal degeneration, which is known as "diffuse axonal injury". In particular, overstretching and torsion of axons can potentially damage the axonal cytoskeleton. Following our previous studies on mechanical response of axonal MT bundles under uniaxial tension and compression, this work seeks to characterize the mechanical behavior of MT bundles under pure torsion as well as a combination of torsional and tensile loads using a coarse-grained computational model. In the case of pure torsion, a competition between MAP tau tensile and MT bending energies is observed. After three turns, a transition occurs in the mechanical behavior of the bundle that is characterized by its diameter shrinkage. Furthermore, crosslink spacing is shown to considerably influence the mechanical response, with larger MAP tau spacing resulting in a higher rate of turns. Therefore, MAP tau crosslinking of MT filaments protects the bundle from excessive deformation. Simultaneous application of torsion and tension on MT bundles is shown to accelerate bundle failure, compared to pure tension experiments. MAP tau proteins fail in clusters of 10-100 elements located at the discontinuities or the ends of MT filaments. This failure occurs in a stepwise fashion, implying gradual accumulation of elastic tensile energy in crosslinks followed by rupture. Failure of large groups of interconnecting MAP tau proteins leads to detachment of MT filaments from the bundle near discontinuities. This study highlights the importance of torsional loading in axonal damage after traumatic brain injury.