Improved reconstruction for highly accelerated propeller diffusion 1.5 T clinical MRI

PURPOSE

Propeller fast-spin-echo diffusion magnetic resonance imaging (FSE-dMRI) is essential for the diagnosis of Cholesteatoma. However, at clinical 1.5 T MRI, its signal-to-noise ratio (SNR) remains relatively low. To gain sufficient SNR, signal averaging (number of excitations, NEX) is usually used with the cost of prolonged scan time. In this work, we leveraged the benefits of Locally Low Rank (LLR) constrained reconstruction to enhance the SNR. Furthermore, we enhanced both the speed and SNR by employing Convolutional Neural Networks (CNNs) for the accelerated PROPELLER FSE-dMRI on a 1.5 T clinical scanner.

METHODS

Residual U-Net (RU-Net) was found to be efficient for propeller FSE-dMRI data. It was trained to predict 2-NEX images obtained by Locally Low Rank (LLR) constrained reconstruction and used 1-NEX images obtained via simplified reconstruction as the inputs. The brain scans from healthy volunteers and patients with cholesteatoma were performed for model training and testing. The performance of trained networks was evaluated with normalized root-mean-square-error (NRMSE), structural similarity index measure (SSIM), and peak SNR (PSNR).

RESULTS

For 4 × under-sampled with 7 blades data, online reconstruction appears to provide suboptimal images-some small details are missing due to high noise interferences. Offline LLR enables suppression of noises and discovering some small structures. RU-Net demonstrated further improvement compared to LLR by increasing 18.87% of PSNR, 2.11% of SSIM, and reducing 53.84% of NRMSE. Moreover, RU-Net is about 1500 × faster than LLR (0.03 vs. 47.59 s/slice).

CONCLUSION

The LLR remarkably enhances the SNR compared to online reconstruction. Moreover, RU-Net improves propeller FSE-dMRI as reflected in PSNR, SSIM, and NRMSE. It requires only 1-NEX data, which allows a 2 × scan time reduction. In addition, its speed is approximately 1500 times faster than that of LLR-constrained reconstruction.

Stereotactic radiosurgery for limited brain metastasis using three different techniques: helical tomotherapy, volumetric modulated arc therapy, and cone-based LINAC radiosurgery

PURPOSE

Specific radiation delivered to tumors by stereotactic radiosurgery (SRS) has become widely used in the treatment of brain metastasis. This study aimed to compare radiation therapy planning and its parameters from SRS using three different modalities: helical tomotherapy (HT), volumetric modulated arc therapy (VMAT), and cone-based linac radiosurgery (Cone-based).

MATERIALS AND METHODS

Each contouring dataset of patents who experienced one to four brain metastasis received SRS in our center was re-planned to create radiation therapy planning in all three treatment systems (HT, VMAT, and Cone-based). The parameters of conformity index (CI), homogeneity index (HI), CI50, and gradient index (CGI) were analyzed to compare the effects of the three techniques. Decision score analysis was used to evaluate the performance on dosimetric and organs-at-risk parameters among the different techniques by applying the Cone-based technique as a benchmark.

RESULTS

A total of 21 patients with 39 lesions were included in this study. The results from the decision score analysis demonstrated statistically identical CI, CI50, and CGI values between Cone-based and VMAT for single lesions. For multiple lesions, VMAT also provided better CI when compared to Cone-based technique while HT exhibited the poorest dosimetric parameters. Moreover, VMAT exhibited the lowest BrainV5Gy value and displayed the shortest beam-on time calculation.

CONCLUSION

We have conducted a comprehensive comparison of SRS planning approaches. The Cone-based technique revealed the highest HI value, while VMAT provided the best estimated beam-on time value. HT displayed a feasible SRS modality for single lesions, but not for multiple lesions.

Conglomerate ring and tract-like enhancement lesions: Neuroimaging in Listeria monocytogenes brain abscess

This report aims to describe a characteristic neuroimaging of Listeria monocytogenes brain abscess in predisposed patients. A 56-year-old man presented with fever and headache for 3 weeks. Cerebrospinal fluid (CSF) revealed pleocytosis with lymphocytosis, high protein, and low glucose. Both hemoculture and CSF culture yielded L monocytogenes. Another case is a 23-year-old woman with systemic lupus erythematosus, who presented with fever, headache and left hemiparesis. CSF showed pleocytosis with polymorphonuclear cells predominance and low glucose. Hemoculture positive for L monocytogenes. Their MRI brain revealed conglomerate ring and tract-like enhancement lesions at the right parietotemporal lobe. The patients were diagnosed with L monocytogenes brain abscess. They received a high dose of ceftriaxone and ampicillin for 6 weeks. The clinical and MRI at the end of treatment was a substantial improvement. Our information can help the physician concern about this pathogen in patients who presented with brain abscess and had these MRI findings.

Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images

Ultrasound imaging is one of the most common visualizing tools used by radiologists to identify the location of thyroid nodules. However, visual assessment of nodules is difficult and often affected by inter- and intra-observer variabilities. Thus, a computer-aided diagnosis (CAD) system can be helpful to cross-verify the severity of nodules. This paper proposes a new CAD system to characterize thyroid nodules using optimized multi-level elongated quinary patterns. In this study, higher order spectral (HOS) entropy features extracted from these patterns appropriately distinguished benign and malignant nodules under particle swarm optimization (PSO) and support vector machine (SVM) frameworks. Our CAD algorithm achieved a maximum accuracy of 97.71% and 97.01% in private and public datasets respectively. The evaluation of this CAD system on both private and public datasets confirmed its effectiveness as a secondary tool in assisting radiological findings.