Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: a deep learning method based on FLAIR and MP2RAGE

Rosa, Francesco La; Abdulkadir, Ahmed; Fartaria, Mário João; Rahmanzadeh, Reza; Lu, Po-Jui; Galbusera, Riccardo; Baraković, Muhamed; Thiran, Jean‐Philippe; Granziera, Cristina; Cuadra, M. Bach

doi:10.1016/j.nicl.2020.102335

Cited by 92 publications

(62 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this combination of sequences is typical of imaging available in university clinics and used in clinical studies. This contrasts with other recent approaches which have employed MP2RAGE 30 or 7 Telsa imaging 34 . It would, of course, be ideal to present a method which can perform at a high level on a variety of imaging contrasts.…”

Section: Discussionmentioning

confidence: 80%

See 1 more Smart Citation

Simultaneous lesion and brain segmentation in multiple sclerosis using deep neural networks

McKinley

Wepfer

Aschwanden

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Segmentation of white matter lesions and deep grey matter structures is an important task in the quantification of magnetic resonance imaging in multiple sclerosis. In this paper we explore segmentation solutions based on convolutional neural networks (CNNs) for providing fast, reliable segmentations of lesions and grey-matter structures in multi-modal MR imaging, and the performance of these methods when applied to out-of-centre data. We trained two state-of-the-art fully convolutional CNN architectures on the 2016 MSSEG training dataset, which was annotated by seven independent human raters: a reference implementation of a 3D Unet, and a more recently proposed 3D-to-2D architecture (DeepSCAN). We then retrained those methods on a larger dataset from a single centre, with and without labels for other brain structures. We quantified changes in performance owing to dataset shift, and changes in performance by adding the additional brain-structure labels. We also compared performance with freely available reference methods. Both fully-convolutional CNN methods substantially outperform other approaches in the literature when trained and evaluated in cross-validation on the MSSEG dataset, showing agreement with human raters in the range of human inter-rater variability. Both architectures showed drops in performance when trained on single-centre data and tested on the MSSEG dataset. When trained with the addition of weak anatomical labels derived from Freesurfer, the performance of the 3D Unet degraded, while the performance of the DeepSCAN net improved. Overall, the DeepSCAN network predicting both lesion and anatomical labels was the best-performing network examined.

show abstract

Section: Discussionmentioning

confidence: 80%

“…As recommended by the authors of the toolkit, we used our training cases to determine the best initial threshold for the LGA algorithm. LST and nicMSlesions have both been used as benchmark methods in recent publications on MS lesion segmentation 30 , 31 .…”

Section: Methodsmentioning

confidence: 99%

Simultaneous lesion and brain segmentation in multiple sclerosis using deep neural networks

McKinley

Wepfer

Aschwanden

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…MS lesions in white matter (WM) show hyperintensities on FLAIR images and in grey matter (GM) are blackholes on MP2RAGE images of the uniform contrast in Fig. 2 a. WM lesions were automatically segmented ( La Rosa et al, 2020 ) and manually corrected by two expert raters. Juxtacortical lesions (JCLs) and periventricular lesions (PVLs) were defined as WM lesions located within 3 mm of the boundary between (i) WM and GM and (ii) WM and ventricles, respectively, in Fig.…”

Section: Methodsmentioning

confidence: 99%

GAMER MRI: Gated-attention mechanism ranking of multi-contrast MRI in brain pathology

Yoo

Rahmanzadeh

et al. 2021

NeuroImage: Clinical

Self Cite

View full text Add to dashboard Cite

“…In addition, they also explored whether adding an additional past time point to the input can improve segmentation performance. La Rosa et al (2020) uses magnetization-prepared 2 rapid acquisition with gradient echo(MP2RAGE) MRI to segment cortical lesions(CLs). Compared to this method, other methods just segment white matter lesions(WMLs).…”

Section: Semantic-wise Segmentationmentioning

confidence: 99%

Review of Deep Learning Approaches for the Segmentation of Multiple Sclerosis Lesions on Brain MRI

Zeng

Liu

et al. 2020

Front. Neuroinform.

View full text Add to dashboard Cite

In recent years, there have been multiple works of literature reviewing methods for automatically segmenting multiple sclerosis (MS) lesions. However, there is no literature systematically and individually review deep learning-based MS lesion segmentation methods. Although the previous review also included methods based on deep learning, there are some methods based on deep learning that they did not review. In addition, their review of deep learning methods did not go deep into the specific categories of Convolutional Neural Network (CNN). They only reviewed these methods in a generalized form, such as supervision strategy, input data handling strategy, etc. This paper presents a systematic review of the literature in automated multiple sclerosis lesion segmentation based on deep learning. Algorithms based on deep learning reviewed are classified into two categories through their CNN style, and their strengths and weaknesses will also be given through our investigation and analysis. We give a quantitative comparison of the methods reviewed through two metrics: Dice Similarity Coefficient (DSC) and Positive Predictive Value (PPV). Finally, the future direction of the application of deep learning in MS lesion segmentation will be discussed.

show abstract

Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: a deep learning method based on FLAIR and MP2RAGE

Abstract: Graphical abstract

Cited by 92 publications

References 31 publications

Simultaneous lesion and brain segmentation in multiple sclerosis using deep neural networks

Simultaneous lesion and brain segmentation in multiple sclerosis using deep neural networks

GAMER MRI: Gated-attention mechanism ranking of multi-contrast MRI in brain pathology

Review of Deep Learning Approaches for the Segmentation of Multiple Sclerosis Lesions on Brain MRI

Contact Info

Product

Resources

About