Artificial double inversion recovery images for (juxta)cortical lesion visualization in multiple sclerosis

Periventricular and juxtacortical characterization of UManitoba-JHU functionally defined human white matter atlas networks

Background

The open-access UManitoba-JHU functionally defined human white matter (WM) atlas contains specific WM pathways and general WM regions underlying 12 functional brain networks in ICBM152 template space. However, it is not known whether any of these WM networks are disproportionately co-localized with periventricular and/or juxtacortical WM (PVWM and JCWM), which could potentially impact their ability to infer network-specific effects in future studies-particularly in patient populations expected to have disproportionate PVWM and/or JCWM damage.

Methods

The current study therefore identified intersecting regions of PVWM and JCWM (defined as WM within 5 mm of the ventricular and cortical boundaries) and: (1) the ICBM152 global WM mask, and (2) all 12 UManitoba-JHU WM networks. Dice Similarity Coefficient (DSC), Jaccard Similarity Coefficient (JSC), and proportion of volume (POV) values between PVWM (and JCWM) and each functionally defined WM network were then compared to corresponding values between PVWM (and JCWM) and global WM.

Results

Between the 12 WM networks and PVWM, 8 had lower DSC, JSC, and POV; 1 had lower DSC and JSC, but higher POV; and 3 had higher DSC, JSC, and POV compared to global WM. For JCWM, all 12 WM networks had lower DSC, JSC, and POV compared to global WM.

Conclusion

The majority of UManitoba-JHU functionally defined WM networks exhibited lower than average spatial similarity with PVWM, and all exhibited lower than average spatial similarity with JCWM. This suggests that they can be used to explore network-specific WM changes, even in patient populations with known predispositions toward PVWM and/or JCWM damage.

Accurate Diagnosis of Cortical and Infratentorial Lesions in Multiple Sclerosis Using Accelerated Fluid and White Matter Suppression Imaging

OBJECTIVES

The precise location of multiple sclerosis (MS) cortical lesions can be very challenging at 3 T, yet distinguishing them from subcortical lesions is essential for the diagnosis and prognosis of the disease. Compressed sensing-accelerated fluid and white matter suppression imaging (CS-FLAWS) is a new magnetic resonance imaging sequence derived from magnetization-prepared 2 rapid acquisition gradient echo with promising features for the detection and classification of MS lesions. The objective of this study was to compare the diagnostic performances of CS-FLAWS (evaluated imaging) and phase sensitive inversion recovery (PSIR; reference imaging) for classification of cortical lesions (primary objective) and infratentorial lesions (secondary objective) in MS, in combination with 3-dimensional (3D) double inversion recovery (DIR).

MATERIALS AND METHODS

Prospective 3 T scans (MS first diagnosis or follow-up) acquired between March and August 2021 were retrospectively analyzed. All underwent 3D CS-FLAWS, axial 2D PSIR, and 3D DIR. Double-blinded reading sessions exclusively in axial plane and final consensual reading were performed to assess the number of cortical and infratentorial lesions. Wilcoxon test was used to compare the 2 imaging datasets (FLAWS + DIR and PSIR + DIR), and intraobserver and interobserver agreement was assessed using the intraclass correlation coefficient.

RESULTS

Forty-two patients were analyzed (38 with relapsing-remitting MS, 29 women, 42.7 ± 12.6 years old). Compressed sensing-accelerated FLAWS allowed the identification of 263 cortical lesions versus 251 with PSIR ( P = 0.74) and 123 infratentorial lesions versus 109 with PSIR ( P = 0.63), corresponding to a nonsignificant difference between the 2 sequences. Compressed sensing-accelerated FLAWS exhibited fewer false-negative findings than PSIR either for cortical lesions (1 vs 13; P < 0.01) or infratentorial lesions (1 vs 15; P < 0.01). No false-positive findings were found with any of the 2 sequences. Diagnostic confidence was high for each contrast.

CONCLUSION

Three-dimensional CS-FLAWS is as accurate as 2D PSIR imaging for classification of cortical and infratentorial MS lesions, with fewer false-negative findings, opening the way to a reliable full brain MS exploration in a clinically acceptable duration (5 minutes 15 seconds).

Multicenter Evaluation of AI-generated DIR and PSIR for Cortical and Juxtacortical Multiple Sclerosis Lesion Detection

Background Cortical multiple sclerosis lesions are clinically relevant but inconspicuous at conventional clinical MRI. Double inversion recovery (DIR) and phase-sensitive inversion recovery (PSIR) are more sensitive but often unavailable. In the past 2 years, artificial intelligence (AI) was used to generate DIR and PSIR from standard clinical sequences (eg, T1-weighted, T2-weighted, and fluid-attenuated inversion-recovery sequences), but multicenter validation is crucial for further implementation. Purpose To evaluate cortical and juxtacortical multiple sclerosis lesion detection for diagnostic and disease monitoring purposes on AI-generated DIR and PSIR images compared with MRI-acquired DIR and PSIR images in a multicenter setting. Materials and Methods Generative adversarial networks were used to generate AI-based DIR (n = 50) and PSIR (n = 43) images. The number of detected lesions between AI-generated images and MRI-acquired (reference) images was compared by randomized blinded scoring by seven readers (all with >10 years of experience in lesion assessment). Reliability was expressed as the intraclass correlation coefficient (ICC). Differences in lesion subtype were determined using Wilcoxon signed-rank tests. Results MRI scans of 202 patients with multiple sclerosis (mean age, 46 years ± 11 [SD]; 127 women) were retrospectively collected from seven centers (February 2020 to January 2021). In total, 1154 lesions were detected on AI-generated DIR images versus 855 on MRI-acquired DIR images (mean difference per reader, 35.0% ± 22.8; P < .001). On AI-generated PSIR images, 803 lesions were detected versus 814 on MRI-acquired PSIR images (98.9% ± 19.4; P = .87). Reliability was good for both DIR (ICC, 0.81) and PSIR (ICC, 0.75) across centers. Regionally, more juxtacortical lesions were detected on AI-generated DIR images than on MRI-acquired DIR images (495 [42.9%] vs 338 [39.5%]; P < .001). On AI-generated PSIR images, fewer juxtacortical lesions were detected than on MRI-acquired PSIR images (232 [28.9%] vs 282 [34.6%]; P = .02). Conclusion Artificial intelligence-generated double inversion-recovery and phase-sensitive inversion-recovery images performed well compared with their MRI-acquired counterparts and can be considered reliable in a multicenter setting, with good between-reader and between-center interpretative agreement. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Zivadinov and Dwyer in this issue.

Diagnostic utility of 3D DIR MRI in the estimation of MS lesions overall load with special emphasis on cortical subtypes

Background

A number of magnetic resonance imaging studies have shown that a significant proportion of multiple sclerosis (MS) lesions are located in the cerebral cortex and correlate with the patient's disability level. Double inversion recovery (DIR) has a higher sensitivity to detect cortical lesions and their different types. The aim of our study was to assess the superiority of 3D DIR as compared to FLAIR in detecting the different cortical subtypes and to enhance its role as a test for the clinical disability of the patient.

Results

The current study included 82 MS patients (60 female and 22 male with mean age of 34.5 ± 8.2 years); 59 cases having relapsing–remitting MS, 5 having secondary progressive MS, and 4 having primary progressive MS, as well as eight clinically isolated syndrome cases, and six radiologically isolated syndrome cases. DIR was superior to FLAIR in MS plaque number detection of cortical plaque-types 1, 2, 3 and 4 with a p value < 0.001. DIR was superior to FLAIR for detection of overall cortical types, juxtacortical and juxtacortical extended MS plaques with p =  < 0.001, 0.010 and < 0.001, respectively. DIR was significantly better than FLAIR for MS plaque number detection in the periventricular white matter, subcortical white matter, infratentorial region and the overall MS plaques burden with a p < 0.001, 0.038, < 0.001, < 0.001, respectively. No significant difference was noted between both sequences for plaques number detection in deep white matter and deep gray matter. A significant correlation between MS disease duration, number of attacks and EDSS and the overall cortical MS plaques types and the overall MS plaque burden.

Conclusion

3D DIR is a reliable tool and provides superior delineation in detecting cortical subtypes. In addition, DIR is of value in assessing the degree of clinical and cognitive impairment of MS affected patients.

Deep Learning for Automated Elective Lymph Node Level Segmentation for Head and Neck Cancer Radiotherapy

Depending on the clinical situation, different combinations of lymph node (LN) levels define the elective LN target volume in head-and-neck cancer (HNC) radiotherapy. The accurate auto-contouring of individual LN levels could reduce the burden and variability of manual segmentation and be used regardless of the primary tumor location. We evaluated three deep learning approaches for the segmenting individual LN levels I−V, which were manually contoured on CT scans from 70 HNC patients. The networks were trained and evaluated using five-fold cross-validation and ensemble learning for 60 patients with (1) 3D patch-based UNets, (2) multi-view (MV) voxel classification networks and (3) sequential UNet+MV. The performances were evaluated using Dice similarity coefficients (DSC) for automated and manual segmentations for individual levels, and the planning target volumes were extrapolated from the combined levels I−V and II−IV, both for the cross-validation and for an independent test set of 10 patients. The median DSC were 0.80, 0.66 and 0.82 for UNet, MV and UNet+MV, respectively. Overall, UNet+MV significantly (p < 0.0001) outperformed other arrangements and yielded DSC = 0.87, 0.85, 0.86, 0.82, 0.77, 0.77 for the combined and individual level I−V structures, respectively. Both PTVs were also significantly (p < 0.0001) more accurate with UNet+MV, with DSC = 0.91 and 0.90, respectively. The accurate segmentation of individual LN levels I−V can be achieved using an ensemble of UNets. UNet+MV can further refine this result.

Sex bias in multiple sclerosis and neuromyelitis optica spectrum disorders: How it influences clinical course, MRI parameters and prognosis

This review is a condensed summary of representative articles addressing the sex/gender bias in multiple sclerosis (MS) and neuromyelitis optica spectrum disorders (NMOSD). The strong effects of sex on the incidence and possibly also the activity and progression of these disorders should be implemented in the evaluation of any phase of clinical research and also in treatment choice consideration in clinical practice and evaluation of MRI parameters. Some relationships between clinical variables and gender still remain elusive but with further understanding of sex/gender-related differences, we should be able to provide appropriate patient-centered care and research.

Uncertainty-Aware and Lesion-Specific Image Synthesis in Multiple Sclerosis Magnetic Resonance Imaging: A Multicentric Validation Study

Generative adversarial networks (GANs) can synthesize high-contrast MRI from lower-contrast input. Targeted translation of parenchymal lesions in multiple sclerosis (MS), as well as visualization of model confidence further augment their utility, provided that the GAN generalizes reliably across different scanners. We here investigate the generalizability of a refined GAN for synthesizing high-contrast double inversion recovery (DIR) images and propose the use of uncertainty maps to further enhance its clinical utility and trustworthiness. A GAN was trained to synthesize DIR from input fluid-attenuated inversion recovery (FLAIR) and T1w of 50 MS patients (training data). In another 50 patients (test data), two blinded readers (R1 and R2) independently quantified lesions in synthetic DIR (synthDIR), acquired DIR (trueDIR) and FLAIR. Of the 50 test patients, 20 were acquired on the same scanner as training data (internal data), while 30 were scanned at different scanners with heterogeneous field strengths and protocols (external data). Lesion-to-Background ratios (LBR) for MS-lesions vs. normal appearing white matter, as well as image quality parameters were calculated. Uncertainty maps were generated to visualize model confidence. Significantly more MS-specific lesions were found in synthDIR compared to FLAIR (R1: 26.7 ± 2.6 vs. 22.5 ± 2.2 p < 0.0001; R2: 22.8 ± 2.2 vs. 19.9 ± 2.0, p = 0.0005). While trueDIR remained superior to synthDIR in R1 [28.6 ± 2.9 vs. 26.7 ± 2.6 (p = 0.0021)], both sequences showed comparable lesion conspicuity in R2 [23.3 ± 2.4 vs. 22.8 ± 2.2 (p = 0.98)]. Importantly, improvements in lesion counts were similar in internal and external data. Measurements of LBR confirmed that lesion-focused GAN training significantly improved lesion conspicuity. The use of uncertainty maps furthermore helped discriminate between MS lesions and artifacts. In conclusion, this multicentric study confirms the external validity of a lesion-focused Deep-Learning tool aimed at MS imaging. When implemented, uncertainty maps are promising to increase the trustworthiness of synthetic MRI.

Artificial double inversion recovery images can substitute conventionally acquired images: an MRI-histology study

Cortical multiple sclerosis lesions are disease-specific, yet inconspicuous on magnetic resonance images (MRI). Double inversion recovery (DIR) images are sensitive, but often unavailable in clinical routine and clinical trials. Artificially generated images can mitigate this issue, but lack histopathological validation. In this work, artificial DIR images were generated from postmortem 3D-T1 and proton-density (PD)/T2 or 3D-T1 and 3D fluid-inversion recovery (FLAIR) images, using a generative adversarial network. All sequences were scored for cortical lesions, blinded to histopathology. Subsequently, tissue samples were stained for proteolipid protein (myelin) and scored for cortical lesions type I-IV (leukocortical, intracortical, subpial and cortex-spanning, respectively). Histopathological scorings were then (unblinded) compared to MRI using linear mixed models. Images from 38 patients (26 female, mean age 64.3 ± 10.7) were included. A total of 142 cortical lesions were detected, predominantly subpial. Histopathology-blinded/unblinded sensitivity was 13.4/35.2% for artificial DIR generated from T1-PD/T2, 14.1/41.5% for artificial DIR from T1-FLAIR, 17.6/49.3% for conventional DIR and 10.6/34.5% for 3D-T1. When blinded to histopathology, there were no differences; with histopathological feedback at hand, conventional DIR and artificial DIR from T1-FLAIR outperformed the other sequences. Differences between histopathology-blinded/unblinded sensitivity could be minified through adjustment of the scoring criteria. In conclusion, artificial DIR images, particularly generated from T1-FLAIR could potentially substitute conventional DIR images when these are unavailable.