Comparison of contrast-enhanced T1-weighted imaging using DANTE-SPACE, PETRA, and MPRAGE: a clinical evaluation of brain tumors at 3 Tesla

PVTAD: ALZHEIMER'S DISEASE DIAGNOSIS USING PYRAMID VISION TRANSFORMER APPLIED TO WHITE MATTER OF T1-WEIGHTED STRUCTURAL MRI DATA

Alzheimer's disease (AD) is a neurodegenerative disorder, and timely diagnosis is crucial for early interventions. AD is known to have disruptive local and global brain neural connections that may be instrumental in understanding and extracting specific biomarkers. Previous machine-learning approaches are mostly based on convolutional neural network (CNN) and standard vision transformer (ViT) models which may not sufficiently capture the multidimensional local and global patterns that may be indicative of AD. Therefore, in this paper, we propose a novel approach called PVTAD to classify AD and cognitively normal (CN) cases using pretrained pyramid vision transformer (PVT) and white matter (WM) of T1-weighted structural MRI (sMRI) data. Our approach combines the advantages of CNN and standard ViT to extract both local and global features indicative of AD from the WM coronal middle slices. We performed experiments on subjects with T1-weighed MPRAGE sMRI scans from the ADNI dataset. Our results demonstrate that the PVTAD achieves an average accuracy of 97.7% and F1-score of 97.6%, outperforming the single and parallel CNN and standard ViT architectures based on sMRI data for AD vs. CN classification.

Optimization of workflow for detection of brain metastases at 3T: is a black-blood MTC prepared 3D T1 used alone robust enough to replace the combination of conventional 3D T1 and the black-blood 3D T1 MTC?

PURPOSE

Sampling perfection with application-optimized contrasts by using different flip angle evolutions (SPACE) is a black-blood 3D T1-weighted (T1w) magnetic resonance imaging (MRI) sequence that has shown robust performance for brain metastases detection. However, this could generate false positive results due to suboptimal blood signal suppression. For that reason, SPACE is used in our institution alongside a non-black-blood T1w sequence: volumetric interpolated breath-hold examination (VIBE). Our study aims to (i) evaluate the diagnostic accuracy of SPACE compared to its use in combination with VIBE, (ii) investigate the effect of radiologist's experience in the sequence's performance, and (iii) analyze causes of discordants results.

METHODS

Four hundred seventy-three 3T MRI scans were retrospectively analyzed following a monocentric study design. Two studies were formed: one including SPACE alone and one combining both sequences (SPACE + VIBE, the reference). An experienced neuroradiologist and a radiology trainee independently reviewed the images of each study and reported the number of brain metastases. The sensitivity (Se) and specificity (Sp) of SPACE compared to SPACE + VIBE in metastases detection were reported. Diagnostic accuracy of SPACE compared to SPACE + VIBE was assessed by using McNemar's test. Significance was set at p < 0.05. Cohen's kappa was used for inter-method and inter-observer variability.

RESULTS

No significant difference was found between the two methods, with SPACE having a Se > 93% and a Sp > 87%. No effect of readers' experience was disclosed.

CONCLUSION

Independently of radiologist's experience, SPACE alone is robust enough to replace SPACE + VIBE for brain metastases detection.

[Evaluation of Enhanced 3D Brain Image Using Ultrashort TE Sequence with Inversion Recovery for Preoperative Examination of Brain Tumor: Phantom Study Compared with MPRAGE]

It is important to obtain accurate anatomical information with little distortion in preoperative examination of brain tumors. Using PETRA, which is an ultrashort echo time (UTE) sequence that is less affected by magnetic susceptibility artifacts, we determined the optimal imaging conditions (radial views [RV] and inversion time [TI]) for IR-PETRA using the inversion recovery (IR) method and compared it with MPRAGE. IR-PETRA was found to be slightly inferior to MPRAGE in sharpness under the optimum conditions (RV=100,000 and TI=500 ms), but it was significantly improved by using a high RV value, and SNR and CNR were higher than or equal to MPRAGE. It is suggested that IR-PETRA may be an alternative sequence of MPRAGE in preoperative examination of brain tumors.

Preoperative Assessment of Blood Vessels and Intratumoral Microbleeds in Brain Tumors Based on a 3D Contrast-Enhanced T1 -Weighted Flow-Sensitive Black-Blood Sequence

BACKGROUND

Three-dimensional (3D) contrast-enhanced T₁ -weighted flow-sensitive black-blood (CE-T₁ WI FSBB) is a newly developed black blood sequence by adding motion probing gradient pulses to gradient echo (GRE) sequences, which has important value for the preoperative assessment of tumor brain blood supply vessels and intratumoral microbleeds.

PURPOSE

To compare 3D CE-T₁ WI FSBB and 3D contrast-enhanced fast spin echo (FSE) sequence for T₁ WI for preoperative assessment of blood vessels and microbleeds in brain tumors and to investigate the correlation between visible vessels and microbleeds.

STUDY TYPE

Prospective.

SUBJECTS

One hundred and seventy-five patients with brain tumors, 65 were male, 110 were female. Including histologically confirmed 73 meningiomas, 23 schwannomas, 20 gliomas, 7 hemangioblastomas, 5 metastases, 2 lymphomas, 2 hemangiopericytomas, 2 germ cell tumors, 1 craniopharyngioma, and 1 cholesteatoma.

FIELD STRENGTH/SEQUENCE

A 3-T, CE-T₁ WI FSBB, GRE; 3-T, CE-T₁ WI, FSE.

ASSESSMENT

Three neuroradiologists counted the number of intratumoral vessels on CE-T₁ WI and CE-T₁ WI FSBB images separately, and they counted the number of intratumoral microbleeds on CE-T₁ WI FSBB images. Brain tumors were classified into grade I, grade II, and grade IV according to the World Health Organization (WHO) grading. Differences in the ability of CE-T₁ WI FSBB and CE-T₁ WI to display intratumoral vessels were compared. The mean counts of three observers were used to study the correlation between vessels and microbleeds.

STATISTICAL TESTS

Two-way random intraclass correlation coeficient (ICC) was used for inter-reader agreement regarding intratumoral vessel and microbleed counts, and the linear regression analysis (with F-test) was used to study the correlation between intratumoral vessels and microbleeds based on CE-T₁ WI FSBB (α = 0.05).

RESULTS

Inter-reader agreements for intratumoral vessel count on CE-T₁ WI (ICC = 0.93) and CE-T₁ WI FSBB (ICC = 0.92), and the agreement for intratumoral microbleed count on CE-T₁ WI FSBB (ICC = 0.99) were excellent. There were statistically significant differences in intratumoral vessel counts between CE-T₁ WI and CE-T₁ WI FSBB using Mann-Whitney U -test: image readers could identify more intratumoral vessels on CE-T₁ WI FSBB images, particularly for meningiomas, schwannomas, gliomas, and WHO grade I tumors. The number of intratumoral vessels had a significant positive effect on the number of intratumoral microbleeds (microbleeds = 5.024 + 1.665 × vessels; F = 11.51).

DATA CONCLUSION

More intratumoral vessels could potentially be identified using a 3D CE-T₁ WI FSBB sequence compared to a CE-T₁ WI sequence, and the number of intratumoral vessels showed a positive linear relationship with the number of intratumoral microbleeds, which might suggest that brain tumors with rich blood supply were more prone to intratumoral microbleeds.

EVIDENCE LEVEL

2 TECHNICAL EFFICACY: Stage 3.