Fast CSF MRI for brain segmentation; Cross-validation by comparison with 3D T1-based brain segmentation methods

Assessment of the Impact of Turbo Factor on Image Quality and Tissue Volumetrics in Brain Magnetic Resonance Imaging Using the Three-Dimensional T1-Weighted (3D T1W) Sequence

Background

The 3D T1W turbo field echo sequence is a standard imaging method for acquiring high-contrast images of the brain. However, the contrast-to-noise ratio (CNR) can be affected by the turbo factor, which could affect the delineation and segmentation of various structures in the brain and may consequently lead to misdiagnosis. This study is aimed at evaluating the effect of the turbo factor on image quality and volumetric measurement reproducibility in brain magnetic resonance imaging (MRI).

Methods

Brain images of five healthy volunteers with no history of neurological diseases were acquired on a 1.5 T MRI scanner with varying turbo factors of 50, 100, 150, 200, and 225. The images were processed and analyzed with FreeSurfer. The influence of the TFE factor on image quality and reproducibility of brain volume measurements was investigated. Image quality metrics assessed included the signal-to-noise ratio (SNR) of white matter (WM), CNR between gray matter/white matter (GM/WM) and gray matter/cerebrospinal fluid (GM/CSF), and Euler number (EN). Moreover, structural brain volume measurements of WM, GM, and CSF were conducted.

Results

Turbo factor 200 produced the best SNR (median = 17.01) and GM/WM CNR (median = 2.29), but turbo factor 100 offered the most reproducible SNR (IQR = 2.72) and GM/WM CNR (IQR = 0.14). Turbo factor 50 had the worst and the least reproducible SNR, whereas turbo factor 225 had the worst and the least reproducible GM/WM CNR. Turbo factor 200 again had the best GM/CSF CNR but offered the least reproducible GM/CSF CNR. Turbo factor 225 had the best performance on EN (-21), while turbo factor 200 was next to the most reproducible turbo factor on EN (11). The results showed that turbo factor 200 had the least data acquisition time, in addition to superior performance on SNR, GM/WM CNR, GM/CSF CNR, and good reproducibility characteristics on EN. Both image quality metrics and volumetric measurements did not vary significantly (p > 0.05) with the range of turbo factors used in the study by one-way ANOVA analysis.

Conclusion

Since no significant differences were observed in the performance of the turbo factors in terms of image quality and volume of brain structure, turbo factor 200 with a 74% acquisition time reduction was found to be optimal for brain MR imaging at 1.5 T.

Validation of a shortened MR imaging protocol for pediatric spinal pathology

OBJECTIVE

Conventional pediatric spine MRI protocols have multiple sequences resulting in long acquisition times. Sedation is consequently required. This study evaluates the diagnostic capability of a limited MRI spine protocol for selected common pediatric indications.

METHODS

Spine MRIs at CHEO between 2017 and 2020 were reviewed across pediatric patients younger than four years old. Two blinded neuroradiologists reviewed limited scan sequences, and results were independently compared to previously reported findings from the complete imaging series. T2 sagittal sequences from the craniocervical junction to sacrum and T1 axial sequence of the lumbar spine constitute the short protocol, with the outcomes of interest being cerebellar ectopia, syrinx, level of conus, filum < 2 mm, fatty filum, and spinal dysraphism.

RESULTS

A total of 105 studies were evaluated in 54 male and 51 female patients (mean age 19.2 months). The average combined scan time of the limited sequences was 15 min compared to 35 min for conventional protocols (delta = 20 min). The average percent agreement between full and limited sequences was > 95% in all but identifying a filum < 2 mm, where the percent agreement was 87%. Using limited MR sequences had high sensitivity (> 0.91) and specificity (> 0.99) for the detection of cerebellar ectopia, syrinx, fatty filum, and spinal dysraphism.

CONCLUSION

This study demonstrates that selected spinal imaging sequences allow for consistent and accurate diagnosis of specific clinical conditions. A limited spine imaging protocol has potential as a screening test to reduce the need for full-sequence MRI scans. Further work is needed to determine utility of selected imaging for other clinical indications.

Artificially intelligent differential diagnosis of enlarged lymph nodes with random vector functional link network plus

Differential diagnosis of enlarged lymph nodes (ELNs) is essential for the treatment of related patients. Though multi-modal ultrasound including B-mode, Doppler ultrasound, elastography and contrast-enhanced ultrasound (CEUS) can enhance diagnostic performance for ELNs, the scenario of having only single or dual modal data is often encountered. In this study, an artificially intelligent diagnosis model based on the learning using privileged information was proposed to aid in differential diagnosis of ELNs in the case of single or dual modal images. In our model, B-mode, or combined with another modality, was used as the standard information (SI) and other modalities were used as the privileged information (PI). The model was constructed through the combination of the SI and PI in the training stage. By learning from the training samples, a random vector functional link network with privileged information (RVFL+) was obtained, which was used to classify the testing samples of solely the SI. Results showed that the accuracy, precision and Youden's index of the RVFL+ model, using B-mode with elastography as the SI and CEUS as the PI, reached 78.4%, 92.4% and 54.9%, increased by 14.0%, 8.4% and 24.5% compared with the model using B-mode as the SI without the PI. The method based on the LUPI can improve the diagnostic performance for ELNs.

Arterial CO2 pressure changes during hypercapnia are associated with changes in brain parenchymal volume

The Monro-Kellie hypothesis (MKH) states that volume changes in any intracranial component (blood, brain tissue, cerebrospinal fluid) should be counterbalanced by a co-occurring opposite change to maintain intracranial pressure within the fixed volume of the cranium. In this feasibility study, we investigate the MKH application to structural magnetic resonance imaging (MRI) in observing compensating intracranial volume changes during hypercapnia, which causes an increase in cerebral blood volume. Seven healthy subjects aged from 24 to 64 years (median 32), 4 males and 3 females, underwent a 3-T three-dimensional T1-weighted MRI under normocapnia and under hypercapnia. Intracranial tissue volumes were computed. According to the MKH, the significant increase in measured brain parenchymal volume (median 6.0 mL; interquartile range 4.5, 8.5; p = 0.016) during hypercapnia co-occurred with a decrease in intracranial cerebrospinal fluid (median -10.0 mL; interquartile range -13.5, -6.5; p = 0.034). These results convey several implications: (i) blood volume changes either caused by disorders, anaesthesia, or medication can affect outcome of brain volumetric studies; (ii) besides probing tissue displacement, this approach may assess the brain cerebrovascular reactivity. Future studies should explore the use of alternative sequences, such as three-dimensional T2-weighted imaging, for improved quantification of hypercapnia-induced volume changes.

An Improved Full Convolutional Network Combined with Conditional Random Fields for Brain MR Image Segmentation Algorithm and its 3D Visualization Analysis

Existing brain region segmentation algorithms based on deep convolutional neural networks (CNN) are inefficient for object boundary segmentation. In order to enhance the segmentation accuracy of brain tissue, this paper proposed an object region segmentation algorithm that combines pixel-level information and semantic information. Firstly, we extract semantic information by CNN with the attention module and get the coarse segmentation results through a specific pixel-level classifier. Then, we exploit conditional random fields to model the relationship between the underlying pixels so as to get local features. Finally, the semantic information and the local pixel-level information are respectively used as the unary potential and the binary potential of the Gibbs distribution, and the combination of both can obtain the fine region segmentation algorithm based on the fusion of pixel-level information and the semantic information. A large number of qualitative and quantitative test results show that our proposed algorithm has higher precision than the existing state-of-the-art deep feature models, which can better solve the problem of rough edge segmentation and produce good 3D visualization effect.