FLAIR2 improves LesionTOADS automatic segmentation of multiple sclerosis lesions in non-homogenized, multi-center, 2D clinical magnetic resonance images

Background

Accurate segmentation of MS lesions on MRI is difficult and, if performed manually, time consuming. Automatic segmentations rely strongly on the image contrast and signal-to-noise ratio. Literature examining segmentation tool performances in real-world multi-site data acquisition settings is scarce.

Objective

FLAIR², a combination of T₂-weighted and fluid attenuated inversion recovery (FLAIR) images, improves tissue contrast while suppressing CSF. We compared the use of FLAIR and FLAIR² in LesionTOADS, OASIS and the lesion segmentation toolbox (LST) when applied to non-homogenized, multi-center 2D-imaging data.

Methods

Lesions were segmented on 47 MS patient data sets obtained from 34 sites using LesionTOADS, OASIS and LST, and compared to a semi-automatically generated reference. The performance of FLAIR and FLAIR² was assessed using the relative lesion volume difference (LVD), Dice coefficient (DSC), sensitivity (SEN) and symmetric surface distance (SSD). Performance improvements related to lesion volumes (LVs) were evaluated for all tools. For comparison, LesionTOADS was also used to segment lesions from 3 T single-center MR data of 40 clinically isolated syndrome (CIS) patients.

Results

Compared to FLAIR, the use of FLAIR² in LesionTOADS led to improvements of 31.6% (LVD), 14.0% (DSC), 25.1% (SEN), and 47.0% (SSD) in the multi-center study. DSC and SSD significantly improved for larger LVs, while LVD and SEN were enhanced independent of LV. OASIS showed little difference between FLAIR and FLAIR², likely due to its inherent use of T₂w and FLAIR. LST replicated the benefits of FLAIR² only in part, indicating that further optimization, particularly at low LVs is needed. In the CIS study, LesionTOADS did not benefit from the use of FLAIR² as the segmentation performance for both FLAIR and FLAIR² was heterogeneous.

Conclusions

In this real-world, multi-center experiment, FLAIR² outperformed FLAIR in its ability to segment MS lesions with LesionTOADS. The computation of FLAIR² enhanced lesion detection, at minimally increased computational time or cost, even retrospectively. Further work is needed to determine how LesionTOADS and other tools, such as LST, can optimally benefit from the improved FLAIR² contrast.

•

FLAIR² improves automatic MS lesion segmentation with LesionTOADS compared to FLAIR.

•

Segmentation similarity improves for higher lesion volumes, particularly for FLAIR².

•

FLAIR² provides greater sensitivity independent of lesion volume than FLAIR alone.

•

Other segmentation tools need further optimization to fully benefit from FLAIR².

•

FLAIR² provides immediate benefits at 1.5 T and visually improves segmentation at 3 T.

Noise reduction in FLAIR2 images using total generalized variation, Gaussian and Wiener filtering

PURPOSE

Multiplication of FLAIR and T2-weighted MRI scans results in images (called FLAIR²) with an improved contrast-to-noise ratio (CNR) for multiple sclerosis (MS) lesions but with a reduced signal-to-noise ratio (SNR). Denoising of these images may therefore further improve FLAIR² image quality. The purpose of this work is to present a systematic investigation of FLAIR² image denoising methods using Gaussian, Wiener and Total Generalized Variation (TGV) filtering approaches.

MATERIALS AND METHODS

T2-weighted and FLAIR data of four MS patients were used. For CNR and SNR measurements, each scan was performed up to three times. TGV, Gaussian and Wiener filtering was applied to T2, FLAIR and the FLAIR² data. FLAIR² images were afterwards additionally created using all combinations of input data (native, filtered T2 and filtered FLAIR). SNR and CNR measurements were performed using the subtraction method for all FLAIR² approaches (native and filtered input data) and for twenty MS lesions. Additionally, quantitative analysis of filtering based image blurring was performed on all data sets.

RESULTS

FLAIR² images denoised with TGV showed the highest SNR and CNR, while SNR values were similar for Gaussian and Wiener filtered images. The average CNR over 20 MS lesions within the native FLAIR² (32.99) achieved an improvement to 91.17, 82.33 and 56.07 corresponding to TGV, Wiener and Gaussian filtering. FLAIR multiplied with T2.denoised showed no improvement, while FLAIR.denoised multiplied with T2 showed an increase by a factor of two to the native, not filtered FLAIR². Blurring was most pronounced in Gaussian filtered images and similar in TGV and Wiener filtered images.

CONCLUSION

FLAIR images filtered with Wiener or TGV multiplied with the unfiltered T2 results in FLAIR² images with increased SNR and CNR and with minimal edge blurring.