Cervical spine fracture detection in computed tomography using convolutional neural networks.

Objective.In the context of primary in-hospital trauma management timely reading of computed tomography (CT) images is critical. However, assessment of the spine is time consuming, fractures can be very subtle, and the potential for under-diagnosis or delayed diagnosis is relevant. Artificial intelligence is increasingly employed to assist radiologists with the detection of spinal fractures and prioritization of cases. Currently, algorithms focusing on the cervical spine are commercially available. A common approach is the vertebra-wise classification. Instead of a classification task, we formulate fracture detection as a segmentation task aiming to find and display all individual fracture locations presented in the image.Approach.Based on 195 CT examinations, 454 cervical spine fractures were identified and annotated by radiologists at a tertiary trauma center. We trained for the detection a U-Net via four-fold-cross validation to segment spine fractures and the spine via a multi-task loss. We further compared advantages of two image reformation approaches-straightened curved planar reformatted (CPR) around the spine and spinal canal aligned volumes of interest (VOI)-to achieve a unified vertebral alignment in comparison to processing the Cartesian data directly.Main results.Of the three data versions (Cartesian, reformatted, VOI) the VOI approach showed the best detection rate and a reduced computation time. The proposed algorithm was able to detect 87.2% of cervical spine fractures at an average number of false positives of 3.5 per case. Evaluation of the method on a public spine dataset resulted in 0.9 false positive detections per cervical spine case.Significance.The display of individual fracture locations as provided with high sensitivity by the proposed voxel classification based fracture detection has the potential to support the trauma CT reading workflow by reducing missed findings.

Machine learning for automated 3-dimensional segmentation of the spine and suggested placement of pedicle screws based on intraoperative cone-beam computer tomography.

OBJECTIVE: The goal of this study was to develop and validate a system for automatic segmentation of the spine, pedicle identification, and screw path suggestion for use with an intraoperative 3D surgical navigation system. METHODS: Cone-beam CT (CBCT) images of the spines of 21 cadavers were obtained. An automated model-based approach was used for segmentation. Using machine learning methodology, the algorithm was trained and validated on the image data sets. For measuring accuracy, surface area errors of the automatic segmentation were compared to the manually outlined reference surface on CBCT. To further test both technical and clinical accuracy, the algorithm was applied to a set of 20 clinical cases. The authors evaluated the system's accuracy in pedicle identification by measuring the distance between the user-defined midpoint of each pedicle and the automatically segmented midpoint. Finally, 2 independent surgeons performed a qualitative evaluation of the segmentation to judge whether it was adequate to guide surgical navigation and whether it would have resulted in a clinically acceptable pedicle screw placement. RESULTS: The clinically relevant pedicle identification and automatic pedicle screw planning accuracy was 86.1%. By excluding patients with severe spinal deformities (i.e., Cobb angle > 75° and severe spinal degeneration) and previous surgeries, a success rate of 95.4% was achieved. The mean time (± SD) for automatic segmentation and screw planning in 5 vertebrae was 11 ± 4 seconds. CONCLUSIONS: The technology investigated has the potential to aid surgeons in navigational planning and improve surgical navigation workflow while maintaining patient safety.

Automated assessment of paraspinal muscle fat composition based on the segmentation of chemical shift encoding-based water/fat-separated images.

Proton-density fat fraction (PDFF) of the paraspinal muscles, derived from chemical shift encoding-based water-fat magnetic resonance imaging, has emerged as an important surrogate biomarker in individuals with intervertebral disc disease, osteoporosis, sarcopenia and neuromuscular disorders. However, quantification of paraspinal muscle PDFF is currently limited in clinical routine due to the required time-consuming manual segmentation procedure. The present study aimed to develop an automatic segmentation algorithm of the lumbar paraspinal muscles based on water-fat sequences and compare the performance of this algorithm to ground truth data based on manual segmentation. The algorithm comprised an average shape model, a dual feature model, associating each surface point with a fat and water image appearance feature, and a detection model. Right and left psoas, quadratus lumborum and erector spinae muscles were automatically segmented. Dice coefficients averaged over all six muscle compartments amounted to 0.83 (range 0.75-0.90).

A voxel-based diffusion tensor imaging study in unipolar and bipolar depression.

OBJECTIVE: The absence of neurobiological diagnostic markers of bipolar disorder (BD) leads to its frequent misdiagnosis as unipolar depression (UD). We investigated if changes in fractional anisotropy (FA) could help to differentiate BD from UD in the state of depression. METHODS: Using diffusion tensor imaging (DTI) we employed a voxel-based analysis approach to examine fractional anisotropy (FA) in 86 patients experiencing an acute major depressive episode according to DSM-IV (N=39 BD, mean age 39.2 years; N=43 UD, mean age 39.0 years), and 42 healthy controls (HC, mean age 36.1 years). The groups did not differ in sex, age or total education time. FA was investigated in white matter (FA >.2) and hypothesis-driven anatomically defined tracts (region-of-interest [ROI] analysis). Additionally, an exploratory gray matter FA analysis was performed. RESULTS: White matter analysis showed decreased FA in the right corticospinal tract in UD vs HC and in the right corticospinal tract/superior longitudinal fascicle in BD vs HC and also in BD vs UD. ROI analysis revealed decreased FA in BD vs UD in the corpus callosum and in the cingulum. Gray matter exploratory analysis revealed decreased FA in the left middle frontal gyrus and in the right inferior frontal gyrus in UD vs HC, and in the left superior medial gyrus in BD vs HC. CONCLUSION: This is one of very few studies directly showing differences in FA between BD and UD. Gray matter FA changes in prefrontal areas might be precursors for future prefrontal gray matter abnormalities in these disorders.

Accelerated motion corrected three-dimensional abdominal MRI using total variation regularized SENSE reconstruction.

PURPOSE: Develop a nonrigid motion corrected reconstruction for highly accelerated free-breathing three-dimensional (3D) abdominal images without external sensors or additional scans. METHODS: The proposed method accelerates the acquisition by undersampling and performs motion correction directly in the reconstruction using a general matrix description of the acquisition. Data are acquired using a self-gated 3D golden radial phase encoding trajectory, enabling a two stage reconstruction to estimate and then correct motion of the same data. In the first stage total variation regularized iterative SENSE is used to reconstruct highly undersampled respiratory resolved images. A nonrigid registration of these images is performed to estimate the complex motion in the abdomen. In the second stage, the estimated motion fields are incorporated in a general matrix reconstruction, which uses total variation regularization and incorporates k-space data from multiple respiratory positions. The proposed approach was tested on nine healthy volunteers and compared against a standard gated reconstruction using measures of liver sharpness, gradient entropy, visual assessment of image sharpness and overall image quality by two experts. RESULTS: The proposed method achieves similar quality to the gated reconstruction with nonsignificant differences for liver sharpness (1.18 and 1.00, respectively), gradient entropy (1.00 and 1.00), visual score of image sharpness (2.22 and 2.44), and visual rank of image quality (3.33 and 3.39). An average reduction of the acquisition time from 102 s to 39 s could be achieved with the proposed method. CONCLUSION: In vivo results demonstrate the feasibility of the proposed method showing similar image quality to the standard gated reconstruction while using data corresponding to a significantly reduced acquisition time. Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance.

Highly efficient 3D motion-compensated abdomen MRI from undersampled golden-RPE acquisitions.

OBJECT: A common approach to compensate for respiratory motion in free-breathing 3D magnetic resonance imaging (MRI) is navigator gating where MRI data is only acquired when the respiratory signal coincides within a small predefined acceptance window. However, this leads to poor scan efficiency and prolonged scan times. Here, we propose a method to reconstruct motion-compensated 3D MRI of the abdomen acquired during free-breathing with nearly 100% scan efficiency without increasing scan time. MATERIALS AND METHODS: The approach is based on a self-gated golden-radial phase encoding sampling scheme that allows for the reconstruction of multiple undersampled 3D images at different respiratory positions. Non-rigid image registrations and time-wise motion field interpolations are employed to form 3D motion models that combine all low-quality images into one high-quality motion-compensated image. RESULTS: Our highly efficient technique allows reconstruction of 3D liver MRI with a high isotropic resolution of 1.75 mm from a short acquisition of 1.1 min. The approach is validated in 10 healthy volunteers by comparing image quality to data sets acquired with a self-gating approach. CONCLUSION: Our method reduces scan time by 56% compared to the gating technique while similar image quality is preserved.

Prospective high-resolution respiratory-resolved whole-heart MRI for image-guided cardiovascular interventions.

Cardiovascular diseases, including arrhythmias and heart failure, are commonly treated with percutaneous procedures guided by X-ray fluoroscopy. The visualization of the targeted structures can be enhanced using preacquired respiratory-resolved anatomic data (dynamic roadmap), which is displayed as an overlay onto X-ray fluoroscopy images. This article demonstrates how dynamic roadmaps using an affine motion model can be obtained from one respiratory-resolved three-dimensional whole-heart acquisition using the previously introduced Radial Phase Encoding-Phase Ordering with Automatic Window Selection method. Respiratory motion in different regions of the heart was analyzed in 10 volunteers, and it was shown that the use of dynamic roadmaps can reduce misalignment errors from more than 10 down to less than 1.5 mm. Furthermore, the results suggest that reliable motion information can be obtained from highly undersampled images due to the advantageous undersampling properties of the radial phase encoding trajectory. Finally, results of a three-dimensional dynamic roadmap obtained from a patient before catheter ablation for atrial fibrillation treatment are presented.

Hierarchical adaptive local affine registration for fast and robust respiratory motion estimation.

Non-rigid image registration techniques are commonly used to estimate complex tissue deformations in medical imaging. A range of non-rigid registration algorithms have been proposed, but they typically have high computational complexity. To reduce this complexity, combinations of multiple less complex deformations have been proposed such as hierarchical techniques which successively split the non-rigid registration problem into multiple locally rigid or affine components. However, to date the splitting has been regular and the underlying image content has not been considered in the splitting process. This can lead to errors and artefacts in the resulting motion fields. In this paper, we propose three novel adaptive splitting techniques, an image-based, a similarity-based, and a motion-based technique within a hierarchical framework which attempt to process regions of similar motion and/or image structure in single registration components. We evaluate our technique on free-breathing whole-chest 3D MRI data from 10 volunteers and two publicly available CT datasets. We demonstrate a reduction in registration error of up to 49.1% over a non-adaptive technique and compare our results with a commonly used free-form registration algorithm.

Simultaneous PET-MR acquisition and MR-derived motion fields for correction of non-rigid motion in PET.

OBJECTIVE: Positron emission tomography (PET) provides an accurate measurement of radiotracer concentration in vivo, but performance can be limited by subject motion which degrades spatial resolution and quantitative accuracy. This effect may become a limiting factor for PET studies in the body as PET scanner technology improves. In this work, we propose a new approach to address this problem by employing motion information from images measured simultaneously using a magnetic resonance (MR) scanner. METHODS: The approach is demonstrated using an MR-compatible PET scanner and PET-MR acquisition with a purpose-designed phantom capable of non-rigid deformations. Measured, simultaneously acquired MR data were used to correct for motion in PET, and results were compared with those obtained using motion information from PET images alone. RESULTS: Motion artefacts were significantly reduced and the PET image quality and quantification was significantly improved by the use of MR motion fields, whilst the use of PET-only motion information was less successful. CONCLUSIONS: Combined PET-MR acquisitions potentially allow PET motion compensation in whole-body acquisitions without prolonging PET acquisition time or increasing radiation dose. This, to the best of our knowledge, is the first study to demonstrate that simultaneously acquired MR data can be used to estimate and correct for the effects of non-rigid motion in PET.