Multiple sclerosis lesion activity segmentation with attention-guided two-path CNNs

Gessert, Nils; Krüger, Julia; Opfer, Roland; Ostwaldt, Ann-Christin; Manogaran, Praveena; Kitzler, Hagen H.; Schippling, Sven; Schlaefer, Alexander

doi:10.1016/j.compmedimag.2020.101772

Cited by 47 publications

(28 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, it is planned to conduct periodic studies on MS follow-up on dataset. [37] MICCAI 2008 cascaded 3D CNN 56.0 NA Birenbaum and Greenspan [44] ISBI 2015 multi-view CNN 62.70 NA Ravnik et al [38] UMCL CNN 81.49 69.95 Zhao et al [10] MICCAI 2008, a level set method 55.0 NA Atlason et al [45] the AGES-Reykjavik, MICCAI 2017 CNN autoencoder 77.0, 67.0 64.0, 40.0 Wang et al [30] MICCAI 2008 adaptive sparse Bayesian model 42.0 NA Gessert et al [49] their…”

Section: Resultsmentioning

confidence: 99%

“…RC in (4), which shows how much of the lesions in an image are segmented correctly, refers to the ratio of successfully masked lesions on the image to all lesions on the image [64]. LTPR, in (5), is the number of lesions that overlap in segmentation and ground truth map divided by the total number of lesions in the ground truth map [49]. Here, LTP shows the number of lesions in the reference segmentation that overlap with a lesion in the output segmentation, and RL is the total number of lesions in the reference segmentation [65].…”

Section: Experimental Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Automatic detection of multiple sclerosis lesions using Mask R‐CNN on magnetic resonance scans

Yildirim

Dandıl

2020

IET image process

View full text Add to dashboard Cite

Multiple Sclerosis (MS) causes the central nervous system to malfunction due to inflammation surrounding nerve cells. Detection of MS at an early stage is very important to prevent progressive MS attacks. Clinical findings, cerebrospinal fluid examinations, the evoked potentials, magnetic resonance imaging (MRI) findings have an important role in the diagnosis and follow-up of MS. However, many of the findings on MRI may indicate brain disorders other than MS. In addition, the clinical practices accepted by physicians for MS detection are very limited. In this study, a Mask R-CNN based method in two dataset is proposed for the automatic detection of MS lesions on magnetic resonance scans.We also improved the ROI detection stage with RPN in the Mask R-CNN to easily adapt for different lesion sizes. MS lesions in different sizes in the dataset are successfully detected with 84.90% Dice similarity rate and 87.03% precision rates using the proposed method. In addition, volumetric overlap error and lesion-wise true positive rate are obtained as 12.97% and 73.75%, respectively. Moreover, performance tests of the use of different numbers of GPU hardware structures are also performed and the evaluation of its effects on processing speed is performed on experimental studies..

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Experimental Studiesmentioning

confidence: 99%

Automatic detection of multiple sclerosis lesions using Mask R‐CNN on magnetic resonance scans

Yildirim

Dandıl

2020

IET image process

View full text Add to dashboard Cite

show abstract

“…For the domain shift problem in MS lesion segmentation, Ackaouy et al (2020) proposes an unsupervised method that learns a shared representation of the source and target domains. Gessert et al (2020b) segment the newly emerging MS lesions by attention mechanism with two paths network while the general method only considers MS lesions segmentation in a single MRI volume. This task is particularly challenging because new lesions are minute, changes are subtle.…”

Section: Semantic-wise Segmentationmentioning

confidence: 99%

“…Through our research, we found that some recent work began to introducing the sequence model (Gessert et al, 2020a,b) to segment the activity of MS lesions. The task of segmentation of multiple sclerosis lesion activity is to detect the appearance of new and enlarged lesions between the baseline and subsequent brain MRI scans (Gessert et al, 2020b). We think this is also a future direction for the segmentation task.…”

Section: Future Directionmentioning

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

“…Nils et al, further extended this segmentation process by the inclusion of two scans made at two separate time positions. Their work in [13] has elucidated that MR images from two different time schedules had a great impact on the exploration of this MS extraction method. The activity-based inspection and deep learning techniques made the process of MS diagnosis to become a step more manageable and simpler.…”

Section: Summary Of Previous Work On Ms Lesion Detectionmentioning

confidence: 99%

Automated Detection of Multiple Sclerosis Lesions in Normal Appearing White Matter from Brain MRI: A Survey

Khatokar

Kumar

Chandrahas

et al. 2021

AJCST

View full text Add to dashboard Cite

Multiple Sclerosis is an inoperable disease of the Central Nervous System (CNS) that irritates the myelin sheath by forming lesions. This affects all organs of the CNS; the vital of them is the brain. This disease can be detected by diagnosis like Magnetic Resonance Imaging (MRI). It is a non-invasive diagnostic test that provides detailed images of the soft tissues of the body. Out of the different variations of MRI, MS lesions are predominantly visible in the DTI (Diffusion Tensor Imaging) variant of MRI. DTI gives enhanced visualization of normal-appearing white matter tracts of the organs, hence providing a better image of the MS lesion. In this paper, the latest methodologies regarding the identification of the MS lesions in MRI scans like T2 FLAIR or DTI, using automated techniques like deep learning, computer vision, neural network and many more are surveyed. Furthermore, this paper consists of a proposed model which would focus on correlating the lesions found in DTI scan with the basic MRI scan like T2. It would identify the MS lesion in DTI scan and eventually highlight that lesion position in the T2 image scan. This would help radiologist in a way to effectively handle multiple MRI scans.

show abstract

Multiple sclerosis lesion activity segmentation with attention-guided two-path CNNs

Cited by 47 publications

References 29 publications

Automatic detection of multiple sclerosis lesions using Mask R‐CNN on magnetic resonance scans

Automatic detection of multiple sclerosis lesions using Mask R‐CNN on magnetic resonance scans

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

Automated Detection of Multiple Sclerosis Lesions in Normal Appearing White Matter from Brain MRI: A Survey

Contact Info

Product

Resources

About