Evaluation of Thick-Slab Overlapping MIP Images of Contrast-Enhanced 3D T1-Weighted CUBE for Detection of Intracranial Metastases: A Pilot Study for Comparison of Lesion Detection, Interpretation Time, and Sensitivity with Nonoverlapping CUBE MIP, CUBE, and Inversion-Recovery-Prepared Fast-Spoiled Gradient Recalled Brain Volume

Automated Detection of Brain Metastases on T1-Weighted MRI Using a Convolutional Neural Network: Impact of Volume Aware Loss and Sampling Strategy

BACKGROUND

Detection of brain metastases (BM) and segmentation for treatment planning could be optimized with machine learning methods. Convolutional neural networks (CNNs) are promising, but their trade-offs between sensitivity and precision frequently lead to missing small lesions.

HYPOTHESIS

Combining volume aware (VA) loss function and sampling strategy could improve BM detection sensitivity.

STUDY TYPE

Retrospective.

POPULATION

A total of 530 radiation oncology patients (55% women) were split into a training/validation set (433 patients/1460 BM) and an independent test set (97 patients/296 BM).

FIELD STRENGTH/SEQUENCE

1.5 T and 3 T, contrast-enhanced three-dimensional (3D) T1-weighted fast gradient echo sequences.

ASSESSMENT

Ground truth masks were based on radiotherapy treatment planning contours reviewed by experts. A U-Net inspired model was trained. Three loss functions (Dice, Dice + boundary, and VA) and two sampling methods (label and VA) were compared. Results were reported with Dice scores, volumetric error, lesion detection sensitivity, and precision. A detected voxel within the ground truth constituted a true positive.

STATISTICAL TESTS

McNemar's exact test to compare detected lesions between models. Pearson's correlation coefficient and Bland-Altman analysis to compare volume agreement between predicted and ground truth volumes. Statistical significance was set at P ≤ 0.05.

RESULTS

Combining VA loss and VA sampling performed best with an overall sensitivity of 91% and precision of 81%. For BM in the 2.5-6 mm estimated sphere diameter range, VA loss reduced false negatives by 58% and VA sampling reduced it further by 30%. In the same range, the boundary loss achieved the highest precision at 81%, but a low sensitivity (24%) and a 31% Dice loss.

DATA CONCLUSION

Considering BM size in the loss and sampling function of CNN may increase the detection sensitivity regarding small BM. Our pipeline relying on a single contrast-enhanced T1-weighted MRI sequence could reach a detection sensitivity of 91%, with an average of only 0.66 false positives per scan.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Vessel wall MR imaging in neuroradiology

Vessel wall MR imaging (VW-MRI) has been introduced into clinical practice and applied to a variety of diseases, and its usefulness has been reported. High-resolution VW-MRI is essential in the diagnostic workup and provides more information than other routine MR imaging protocols. VW-MRI is useful in assessing lesion location, morphology, and severity. Additional information, such as vessel wall enhancement, which is useful in the differential diagnosis of atherosclerotic disease and vasculitis could be assessed by this special imaging technique. This review describes the VW-MRI technique and its clinical applications in arterial disease, venous disease, vasculitis, and leptomeningeal disease.

From Dose Reduction to Contrast Maximization: Can Deep Learning Amplify the Impact of Contrast Media on Brain Magnetic Resonance Image Quality? A Reader Study

OBJECTIVES

The aim of this study was to evaluate a deep learning method designed to increase the contrast-to-noise ratio in contrast-enhanced gradient echo T1-weighted brain magnetic resonance imaging (MRI) acquisitions. The processed images are quantitatively evaluated in terms of lesion detection performance.

MATERIALS AND METHODS

A total of 250 multiparametric brain MRIs, acquired between November 2019 and March 2021 at Gustave Roussy Cancer Campus (Villejuif, France), were considered for inclusion in this retrospective monocentric study. Independent training (107 cases; age, 55 ± 14 years; 58 women) and test (79 cases; age, 59 ± 14 years; 41 women) samples were defined. Patients had glioma, brain metastasis, meningioma, or no enhancing lesion. Gradient echo and turbo spin echo with variable flip angles postcontrast T1 sequences were acquired in all cases. For the cases that formed the training sample, "low-dose" postcontrast gradient echo T1 images using 0.025 mmol/kg injections of contrast agent were also acquired. A deep neural network was trained to synthetically enhance the low-dose T1 acquisitions, taking standard-dose T1 MRI as reference. Once trained, the contrast enhancement network was used to process the test gradient echo T1 images. A read was then performed by 2 experienced neuroradiologists to evaluate the original and processed T1 MRI sequences in terms of contrast enhancement and lesion detection performance, taking the turbo spin echo sequences as reference.

RESULTS

The processed images were superior to the original gradient echo and reference turbo spin echo T1 sequences in terms of contrast-to-noise ratio (44.5 vs 9.1 and 16.8; P < 0.001), lesion-to-brain ratio (1.66 vs 1.31 and 1.44; P < 0.001), and contrast enhancement percentage (112.4% vs 85.6% and 92.2%; P < 0.001) for cases with enhancing lesions. The overall image quality of processed T1 was preferred by both readers (graded 3.4/4 on average vs 2.7/4; P < 0.001). Finally, the proposed processing improved the average sensitivity of gradient echo T1 MRI from 88% to 96% for lesions larger than 10 mm (P = 0.008), whereas no difference was found in terms of the false detection rate (0.02 per case in both cases; P > 0.99). The same effect was observed when considering all lesions larger than 5 mm: sensitivity increased from 70% to 85% (P < 0.001), whereas false detection rates remained similar (0.04 vs 0.06 per case; P = 0.48). With all lesions included regardless of their size, sensitivities were 59% and 75% for original and processed T1 images, respectively (P < 0.001), and the corresponding false detection rates were 0.05 and 0.14 per case, respectively (P = 0.06).

CONCLUSION

The proposed deep learning method successfully amplified the beneficial effects of contrast agent injection on gradient echo T1 image quality, contrast level, and lesion detection performance. In particular, the sensitivity of the MRI sequence was improved by up to 16%, whereas the false detection rate remained similar.

EGFR-targeted intraoperative fluorescence imaging detects high-grade glioma with panitumumab-IRDye800 in a phase 1 clinical trial

Rationale: First-line therapy for high-grade gliomas (HGGs) includes maximal safe surgical resection. The extent of resection predicts overall survival, but current neuroimaging approaches lack tumor specificity. The epidermal growth factor receptor (EGFR) is a highly expressed HGG biomarker. We evaluated the safety and feasibility of an anti-EGFR antibody, panitumuab-IRDye800, at subtherapeutic doses as an imaging agent for HGG. Methods: Eleven patients with contrast-enhancing HGGs were systemically infused with panitumumab-IRDye800 at a low (50 mg) or high (100 mg) dose 1-5 days before surgery. Near-infrared fluorescence imaging was performed intraoperatively and ex vivo, to identify the optimal tumor-to-background ratio by comparing mean fluorescence intensities of tumor and histologically uninvolved tissue. Fluorescence was correlated with preoperative T1 contrast, tumor size, EGFR expression and other biomarkers. Results: No adverse events were attributed to panitumumab-IRDye800. Tumor fragments as small as 5 mg could be detected ex vivo and detection threshold was dose dependent. In tissue sections, panitumumab-IRDye800 was highly sensitive (95%) and specific (96%) for pathology confirmed tumor containing tissue. Cellular delivery of panitumumab-IRDye800 was correlated to EGFR overexpression and compromised blood-brain barrier in HGG, while normal brain tissue showed minimal fluorescence. Intraoperative fluorescence improved optical contrast in tumor tissue within and beyond the T1 contrast-enhancing margin, with contrast-to-noise ratios of 9.5 ± 2.1 and 3.6 ± 1.1, respectively. Conclusions: Panitumumab-IRDye800 provided excellent tumor contrast and was safe at both doses. Smaller fragments of tumor could be detected at the 100 mg dose and thus more suitable for intraoperative imaging.

Consensus recommendations for a standardized brain tumor imaging protocol for clinical trials in brain metastases

A recent meeting was held on March 22, 2019, among the FDA, clinical scientists, pharmaceutical and biotech companies, clinical trials cooperative groups, and patient advocacy groups to discuss challenges and potential solutions for increasing development of therapeutics for central nervous system metastases. A key issue identified at this meeting was the need for consistent tumor measurement for reliable tumor response assessment, including the first step of standardized image acquisition with an MRI protocol that could be implemented in multicenter studies aimed at testing new therapeutics. This document builds upon previous consensus recommendations for a standardized brain tumor imaging protocol (BTIP) in high-grade gliomas and defines a protocol for brain metastases (BTIP-BM) that addresses unique challenges associated with assessment of CNS metastases. The "minimum standard" recommended pulse sequences include: (i) parameter matched pre- and post-contrast inversion recovery (IR)-prepared, isotropic 3D T1-weighted gradient echo (IR-GRE); (ii) axial 2D T2-weighted turbo spin echo acquired after injection of gadolinium-based contrast agent and before post-contrast 3D T1-weighted images; (iii) axial 2D or 3D T2-weighted fluid attenuated inversion recovery; (iv) axial 2D, 3-directional diffusion-weighted images; and (v) post-contrast 2D T1-weighted spin echo images for increased lesion conspicuity. Recommended sequence parameters are provided for both 1.5T and 3T MR systems. An "ideal" protocol is also provided, which replaces IR-GRE with 3D TSE T1-weighted imaging pre- and post-gadolinium, and is best performed at 3T, for which dynamic susceptibility contrast perfusion is included. Recommended perfusion parameters are given.

Detection of brain metastases using alternative magnetic resonance imaging sequences: a comparison between SPACE and VIBE sequences

Background

Accurate identification of brain metastases is crucial for cancer treatment.

Objectives

To compare the ability to detect brain metastases of two alternative types of contrast-enhanced three-dimensional (3D) T1-weighted sequences called SPACE (Sampling Perfection with Application optimized Contrasts using different flip angle Evolutions) and VIBE (Volumetric Interpolated Brain Sequence) on magnetic resonance imaging (MRI) at 3 tesla.

Methods

Between April 2017 and February 2018, 27 consecutive adult Thai patients with a total number of 424 brain metastases were retrospectively included. The patients underwent both contrast-enhanced 3D T1-weighted SPACE and 3D T1-weighted VIBE MRI sequences at 3 tesla. Two neuroradiology experts independently reviewed the images to determine the number of enhancing lesions on each sequence. Wilcoxon signed rank test was used to compare the difference between the numbers of detectable parenchymal enhancing lesions. Interobserver reliability was calculated using intraclass correlation.

Results

3D T1-weighted SPACE detected more parenchymal enhancing lesions than 3D T1-weighted VIBE (424 vs. 378 lesions, median 6 vs. 5, P = 0.008). Fifteen patients (55.6%) had equal number of parenchymal enhancing lesions between two sequences. 3D T1-weighted SPACE detected more parenchymal enhancing lesions (up to 9 more lesions) in 10 patients (37%), while 3D T1-weighted VIBE detected more enhancing lesions (up to 2 more lesions) in 2 patients (7.4%). Interobserver reliability between the readers was excellent.

Conclusion

Contrast-enhanced 3D T1-weighted SPACE sequence demonstrates a higher ability to detect brain metastases than contrast-enhanced 3D T1-weighted VIBE sequence at 3 tesla.

Advanced Imaging of Brain Metastases: From Augmenting Visualization and Improving Diagnosis to Evaluating Treatment Response

Early detection of brain metastases and differentiation from other neuropathologies is crucial. Although biopsy is often required for definitive diagnosis, imaging can provide useful information. After treatment commences, imaging is also performed to assess the efficacy of treatment. Contrast-enhanced magnetic resonance imaging (MRI) is the traditional imaging method for the evaluation of brain metastases, as it provides information about lesion size, morphology, and macroscopic properties. Newer MRI sequences have been developed to increase the conspicuity of detecting enhancing metastases. Other advanced MRI techniques, that have the capability to probe beyond the anatomic structure, are available to characterize micro-structures, cellularity, physiology, perfusion, and metabolism. Artificial intelligence provides powerful computational tools for detection, segmentation, classification, prediction, and prognosis. We highlight and review a few advanced MRI techniques for the assessment of brain metastases-specifically for (1) diagnosis, including differentiating between malignancy types and (2) evaluation of treatment response, including the differentiation between radiation necrosis and disease progression.

Deep learning enables automatic detection and segmentation of brain metastases on multisequence MRI

BACKGROUND

Detecting and segmenting brain metastases is a tedious and time-consuming task for many radiologists, particularly with the growing use of multisequence 3D imaging.

PURPOSE

To demonstrate automated detection and segmentation of brain metastases on multisequence MRI using a deep-learning approach based on a fully convolution neural network (CNN).

STUDY TYPE

Retrospective.

POPULATION

In all, 156 patients with brain metastases from several primary cancers were included.

FIELD STRENGTH

1.5T and 3T. [Correction added on May 24, 2019, after first online publication: In the preceding sentence, the first field strength listed was corrected.] SEQUENCE: Pretherapy MR images included pre- and postgadolinium T₁ -weighted 3D fast spin echo (CUBE), postgadolinium T₁ -weighted 3D axial IR-prepped FSPGR (BRAVO), and 3D CUBE fluid attenuated inversion recovery (FLAIR).

ASSESSMENT

The ground truth was established by manual delineation by two experienced neuroradiologists. CNN training/development was performed using 100 and 5 patients, respectively, with a 2.5D network based on a GoogLeNet architecture. The results were evaluated in 51 patients, equally separated into those with few (1-3), multiple (4-10), and many (>10) lesions.

STATISTICAL TESTS

Network performance was evaluated using precision, recall, Dice/F1 score, and receiver operating characteristic (ROC) curve statistics. For an optimal probability threshold, detection and segmentation performance was assessed on a per-metastasis basis. The Wilcoxon rank sum test was used to test the differences between patient subgroups.

RESULTS

The area under the ROC curve (AUC), averaged across all patients, was 0.98 ± 0.04. The AUC in the subgroups was 0.99 ± 0.01, 0.97 ± 0.05, and 0.97 ± 0.03 for patients having 1-3, 4-10, and >10 metastases, respectively. Using an average optimal probability threshold determined by the development set, precision, recall, and Dice score were 0.79 ± 0.20, 0.53 ± 0.22, and 0.79 ± 0.12, respectively. At the same probability threshold, the network showed an average false-positive rate of 8.3/patient (no lesion-size limit) and 3.4/patient (10 mm³ lesion size limit).

DATA CONCLUSION

A deep-learning approach using multisequence MRI can automatically detect and segment brain metastases with high accuracy.

LEVEL OF EVIDENCE

3 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2020;51:175-182.