A multi-center study of transformer-based CNNs for multiple sclerosis lesion segmentation on 3D FLAIR MRI.

Automated multiple sclerosis lesion segmentation from 3D-FLAIR MRI using R2AUNet: A deep learning approach with recurrent residual and attention mechanisms.

The aim of this study was to develop a new automated segmentation method of white matter (WM) and cortical multiple sclerosis (MS) lesions visible on magnetization-prepared 2 inversion-contrast rapid gradient echo (MP2RAGE) images acquired at 7 T MRI. The proposed prototype (MSLAST [Multiple Sclerosis Lesion Analysis at Seven Tesla]) takes as input a single image contrast derived from the 7T MP2RAGE prototype sequence and is based on partial volume estimation and topological constraints. First, MSLAST performs a skull-strip of MP2RAGE images and computes tissue concentration maps for WM, gray matter (GM), and cerebrospinal fluid (CSF) using a partial volume model of tissues within each voxel. Second, MSLAST performs (1) connected-component analysis to GM and CSF concentration maps to classify small isolated components as MS lesions; (2) hole-filling in the WM concentration map to classify areas with low WM concentration surrounded by WM (ie, MS lesions); and (3) outlier rejection to the WM mask to improve the classification of small WM lesions. Third, MSLAST unifies the 3 maps obtained from 1, 2, and 3 processing steps to generate a global lesion mask. Quantitative and qualitative assessments were performed using MSLAST in 25 MS patients from 2 research centers. Overall, MSLAST detected a median of 71% of MS lesions, specifically 74% of WM and 58% of cortical lesions, when a minimum lesion size of 6 μL was considered. The median false-positive rate was 40%. When a 15 μL minimal lesions size was applied, which is the approximation of the minimal size recommended for 1.5/3 T images, the median detection rate was 80% for WM and 63% for cortical lesions, respectively, and the median false-positive rate was 33%. We observed high correlation between MSLAST and manual segmentations (Spearman rank correlation coefficient, ρ = 0.91), although MSLAST underestimated the total lesion volume (average difference of 1.1 mL), especially in patients with high lesion loads. MSLAST also showed good scan-rescan repeatability within the same session with an average absolute volume difference and F1 score of 0.38 ± 0.32 mL and 84%, respectively. We propose a new methodology to facilitate the segmentation of WM and cortical MS lesions at 7 T MRI, our approach uses a single MP2RAGE scan and may be of special interest to clinicians and researchers.

Evaluate the performance of a deep learning (DL)-based model for multiple sclerosis (MS) lesion segmentation and compare it to other DL and non-DL algorithms. This ambispective, multicenter study assessed the performance of a DL-based model for MS lesion segmentation and compared it to alternative DL- and non-DL-based methods. Models were tested on internal (n = 20) and external (n = 18) datasets from Latin America, and on an external dataset from Europe (n = 49). We also examined robustness by rescanning six patients (n = 6) from our MS clinical cohort. Moreover, we studied inter-human annotator agreement and discussed our findings in light of these results. Performance and robustness were assessed using intraclass correlation coefficient (ICC), Dice coefficient (DC), and coefficient of variation (CV). Inter-human ICC ranged from 0.89 to 0.95, while spatial agreement among annotators showed a median DC of 0.63. Using expert manual segmentations as ground truth, our DL model achieved a median DC of 0.73 on the internal, 0.66 on the external, and 0.70 on the challenge datasets. The performance of our DL model exceeded that of the alternative algorithms on all datasets. In the robustness experiment, our DL model also achieved higher DC (ranging from 0.82 to 0.90) and lower CV (ranging from 0.7 to 7.9%) when compared to the alternative methods. Our DL-based model outperformed alternative methods for brain MS lesion segmentation. The model also proved to generalize well on unseen data and has a robust performance and low processing times both on real-world and challenge-based data. Our DL-based model demonstrated superior performance in accurately segmenting brain MS lesions compared to alternative methods, indicating its potential for clinical application with improved accuracy, robustness, and efficiency. • Automated lesion load quantification in MS patients is valuable; however, more accurate methods are still necessary. • A novel deep learning model outperformed alternative MS lesion segmentation methods on multisite datasets. • Deep learning models are particularly suitable for MS lesion segmentation in clinical scenarios.

The accurate segmentation of multiple sclerosis (MS) lesions in magnetic resonance imaging (MRI) is essential for diagnosis, disease monitoring, and therapeutic assessment. Despite the significant advances in deep learning-based segmentation, the current boundary-aware approaches are limited by their reliance on spatial distance transforms, which fail to fully exploit the rich texture and intensity information inherent in MRI data. This limitation is particularly problematic in regions where MS lesions and normal-appearing white matter exhibit overlapping intensity distributions, resulting in ambiguous boundaries and reduced segmentation accuracy. To address these challenges, we propose a novel Mahalanobis distance map (MDM) and a corresponding Mahalanobis distance loss, which generalize traditional distance transforms by incorporating spatial coordinates, the FLAIR intensity, and radiomic texture features into a unified feature space. Our method leverages the covariance structure of these features to better distinguish ambiguous regions near lesion boundaries, mimicking the texture-aware reasoning of expert radiologists. Experimental evaluation on the ISBI-MS and MSSEG datasets demonstrates that our approach achieves superior performance in both boundary quality metrics (HD95, ASSD) and overall segmentation accuracy (Dice score, precision) compared to state-of-the-art methods. These results highlight the potential of texture-integrated distance metrics to overcome MS lesion segmentation difficulties, providing more reliable and reproducible assessments for MS management and research.

Magnetic Resonance Imaging (MRI) plays a significant role in the current characterization and diagnosis of multiple sclerosis (MS) in radiological imaging. However, early detection of MS lesions from MRI still remains a challenging problem. In the present work, an information theoretic approach to cluster the voxels in MS lesions for automatic segmentation of lesions of various sizes in multi-contrast (T1, T2, PD-weighted) MR images, is applied. For accurate detection of MS lesions of various sizes, the skull-stripped brain data are rescaled and histogram manipulated prior to mapping the multi-contrast data to pseudo-color images. For automated segmentation of multiple sclerosis (MS) lesions in multi-contrast MRI, the improved jump method (IJM) clustering method has been enhanced via edge suppression for improved segmentation of white matter (WM), gray matter (GM), cerebrospinal fluid (CSF) and MS lesions if present. From this preliminary clustering, a pseudo-color to grayscale conversion is designed to equalize the intensities of the normal brain tissues, leaving the MS lesions as outliers. Binary discrete and 8-bit fuzzy labels are then assigned to segment the MS lesions throughout the full brain. For validation of the proposed method, three brains, with mild, moderate and severe hyperintense MS lesions labeled as ground truth, were selected. The MS lesions of mild, moderate and severe categories were detected with a sensitivity of 80%, and 96%, and 94%, and with the corresponding Dice similarity coefficient (DSC) of 0.5175, 0.8739, and 0.8266 respectively. The MS lesions can also be clearly visualized in a transparent pseudo-color computer rendered 3D brain.

An energy minimization method for MS lesion segmentation from T1-w and FLAIR images

Human investigators instinctively segment medical images into their anatomical components, drawing upon prior knowledge of anatomy to overcome image artifacts, noise, and lack of tissue contrast. The authors describe: 1) the development and use of a brain tissue probability model for the segmentation of multiple sclerosis (MS) lesions in magnetic resonance (MR) brain images, and 2) an empirical comparison of the performance of statistical and decision tree classifiers, applied to MS lesion segmentation. Based on MR image data obtained from healthy volunteers, the model provides prior probabilities of brain tissue distribution per unit voxel in a standardized 3-D "brain space". In comparison to purely data-driven segmentation, the use of the model to guide the segmentation of MS lesions reduced the volume of false positive lesions by 50-80%

This paper explores the use of a soft ground-truth mask (“soft mask”) to train a Fully Convolutional Neural Network (FCNN) for segmentation of Multiple Sclerosis (MS) lesions. Detection and segmentation of MS lesions is a complex task largely due to the extreme unbalanced data, with very small number of lesion pixels that can be used for training. Utilizing the anatomical knowledge that the lesion surrounding pixels may also include some lesion level information, we suggest to increase the data set of the lesion class with neighboring pixel data -with a reduced confidence weight. A soft mask is constructed by morphological dilation of the binary segmentation mask provided by a given expert, where expert-marked voxels receive label 1 and voxels of the dilated region are assigned a soft label. In the methodology proposed, the FCNN is trained using the soft mask. On the ISBI 2015 challenge dataset, this is shown to provide a better precision-recall tradeoff and to achieve a higher average Dice similarity coefficient. We also show that by using this soft mask scheme we can improve the network segmentation performance when compared to a second independent expert.

In this paper, we present a fully convolutional densely connected network (Tiramisu) for multiple sclerosis (MS) lesion segmentation. Different from existing methods, we use stacked slices from all three anatomical planes to achieve a 2.5D method. Individual slices from a given orientation provide global context along the plane and the stack of adjacent slices adds local context. By taking stacked data from three orientations, the network has access to more samples for training and can make more accurate segmentation by combining information of different forms. The conducted experiments demonstrated the competitive performance of our method. For an ablation study, we simulated lesions on healthy controls to generate images with ground truth lesion masks. This experiment confirmed that the use of 2.5D patches, stacked data and the Tiramisu model improve the MS lesion segmentation performance. In addition, we evaluated our approach on the Longitudinal MS Lesion Segmentation Challenge. The overall score of 93.1 places the L 2-loss variant of our method in the first position on the leaderboard, while the focal-loss variant has obtained the best Dice coefficient and lesion-wise true positive rate with 69.3% and 60.2%, respectively.

Multiple Sclerosis (MS) lesion segmentation from MR images is important for neuroimaging analysis. MS is diffuse, multifocal, and tend to involve peripheral brain structures such as the white matter, corpus callosum, and brainstem. Recently, U-Net has made great achievements in medical image segmentation area. However, the insufficiently use of context information and feature representation, makes it fail to achieve segmentation of MS lesions accurately. To solve the problem, 3D attention context U-Net (ACU-Net) is proposed for MS lesion segmentation in this paper. The proposed ACU-Net includes 3D spatial attention block, which is used to enrich spatial details and feature representation of lesion in the decoding stage. Furthermore, in the encoding and decoding stage of the network, 3D context guided module is designed for guiding local information and surrounding information. The proposed ACU-Net was evaluated on the ISBI 2015 longitudinal MS lesion segmentation challenge dataset, and it achieved superior performance compared to latest approaches.

In this paper, a new technique is proposed for automatic segmentation of multiple sclerosis (MS) lesions from brain magnetic resonance imaging (MRI) data. The technique uses a trained support vector machine (SVM) to discriminate between the blocks in regions of MS lesions and the blocks in non-MS lesion regions mainly based on the textural features with aid of the other features. The classification is done on each of the axial, sagittal and coronal sectional brain view independently and the resultant segmentations are aggregated to provide more accurate output segmentation. The main contribution of the proposed technique described in this paper is the use of textural features to detect MS lesions in a fully automated approach that does not rely on manually delineating the MS lesions. In addition, the technique introduces the concept of the multi-sectional view segmentation to produce verified segmentation. The proposed textural-based SVM technique was evaluated using three simulated datasets and more than fifty real MRI datasets. The results were compared with state of the art methods. The obtained results indicate that the proposed method would be viable for use in clinical practice for the detection of MS lesions in MRI.

In this paper, a new technique is proposed for automatic segmentation of multiple sclerosis (MS) lesions from brain magnetic resonance imaging (MRI) data. The technique uses a trained support vector machine (SVM) to discriminate between the blocks in regions of MS lesions and the blocks in non-MS lesion regions mainly based on the textural features with aid of the other features. The classification is done on each of the axial, sagittal and coronal sectional brain view independently and the resultant segmentations are aggregated to provide more accurate output segmentation. The main contribution of the proposed technique described in this paper is the use of textural features to detect MS lesions in a fully automated approach that does not rely on manually delineating the MS lesions. In addition, the technique introduces the concept of the multi-sectional view segmentation to produce verified segmentation. The proposed textural-based SVM technique was evaluated using three simulated datasets and more than fifty real MRI datasets. The results were compared with state of the art methods. The obtained results indicate that the proposed method would be viable for use in clinical practice for the detection of MS lesions in MRI.

The objective of the research work is to accurately segment multiple sclerosis (MS) lesions in brain Magnetic Resonance Imaging (MRI) of varying sizes and also to classify its types. Designing effective automatic segmentation and classification tool aid the doctors in better understanding MS lesion progressions. In meeting research challenges, this paper presents Noise Invariant Convolution Neural Network (NICNN). The NICNN model is efficient in the detection and segmentation of MS lesions of varying sizes in comparison with standard CNN-based segmentation methods. Further, this paper introduced a new cross-validation scheme to address the class imbalance issue by selecting effective features for classifying the type of MS lesion. The experiment outcome shows the proposed method provides improved Dice Similarity Coefficient (DSC), Positive Predicted Value (PPV), and True Positive Rate (TPR) value compared to the state-of-art CNN-based MS lesion segmentation method. Further, achieves better accuracy in classifying MS lesion types compared to standard MS lesion type classification models.

We propose a novel method for the segmentation of Multiple Sclerosis (MS) lesions in MRI. The method is based on a three-step approach: first a conventional k-NN classifier is applied to pre-classify gray matter (GM), white matter (WM), cerebro-spinal fluid (CSF) and MS lesions from a set of prototypes selected by an expert. Second, the classification of problematic patterns is resolved computing a fast distance transformation (DT) algorithm from the set of prototypes in the Euclidean space defined by the MRI dataset. Finally, a connected component filtering algorithm is used to remove lesion voxels not connected to the real lesions. This method uses distance information together with intensity information to improve the accuracy of lesion segmentation and, thus, it is specially useful when MS lesions have similar intensity values than other tissues. It is also well suited for interactive segmentations due to its efficiency. Results are shown on real MRI data as wall as on a standard database of synthetic images.KeywordsGray MatterVoronoi DiagramLookup TableDistance TransformationPattern Recognition LetterThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Magnetic Resonance Imaging (MRI) is a vital tool in the diagnosis and characterization of multiple sclerosis (MS). MS lesions can be imaged with relatively high contrast using either Fluid Attenuated Inversion Recovery (FLAIR) or Double Inversion Recovery (DIR). Automated segmentation and accurate tracking of MS lesions from MRI remains a challenging problem. Here, an information theoretic approach to cluster the voxels in pseudo-colorized multispectral MR data (FLAIR, DIR, T2-weighted) is utilized to automatically segment MS lesions of various sizes and noise levels. The Improved Jump Method (IJM) clustering, assisted by edge suppression, is applied to the segmentation of white matter (WM), gray matter (GM), cerebrospinal fluid (CSF) and MS lesions, if present, into a subset of slices determined to be the best MS lesion candidates via Otsu’s method. From this preliminary clustering, the modal data values for the tissues can be determined. A Euclidean distance is then used to estimate the fuzzy memberships of each brain voxel for all tissue types and their 50/50 partial volumes. From these estimates, binary discrete and fuzzy MS lesion masks are constructed. Validation is provided by using three synthetic MS lesions brains (mild, moderate and severe) with labeled ground truths. The MS lesions of mild, moderate and severe designations were detected with a sensitivity of 83.2%, and 88.5%, and 94.5%, and with the corresponding Dice similarity coefficient (DSC) of 0.7098, 0.8739, and 0.8266, respectively. The effect of MRI noise is also examined by simulated noise and the application of a bilateral filter in preprocessing.