Longitudinal multiple sclerosis lesion segmentation: Resource and challenge

A Clinically-Compatible Workflow for Computer-Aided Assessment of Brain Disease Activity in Multiple Sclerosis Patients

Over the last 10 years, the number of approved disease modifying drugs acting on the focal inflammatory process in Multiple Sclerosis (MS) has increased from 3 to 10. This wide choice offers the opportunity of a personalized medicine with the objective of no clinical and radiological activity for each patient. This new paradigm requires the optimization of the detection of new FLAIR lesions on longitudinal MRI. In this paper, we describe a complete workflow—that we developed, implemented, deployed, and evaluated—to facilitate the monitoring of new FLAIR lesions on longitudinal MRI of MS patients. This workflow has been designed to be usable by both hospital and private neurologists and radiologists in France. It consists of three main components: (i) a software component that allows for automated and secured anonymization and transfer of MRI data from the clinical Picture Archive and Communication System (PACS) to a processing server (and vice-versa); (ii) a fully automated segmentation core that enables detection of focal longitudinal changes in patients from T1-weighted, T2-weighted and FLAIR brain MRI scans, and (iii) a dedicated web viewer that provides an intuitive visualization of new lesions to radiologists and neurologists. We first present these different components. Then, we evaluate the workflow on 54 pairs of longitudinal MRI scans that were analyzed by 3 experts (1 neuroradiologist, 1 radiologist, and 1 neurologist) with and without the proposed workflow. We show that our workflow provided a valuable aid to clinicians in detecting new MS lesions both in terms of accuracy (mean number of detected lesions per patient and per expert 1.8 without the workflow vs. 2.3 with the workflow, p = 5.10⁻⁴) and of time dedicated by the experts (mean time difference 2′45″, p = 10⁻⁴). This increase in the number of detected lesions has implications in the classification of MS patients as stable or active, even for the most experienced neuroradiologist (mean sensitivity was 0.74 without the workflow and 0.90 with the workflow, p-value for no difference = 0.003). It therefore has potential consequences on the therapeutic management of MS patients.

Opportunities for Understanding MS Mechanisms and Progression With MRI Using Large-Scale Data Sharing and Artificial Intelligence

Patients with multiple sclerosis (MS) have heterogeneous clinical presentations, symptoms, and progression over time, making MS difficult to assess and comprehend in vivo. The combination of large-scale data sharing and artificial intelligence creates new opportunities for monitoring and understanding MS using MRI. First, development of validated MS-specific image analysis methods can be boosted by verified reference, test, and benchmark imaging data. Using detailed expert annotations, artificial intelligence algorithms can be trained on such MS-specific data. Second, understanding disease processes could be greatly advanced through shared data of large MS cohorts with clinical, demographic, and treatment information. Relevant patterns in such data that may be imperceptible to a human observer could be detected through artificial intelligence techniques. This applies from image analysis (lesions, atrophy, or functional network changes) to large multidomain datasets (imaging, cognition, clinical disability, genetics). After reviewing data sharing and artificial intelligence, we highlight 3 areas that offer strong opportunities for making advances in the next few years: crowdsourcing, personal data protection, and organized analysis challenges. Difficulties as well as specific recommendations to overcome them are discussed, in order to best leverage data sharing and artificial intelligence to improve image analysis, imaging, and the understanding of MS.

ALL-Net: Anatomical information lesion-wise loss function integrated into neural network for multiple sclerosis lesion segmentation

Accurate detection and segmentation of multiple sclerosis (MS) brain lesions on magnetic resonance images are important for disease diagnosis and treatment. This is a challenging task as lesions vary greatly in size, shape, location, and image contrast. The objective of our study was to develop an algorithm based on deep convolutional neural network integrated with anatomic information and lesion-wise loss function (ALL-Net) for fast and accurate automated segmentation of MS lesions. Distance transformation mapping was used to construct a convolutional module that encoded lesion-specific anatomical information. To overcome the lesion size imbalance during network training and improve the detection of small lesions, a lesion-wise loss function was developed in which individual lesions were modeled as spheres of equal size. On the ISBI-2015 longitudinal MS lesion segmentation challenge dataset (19 subjects in total), ALL-Net achieved an overall score of 93.32 and was amongst the top performing methods. On the larger Cornell MS dataset (176 subjects in total), ALL-Net significantly improved both voxel-wise metrics (Dice improvement of 3.9% to 35.3% with p-values ranging from p < 0.01 to p < 0.0001, and AUC of voxel-wise precision-recall curve improvement of 2.1% to 29.8%) and lesion-wise metrics (lesion-wise F1 score improvement of 12.6% to 29.8% with all p-values p < 0.0001, and AUC of lesion-wise ROC curve improvement of 1.4% to 20.0%) compared to leading publicly available MS lesion segmentation tools.

Assessment of Artificial Intelligence Automatic Multiple Sclerosis Lesion Delineation Tool for Clinical Use

PURPOSE

To implement and validate an existing algorithm for automatic delineation of white matter lesions on magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) on a local single-center dataset.

METHODS

We implemented a white matter hyperintensity segmentation model, based on a 2D convolutional neural network, using the conventional T2-weighted fluid attenuated inversion recovery (FLAIR) MRI sequence as input. The model was adapted for delineation of MS lesions by further training on a local dataset of 93 MS patients with a total of 3040 lesions. A quantitative evaluation was performed on ten test patients, in which model-generated masks were compared to manually delineated masks from two expert delineators. A subsequent qualitative evaluation of the implemented model was performed by two expert delineators, in which generated delineation masks on a clinical dataset of 53 patients were rated acceptable (< 10% errors) or unacceptable (> 10% errors) based on the total number of true lesions.

RESULTS

The quantitative evaluation resulted in an average accuracy score (F1) of 0.71, recall of 0.77 and dice similarity coefficient of 0.62. Our implemented model obtained the highest scores in all three metrics, when compared to three out of the box lesion segmentation models. In the clinical evaluation an average of 94% of our 53 model-generated masks were rated acceptable.

CONCLUSION

After adaptation to our local dataset, the implemented segmentation model was able to delineate MS lesions with a high clinical value as rated by delineation experts while outperforming popular out of the box applications. This serves as a promising step towards implementation of automatic lesion delineation in our MS clinic.

Emerging deep learning techniques using magnetic resonance imaging data applied in multiple sclerosis and clinical isolated syndrome patients (Review)

Computer-aided diagnosis systems aim to assist clinicians in the early identification of abnormal signs in order to optimize the interpretation of medical images and increase diagnostic precision. Multiple sclerosis (MS) and clinically isolated syndrome (CIS) are chronic inflammatory, demyelinating diseases affecting the central nervous system. Recent advances in deep learning (DL) techniques have led to novel computational paradigms in MS and CIS imaging designed for automatic segmentation and detection of areas of interest and automatic classification of anatomic structures, as well as optimization of neuroimaging protocols. To this end, there are several publications presenting artificial intelligence-based predictive models aiming to increase diagnostic accuracy and to facilitate optimal clinical management in patients diagnosed with MS and/or CIS. The current study presents a thorough review covering DL techniques that have been applied in MS and CIS during recent years, shedding light on their current advances and limitations.

Deep Attention and Graphical Neural Network for Multiple Sclerosis Lesion Segmentation from MR Imaging Sequences

The segmentation of multiple sclerosis (MS) lesions from MR imaging sequences remains a challenging task, due to the characteristics of variant shapes, scattered distributions and unknown numbers of lesions. However, the current automated MS segmentation methods with deep learning models face the challenges of (1) capturing the multiple scattered lesions in multiple regions and (2) delineating the global contour of variant lesions. To address these challenges, in this paper, we propose a novel attention and graph-driven network (DAG-Net), which incorporates (1) the spatial correlations for embracing the lesions in distant regions and (2) the global context for better representing lesions of variant features in a unified architecture. Firstly, the novel local attention coherence mechanism is designed to construct dynamic and expansible graphs for the spatial correlations between pixels and their proximities. Secondly, the proposed spatial-channel attention module enhances features to optimize the global contour delineation, by aggregating relevant features. Moreover, with the dynamic graphs, the learning process of the DAG-Net is interpretable, which in turns support the reliability of segmentation results. Extensive experiments were conducted on a public ISBI2015 dataset and an in-house dataset in comparison to state-of-the-art methods, based on the geometrical and clinical metrics. The experimental results validate the effectiveness of the proposed DAG-Net on segmenting variant and scatted lesions in multiple regions.

Self-Supervised Longitudinal Neighbourhood Embedding

Longitudinal MRIs are often used to capture the gradual deterioration of brain structure and function caused by aging or neurological diseases. Analyzing this data via machine learning generally requires a large number of ground-truth labels, which are often missing or expensive to obtain. Reducing the need for labels, we propose a self-supervised strategy for representation learning named Longitudinal Neighborhood Embedding (LNE). Motivated by concepts in contrastive learning, LNE explicitly models the similarity between trajectory vectors across different subjects. We do so by building a graph in each training iteration defining neighborhoods in the latent space so that the progression direction of a subject follows the direction of its neighbors. This results in a smooth trajectory field that captures the global morphological change of the brain while maintaining the local continuity. We apply LNE to longitudinal T1w MRIs of two neuroimaging studies: a dataset composed of 274 healthy subjects, and Alzheimer's Disease Neuroimaging Initiative (ADNI, N = 632). The visualization of the smooth trajectory vector field and superior performance on downstream tasks demonstrate the strength of the proposed method over existing self-supervised methods in extracting information associated with normal aging and in revealing the impact of neurodegenerative disorders. The code is available at https://github.com/ouyangjiahong/longitudinal-neighbourhood-embedding.

Multiple Sclerosis Lesion Segmentation in Brain MRI Using Inception Modules Embedded in a Convolutional Neural Network

Multiple sclerosis (MS) is a chronic and autoimmune disease that forms lesions in the central nervous system. Quantitative analysis of these lesions has proved to be very useful in clinical trials for therapies and assessing disease prognosis. However, the efficacy of these quantitative analyses greatly depends on how accurately the MS lesions have been identified and segmented in brain MRI. This is usually carried out by radiologists who label 3D MR images slice by slice using commonly available segmentation tools. However, such manual practices are time consuming and error prone. To circumvent this problem, several automatic segmentation techniques have been investigated in recent years. In this paper, we propose a new framework for automatic brain lesion segmentation that employs a novel convolutional neural network (CNN) architecture. In order to segment lesions of different sizes, we have to pick a specific filter or size 3 × 3 or 5 × 5. Sometimes, it is hard to decide which filter will work better to get the best results. Google Net has solved this problem by introducing an inception module. An inception module uses 3 × 3, 5 × 5, 1 × 1 and max pooling filters in parallel fashion. Results show that incorporating inception modules in a CNN has improved the performance of the network in the segmentation of MS lesions. We compared the results of the proposed CNN architecture for two loss functions: binary cross entropy (BCE) and structural similarity index measure (SSIM) using the publicly available ISBI-2015 challenge dataset. A score of 93.81 which is higher than the human rater with BCE loss function is achieved.

Applications of deep learning techniques for automated multiple sclerosis detection using magnetic resonance imaging: A review

Multiple Sclerosis (MS) is a type of brain disease which causes visual, sensory, and motor problems for people with a detrimental effect on the functioning of the nervous system. In order to diagnose MS, multiple screening methods have been proposed so far; among them, magnetic resonance imaging (MRI) has received considerable attention among physicians. MRI modalities provide physicians with fundamental information about the structure and function of the brain, which is crucial for the rapid diagnosis of MS lesions. Diagnosing MS using MRI is time-consuming, tedious, and prone to manual errors. Research on the implementation of computer aided diagnosis system (CADS) based on artificial intelligence (AI) to diagnose MS involves conventional machine learning and deep learning (DL) methods. In conventional machine learning, feature extraction, feature selection, and classification steps are carried out by using trial and error; on the contrary, these steps in DL are based on deep layers whose values are automatically learn. In this paper, a complete review of automated MS diagnosis methods performed using DL techniques with MRI neuroimaging modalities is provided. Initially, the steps involved in various CADS proposed using MRI modalities and DL techniques for MS diagnosis are investigated. The important preprocessing techniques employed in various works are analyzed. Most of the published papers on MS diagnosis using MRI modalities and DL are presented. The most significant challenges facing and future direction of automated diagnosis of MS using MRI modalities and DL techniques are also provided.

An atlas of classifiers-a machine learning paradigm for brain MRI segmentation

We present the Atlas of Classifiers (AoC)-a conceptually novel framework for brain MRI segmentation. The AoC is a spatial map of voxel-wise multinomial logistic regression (LR) functions learned from the labeled data. Upon convergence, the resulting fixed LR weights, a few for each voxel, represent the training dataset. It can, therefore, be considered as a light-weight learning machine, which despite its low capacity does not underfit the problem. The AoC construction is independent of the actual intensities of the test images, providing the flexibility to train it on the available labeled data and use it for the segmentation of images from different datasets and modalities. In this sense, it does not overfit the training data, as well. The proposed method has been applied to numerous publicly available datasets for the segmentation of brain MRI tissues and is shown to be robust to noise and outreach commonly used methods. Promising results were also obtained for multi-modal, cross-modality MRI segmentation. Finally, we show how AoC trained on brain MRIs of healthy subjects can be exploited for lesion segmentation of multiple sclerosis patients.

An automatic multi-tissue human fetal brain segmentation benchmark using the Fetal Tissue Annotation Dataset

It is critical to quantitatively analyse the developing human fetal brain in order to fully understand neurodevelopment in both normal fetuses and those with congenital disorders. To facilitate this analysis, automatic multi-tissue fetal brain segmentation algorithms are needed, which in turn requires open datasets of segmented fetal brains. Here we introduce a publicly available dataset of 50 manually segmented pathological and non-pathological fetal magnetic resonance brain volume reconstructions across a range of gestational ages (20 to 33 weeks) into 7 different tissue categories (external cerebrospinal fluid, grey matter, white matter, ventricles, cerebellum, deep grey matter, brainstem/spinal cord). In addition, we quantitatively evaluate the accuracy of several automatic multi-tissue segmentation algorithms of the developing human fetal brain. Four research groups participated, submitting a total of 10 algorithms, demonstrating the benefits the dataset for the development of automatic algorithms.

Automatic brain lesion segmentation on standard magnetic resonance images: a scoping review

OBJECTIVES

Medical image analysis practices face challenges that can potentially be addressed with algorithm-based segmentation tools. In this study, we map the field of automatic MR brain lesion segmentation to understand the clinical applicability of prevalent methods and study designs, as well as challenges and limitations in the field.

DESIGN

Scoping review.

SETTING

Three databases (PubMed, IEEE Xplore and Scopus) were searched with tailored queries. Studies were included based on predefined criteria. Emerging themes during consecutive title, abstract, methods and whole-text screening were identified. The full-text analysis focused on materials, preprocessing, performance evaluation and comparison.

RESULTS

Out of 2990 unique articles identified through the search, 441 articles met the eligibility criteria, with an estimated growth rate of 10% per year. We present a general overview and trends in the field with regard to publication sources, segmentation principles used and types of lesions. Algorithms are predominantly evaluated by measuring the agreement of segmentation results with a trusted reference. Few articles describe measures of clinical validity.

CONCLUSIONS

The observed reporting practices leave room for improvement with a view to studying replication, method comparison and clinical applicability. To promote this improvement, we propose a list of recommendations for future studies in the field.

Neuropsychiatric disease classification using functional connectomics - results of the connectomics in neuroimaging transfer learning challenge

Large, open-source datasets, such as the Human Connectome Project and the Autism Brain Imaging Data Exchange, have spurred the development of new and increasingly powerful machine learning approaches for brain connectomics. However, one key question remains: are we capturing biologically relevant and generalizable information about the brain, or are we simply overfitting to the data? To answer this, we organized a scientific challenge, the Connectomics in NeuroImaging Transfer Learning Challenge (CNI-TLC), held in conjunction with MICCAI 2019. CNI-TLC included two classification tasks: (1) diagnosis of Attention-Deficit/Hyperactivity Disorder (ADHD) within a pre-adolescent cohort; and (2) transference of the ADHD model to a related cohort of Autism Spectrum Disorder (ASD) patients with an ADHD comorbidity. In total, 240 resting-state fMRI (rsfMRI) time series averaged according to three standard parcellation atlases, along with clinical diagnosis, were released for training and validation (120 neurotypical controls and 120 ADHD). We also provided Challenge participants with demographic information of age, sex, IQ, and handedness. The second set of 100 subjects (50 neurotypical controls, 25 ADHD, and 25 ASD with ADHD comorbidity) was used for testing. Classification methodologies were submitted in a standardized format as containerized Docker images through ChRIS, an open-source image analysis platform. Utilizing an inclusive approach, we ranked the methods based on 16 metrics: accuracy, area under the curve, F1-score, false discovery rate, false negative rate, false omission rate, false positive rate, geometric mean, informedness, markedness, Matthew's correlation coefficient, negative predictive value, optimized precision, precision, sensitivity, and specificity. The final rank was calculated using the rank product for each participant across all measures. Furthermore, we assessed the calibration curves of each methodology. Five participants submitted their method for evaluation, with one outperforming all other methods in both ADHD and ASD classification. However, further improvements are still needed to reach the clinical translation of functional connectomics. We have kept the CNI-TLC open as a publicly available resource for developing and validating new classification methodologies in the field of connectomics.

Autoencoders for unsupervised anomaly segmentation in brain MR images: A comparative study

Deep unsupervised representation learning has recently led to new approaches in the field of Unsupervised Anomaly Detection (UAD) in brain MRI. The main principle behind these works is to learn a model of normal anatomy by learning to compress and recover healthy data. This allows to spot abnormal structures from erroneous recoveries of compressed, potentially anomalous samples. The concept is of great interest to the medical image analysis community as it i) relieves from the need of vast amounts of manually segmented training data-a necessity for and pitfall of current supervised Deep Learning-and ii) theoretically allows to detect arbitrary, even rare pathologies which supervised approaches might fail to find. To date, the experimental design of most works hinders a valid comparison, because i) they are evaluated against different datasets and different pathologies, ii) use different image resolutions and iii) different model architectures with varying complexity. The intent of this work is to establish comparability among recent methods by utilizing a single architecture, a single resolution and the same dataset(s). Besides providing a ranking of the methods, we also try to answer questions like i) how many healthy training subjects are needed to model normality and ii) if the reviewed approaches are also sensitive to domain shift. Further, we identify open challenges and provide suggestions for future community efforts and research directions.

Ensembling Low Precision Models for Binary Biomedical Image Segmentation

Segmentation of anatomical regions of interest such as vessels or small lesions in medical images is still a difficult problem that is often tackled with manual input by an expert. One of the major challenges for this task is that the appearance of foreground (positive) regions can be similar to background (negative) regions. As a result, many automatic segmentation algorithms tend to exhibit asymmetric errors, typically producing more false positives than false negatives. In this paper, we aim to leverage this asymmetry and train a diverse ensemble of models with very high recall, while sacrificing their precision. Our core idea is straightforward: A diverse ensemble of low precision and high recall models are likely to make different false positive errors (classifying background as foreground in different parts of the image), but the true positives will tend to be consistent. Thus, in aggregate the false positive errors will cancel out, yielding high performance for the ensemble. Our strategy is general and can be applied with any segmentation model. In three different applications (carotid artery segmentation in a neck CT angiography, myocardium segmentation in a cardiovascular MRI and multiple sclerosis lesion segmentation in a brain MRI), we show how the proposed approach can significantly boost the performance of a baseline segmentation method.

Investigating efficient CNN architecture for multiple sclerosis lesion segmentation

Purpose: The automatic segmentation of multiple sclerosis lesions in magnetic resonance imaging has the potential to reduce radiologists' efforts on a daily time-consuming task and to bring more reproducibility. Almost all new segmentation techniques make use of convolutional neural networks with their own different architecture. Architectural choices are rarely explained. We aimed at presenting the relevance of a U-net-like architecture for our specific task and at building an efficient and simple model. Approach: An experimental study was performed by observing the impact of applying different mutations and deletions to a simple U-net-like architecture. Results: The power of the U-net architecture is explained by the joint benefits of using an encoder-decoder architecture and by linking them with long skip connections. Augmenting the number of convolutional layers and decreasing the number of feature maps allowed us to build an exceptionally light and competitive architecture, the minimally parameterized U-net (MPU-net), with only ∼ 30,000 parameters. Conclusion: The empirical study of the U-net has led to a better understanding of its architecture. It has guided the building of the MPU-net, a model far less parameterized than others (at least by a factor of seven). This neural network achieves a human-level segmentation of multiple sclerosis lesions on fluid-attenuated inversion recovery images only. It shows that this segmentation task does not necessitate overly complicated models to be achieved. This gives the opportunity to build more explainable models that can help such methods to be adopted in a clinical environment.

FLAIR-only joint volumetric analysis of brain lesions and atrophy in clinically isolated syndrome (CIS) suggestive of multiple sclerosis

Background

MRI assessment in multiple sclerosis (MS) focuses on the presence of typical white matter (WM) lesions. Neurodegeneration characterised by brain atrophy is recognised in the research field as an important prognostic factor. It is not routinely reported clinically, in part due to difficulty in achieving reproducible measurements. Automated MRI quantification of WM lesions and brain volume could provide important clinical monitoring data. In general, lesion quantification relies on both T1 and FLAIR input images, while tissue volumetry relies on T1. However, T1-weighted scans are not routinely included in the clinical MS protocol, limiting the utility of automated quantification.

Objectives

We address an aspect of this important translational challenge by assessing the performance of FLAIR-only lesion and brain segmentation, against a conventional approach requiring multi-contrast acquisition. We explore whether FLAIR-only grey matter (GM) segmentation yields more variability in performance compared with two-channel segmentation; whether this is related to field strength; and whether the results meet a level of clinical acceptability demonstrated by the ability to reproduce established biological associations.

Methods

We used a multicentre dataset of subjects with a CIS suggestive of MS scanned at 1.5T and 3T in the same week. WM lesions were manually segmented by two raters, ‘manual 1′ guided by consensus reading of CIS-specific lesions and ‘manual 2′ by any WM hyperintensity. An existing brain segmentation method was adapted for FLAIR-only input. Automated segmentation of WM hyperintensity and brain volumes were performed with conventional (T1/T1 + FLAIR) and FLAIR-only methods.

Results

WM lesion volumes were comparable at 1.5T between ‘manual 2′ and FLAIR-only methods and at 3T between ‘manual 2′, T1 + FLAIR and FLAIR-only methods. For cortical GM volume, linear regression measures between conventional and FLAIR-only segmentation were high (1.5T: α = 1.029, R² = 0.997, standard error (SE) = 0.007; 3T: α = 1.019, R² = 0.998, SE = 0.006). Age-associated change in cortical GM volume was a significant covariate in both T1 (p = 0.001) and FLAIR-only (p = 0.005) methods, confirming the expected relationship between age and GM volume for FLAIR-only segmentations.

Conclusions

FLAIR-only automated segmentation of WM lesions and brain volumes were consistent with results obtained through conventional methods and had the ability to demonstrate biological effects in our study population. Imaging protocol harmonisation and validation with other MS phenotypes could facilitate the integration of automated WM lesion volume and brain atrophy analysis as clinical tools in radiological MS reporting.

nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation

Biomedical imaging is a driver of scientific discovery and a core component of medical care and is being stimulated by the field of deep learning. While semantic segmentation algorithms enable image analysis and quantification in many applications, the design of respective specialized solutions is non-trivial and highly dependent on dataset properties and hardware conditions. We developed nnU-Net, a deep learning-based segmentation method that automatically configures itself, including preprocessing, network architecture, training and post-processing for any new task. The key design choices in this process are modeled as a set of fixed parameters, interdependent rules and empirical decisions. Without manual intervention, nnU-Net surpasses most existing approaches, including highly specialized solutions on 23 public datasets used in international biomedical segmentation competitions. We make nnU-Net publicly available as an out-of-the-box tool, rendering state-of-the-art segmentation accessible to a broad audience by requiring neither expert knowledge nor computing resources beyond standard network training.

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

INTRODUCTION

During the last decade, a multitude of novel quantitative and semiquantitative MRI techniques have provided new information about the pathophysiology of neurological diseases. Yet, selection of the most relevant contrasts for a given pathology remains challenging. In this work, we developed and validated a method, Gated-Attention MEchanism Ranking of multi-contrast MRI in brain pathology (GAMER MRI), to rank the relative importance of MR measures in the classification of well understood ischemic stroke lesions. Subsequently, we applied this method to the classification of multiple sclerosis (MS) lesions, where the relative importance of MR measures is less understood.

METHODS

GAMER MRI was developed based on the gated attention mechanism, which computes attention weights (AWs) as proxies of importance of hidden features in the classification. In the first two experiments, we used Trace-weighted (Trace), apparent diffusion coefficient (ADC), Fluid-Attenuated Inversion Recovery (FLAIR), and T1-weighted (T1w) images acquired in 904 acute/subacute ischemic stroke patients and in 6,230 healthy controls and patients with other brain pathologies to assess if GAMER MRI could produce clinically meaningful importance orders in two different classification scenarios. In the first experiment, GAMER MRI with a pretrained convolutional neural network (CNN) was used in conjunction with Trace, ADC, and FLAIR to distinguish patients with ischemic stroke from those with other pathologies and healthy controls. In the second experiment, GAMER MRI with a patch-based CNN used Trace, ADC and T1w to differentiate acute ischemic stroke lesions from healthy tissue. The last experiment explored the performance of patch-based CNN with GAMER MRI in ranking the importance of quantitative MRI measures to distinguish two groups of lesions with different pathological characteristics and unknown quantitative MR features. Specifically, GAMER MRI was applied to assess the relative importance of the myelin water fraction (MWF), quantitative susceptibility mapping (QSM), T1 relaxometry map (qT1), and neurite density index (NDI) in distinguishing 750 juxtacortical lesions from 242 periventricular lesions in 47 MS patients. Pair-wise permutation t-tests were used to evaluate the differences between the AWs obtained for each quantitative measure.

RESULTS

In the first experiment, we achieved a mean test AUC of 0.881 and the obtained AWs of FLAIR and the sum of AWs of Trace and ADC were 0.11 and 0.89, respectively, as expected based on previous knowledge. In the second experiment, we achieved a mean test F1 score of 0.895 and a mean AW of Trace = 0.49, of ADC = 0.28, and of T1w = 0.23, thereby confirming the findings of the first experiment. In the third experiment, MS lesion classification achieved test balanced accuracy = 0.777, sensitivity = 0.739, and specificity = 0.814. The mean AWs of T1map, MWF, NDI, and QSM were 0.29, 0.26, 0.24, and 0.22 (p < 0.001), respectively.

CONCLUSIONS

This work demonstrates that the proposed GAMER MRI might be a useful method to assess the relative importance of MRI measures in neurological diseases with focal pathology. Moreover, the obtained AWs may in fact help to choose the best combination of MR contrasts for a specific classification problem.

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

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.

Cross-organ, cross-modality transfer learning: feasibility study for segmentation and classification

We conducted two analyses by comparing the transferability of a traditionally transfer-learned CNN (TL) to that of a CNN fine-tuned with an unrelated set of medical images (mammograms in this study) first and then fine-tuned a second time using TL, which we call the cross-organ, cross-modality transfer learned (XTL) network, on 1) multiple sclerosis (MS) segmentation of brain magnetic resonance (MR) images and 2) tumor malignancy classification of multi-parametric prostate MR images. We used 2133 screening mammograms and two public challenge datasets (longitudinal MS lesion segmentation and ProstateX) as intermediate and target datasets for XTL, respectively. We used two CNN architectures as basis networks for each analysis and fine-tuned it to match the target image types (volumetric) and tasks (segmentation and classification). We evaluated the XTL networks against the traditional TL networks using Dice coefficient and AUC as figure of merits for each analysis, respectively. For the segmentation test, XTL networks outperformed TL networks in terms of Dice coefficient (Dice coefficients of 0.72 vs [0.70 - 0.71] with p-value < 0.0001 in differences). For the classification test, XTL networks (AUCs = 0.77 - 0.80) outperformed TL networks (AUC = 0.73 - 0.75). The difference in the AUCs (AUC_diff = 0.045 - 0.047) was statistically significant (p-value < 0.03). We showed XTL using mammograms improves the network performance compared to traditional TL, despite the difference in image characteristics (x-ray vs. MRI and 2D vs. 3D) and imaging tasks (classification vs. segmentation for one of the tasks).

Multiple Sclerosis lesions detection by a hybrid Watershed-Clustering algorithm

BACKGROUND

Computer Aided Diagnosis (CAD) systems have been developing in the last years with the aim of helping the diagnosis and monitoring of several diseases. We present a novel CAD system based on a hybrid Watershed-Clustering algorithm for the detection of lesions in Multiple Sclerosis.

METHODS

Magnetic Resonance Imaging scans (FLAIR sequences without gadolinium) of 20 patients affected by Multiple Sclerosis with hyperintense lesions were studied. The CAD system consisted of the following automated processing steps: images recording, automated segmentation based on the Watershed algorithm, detection of lesions, extraction of both dynamic and morphological features, and classification of lesions by Cluster Analysis.

RESULTS

The investigation was performed on 316 suspect regions including 255 lesion and 61 non-lesion cases. The Receiver Operating Characteristic analysis revealed a highly significant difference between lesions and non-lesions; the diagnostic accuracy was 87% (95% CI: 0.83-0.90), with an appropriate cut-off of 192.8; the sensitivity was 77% and the specificity was 87%.

CONCLUSIONS

In conclusion, we developed a CAD system by using a modified algorithm for automated image segmentation which may discriminate MS lesions from non-lesions. The proposed method generates a detection out-put that may be support the clinical evaluation.

A contrast-adaptive method for simultaneous whole-brain and lesion segmentation in multiple sclerosis

Here we present a method for the simultaneous segmentation of white matter lesions and normal-appearing neuroanatomical structures from multi-contrast brain MRI scans of multiple sclerosis patients. The method integrates a novel model for white matter lesions into a previously validated generative model for whole-brain segmentation. By using separate models for the shape of anatomical structures and their appearance in MRI, the algorithm can adapt to data acquired with different scanners and imaging protocols without retraining. We validate the method using four disparate datasets, showing robust performance in white matter lesion segmentation while simultaneously segmenting dozens of other brain structures. We further demonstrate that the contrast-adaptive method can also be safely applied to MRI scans of healthy controls, and replicate previously documented atrophy patterns in deep gray matter structures in MS. The algorithm is publicly available as part of the open-source neuroimaging package FreeSurfer.

Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis

Supervised training of deep learning models requires large labeled datasets. There is a growing interest in obtaining such datasets for medical image analysis applications. However, the impact of label noise has not received sufficient attention. Recent studies have shown that label noise can significantly impact the performance of deep learning models in many machine learning and computer vision applications. This is especially concerning for medical applications, where datasets are typically small, labeling requires domain expertise and suffers from high inter- and intra-observer variability, and erroneous predictions may influence decisions that directly impact human health. In this paper, we first review the state-of-the-art in handling label noise in deep learning. Then, we review studies that have dealt with label noise in deep learning for medical image analysis. Our review shows that recent progress on handling label noise in deep learning has gone largely unnoticed by the medical image analysis community. To help achieve a better understanding of the extent of the problem and its potential remedies, we conducted experiments with three medical imaging datasets with different types of label noise, where we investigated several existing strategies and developed new methods to combat the negative effect of label noise. Based on the results of these experiments and our review of the literature, we have made recommendations on methods that can be used to alleviate the effects of different types of label noise on deep models trained for medical image analysis. We hope that this article helps the medical image analysis researchers and developers in choosing and devising new techniques that effectively handle label noise in deep learning.

Comparison and validation of seven white matter hyperintensities segmentation software in elderly patients

•

The comparison used 207 images from both research and clinical datasets.

•

When retrained, NicMSlesion, a convolutional network, was the most accurate.

•

Performance of this deep learning method severely dropped on clinical routine data.

•

On clinical routine data, regression and clustering methods were the top-ranked methods.

•

SLS was the most robust to artifacted images, and BIANCA to scanners variability.

Background

Manual segmentation is currently the gold standard to assess white matter hyperintensities (WMH), but it is time consuming and subject to intra and inter-operator variability.

Purpose

To compare automatic methods to segment white matter hyperintensities (WMH) in the elderly in order to assist radiologist and researchers in selecting the most relevant method for application on clinical or research data.

Material and Methods

We studied a research dataset composed of 147 patients, including 97 patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) 2 database and 50 patients from ADNI 3 and a clinical routine dataset comprising 60 patients referred for cognitive impairment at the Pitié-Salpêtrière hospital (imaged using four different MRI machines). We used manual segmentation as the gold standard reference. Both manual and automatic segmentations were performed using FLAIR MRI. We compared seven freely available methods that produce segmentation mask and are usable by a radiologist without a strong knowledge of computer programming: LGA (Schmidt et al., 2012), LPA (Schmidt, 2017), BIANCA (Griffanti et al., 2016), UBO detector (Jiang et al., 2018), W2MHS (Ithapu et al., 2014), nicMSlesion (with and without retraining) (Valverde et al., 2019, Valverde et al., 2017). The primary outcome for assessing segmentation accuracy was the Dice similarity coefficient (DSC) between the manual and the automatic segmentation software. Secondary outcomes included five other metrics.

Results

A deep learning approach, NicMSlesion, retrained on data from the research dataset ADNI, performed best on this research dataset (DSC: 0.595) and its DSC was significantly higher than that of all others. However, it ranked fifth on the clinical routine dataset and its performance severely dropped on data with artifacts. On the clinical routine dataset, the three top-ranked methods were LPA, SLS and BIANCA. Their performance did not differ significantly but was significantly higher than that of other methods.

Conclusion

This work provides an objective comparison of methods for WMH segmentation. Results can be used by radiologists to select a tool.

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

The presence of cortical lesions in multiple sclerosis patients has emerged as an important biomarker of the disease. They appear in the earliest stages of the illness and have been shown to correlate with the severity of clinical symptoms. However, cortical lesions are hardly visible in conventional magnetic resonance imaging (MRI) at 3T, and thus their automated detection has been so far little explored. In this study, we propose a fully-convolutional deep learning approach, based on the 3D U-Net, for the automated segmentation of cortical and white matter lesions at 3T. For this purpose, we consider a clinically plausible MRI setting consisting of two MRI contrasts only: one conventional T2-weighted sequence (FLAIR), and one specialized T1-weighted sequence (MP2RAGE). We include 90 patients from two different centers with a total of 728 and 3856 gray and white matter lesions, respectively. We show that two reference methods developed for white matter lesion segmentation are inadequate to detect small cortical lesions, whereas our proposed framework is able to achieve a detection rate of 76% for both cortical and white matter lesions with a false positive rate of 29% in comparison to manual segmentation. Further results suggest that our framework generalizes well for both types of lesion in subjects acquired in two hospitals with different scanners.

7T MPFLAIR versus MP2RAGE for Quantifying Lesion Volume in Multiple Sclerosis

BACKGROUND AND PURPOSE

Use of fluid-attenuated inversion recovery (FLAIR) scans to quantify multiple sclerosis (MS) lesion volume on 7 Tesla (7T) magnetic resonance imaging (MRI) has many downsides, including poor image homogeneity. There are little data about the relative benefit of alternative modalities. The purpose of this paper is to investigate if magnetization-prepared 2 rapid acquisition gradient echo (MP2RAGE) is a viable alternative to FLAIR for robust lesion volume measurement and disability correlations.

METHODS

Forty-seven participants with MS underwent annual brain 7T MRIs. Magnetization-prepared FLAIR (MPFLAIR) and MP2RAGE (both at .7 mm³ isotropic resolution) sequences from a total of 80 MRI scans from 47 subjects were reviewed. White matter lesion (WML) masks were manually constructed from MPFLAIR and T1 maps (from MP2RAGE). Lesion volumes (normalized to intracranial volume) were compared to clinical characteristics and disability scales scores by Pearson or Spearman correlation, as appropriate. Relative correlation strength was compared by Fisher r- to z-transformation.

RESULTS

Normalized lesion volume was greater in MPFLAIR masks (median .005 [range, .001-.030]) than from T1 maps (median .003 [range, .000-.015]). However, lesion volumes between MPFLAIR and T1 maps were highly correlated (rho = .87, P < .001). WML masks from both modalities correlated with most disability measures with no significant difference in the strength of correlation.

CONCLUSIONS

7T MPFLAIR and MP2RAGE T1 map-based WML volumes are highly intercorrelated and both correlate with disability. Thus, MP2RAGE may be a viable alternative to FLAIR-based methods for WML measurement on 7T MRI in MS research.

Subsampled brain MRI reconstruction by generative adversarial neural networks

A main challenge in magnetic resonance imaging (MRI) is speeding up scan time. Beyond improving patient experience and reducing operational costs, faster scans are essential for time-sensitive imaging, such as fetal, cardiac, or functional MRI, where temporal resolution is important and target movement is unavoidable, yet must be reduced. Current MRI acquisition methods speed up scan time at the expense of lower spatial resolution and costlier hardware. We introduce a practical, software-only framework, based on deep learning, for accelerating MRI acquisition, while maintaining anatomically meaningful imaging. This is accomplished by MRI subsampling followed by estimating the missing k-space samples via generative adversarial neural networks. A generator-discriminator interplay enables the introduction of an adversarial cost in addition to fidelity and image-quality losses used for optimizing the reconstruction. Promising reconstruction results are obtained from feasible sampling patterns of up to a fivefold acceleration of diverse brain MRIs, from a large publicly available dataset of healthy adult scans as well as multimodal acquisitions of multiple sclerosis patients and dynamic contrast-enhanced MRI (DCE-MRI) sequences of stroke and tumor patients. Clinical usability of the reconstructed MRI scans is assessed by performing either lesion or healthy tissue segmentation and comparing the results to those obtained by using the original, fully sampled images. Reconstruction quality and usability of the DCE-MRI sequences is demonstrated by calculating the pharmacokinetic (PK) parameters. The proposed MRI reconstruction approach is shown to outperform state-of-the-art methods for all datasets tested in terms of the peak signal-to-noise ratio (PSNR), the structural similarity index (SSIM), as well as either the mean squared error (MSE) with respect to the PK parameters, calculated for the fully sampled DCE-MRI sequences, or the segmentation compatibility, measured in terms of Dice scores and Hausdorff distance. The code is available on GitHub.

MRI Segmentation and Classification of Human Brain Using Deep Learning for Diagnosis of Alzheimer's Disease: A Survey

Many neurological diseases and delineating pathological regions have been analyzed, and the anatomical structure of the brain researched with the aid of magnetic resonance imaging (MRI). It is important to identify patients with Alzheimer's disease (AD) early so that preventative measures can be taken. A detailed analysis of the tissue structures from segmented MRI leads to a more accurate classification of specific brain disorders. Several segmentation methods to diagnose AD have been proposed with varying complexity. Segmentation of the brain structure and classification of AD using deep learning approaches has gained attention as it can provide effective results over a large set of data. Hence, deep learning methods are now preferred over state-of-the-art machine learning methods. We aim to provide an outline of current deep learning-based segmentation approaches for the quantitative analysis of brain MRI for the diagnosis of AD. Here, we report how convolutional neural network architectures are used to analyze the anatomical brain structure and diagnose AD, discuss how brain MRI segmentation improves AD classification, describe the state-of-the-art approaches, and summarize their results using publicly available datasets. Finally, we provide insight into current issues and discuss possible future research directions in building a computer-aided diagnostic system for AD.

Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis

The Sørensen-Dice index (SDI) is a widely used measure for evaluating medical image segmentation algorithms. It offers a standardized measure of segmentation accuracy which has proven useful. However, it offers diminishing insight when the number of objects is unknown, such as in white matter lesion segmentation of multiple sclerosis (MS) patients. We present a refinement for finer grained parsing of SDI results in situations where the number of objects is unknown. We explore these ideas with two case studies showing what can be learned from our two presented studies. Our first study explores an inter-rater comparison, showing that smaller lesions cannot be reliably identified. In our second case study, we demonstrate fusing multiple MS lesion segmentation algorithms based on the insights into the algorithms provided by our analysis to generate a segmentation that exhibits improved performance. This work demonstrates the wealth of information that can be learned from refined analysis of medical image segmentations.

TAPAS: A Thresholding Approach for Probability Map Automatic Segmentation in Multiple Sclerosis

Total brain white matter lesion (WML) volume is the most widely established magnetic resonance imaging (MRI) outcome measure in studies of multiple sclerosis (MS). To estimate WML volume, there are a number of automatic segmentation methods available, yet manual delineation remains the gold standard approach. Automatic approaches often yield a probability map to which a threshold is applied to create lesion segmentation masks. Unfortunately, few approaches systematically determine the threshold employed; many methods use a manually selected threshold, thus introducing human error and bias into the automated procedure. In this study, we propose and validate an automatic thresholding algorithm, Thresholding Approach for Probability Map Automatic Segmentation in Multiple Sclerosis (TAPAS), to obtain subject-specific threshold estimates for probability map automatic segmentation of T2-weighted (T2) hyperintense WMLs. Using multimodal MRI, the proposed method applies an automatic segmentation algorithm to obtain probability maps. We obtain the true subject-specific threshold that maximizes the Sørensen-Dice similarity coefficient (DSC). Then the subject-specific thresholds are modeled on a naive estimate of volume using a generalized additive model. Applying this model, we predict a subject-specific threshold in data not used for training. We ran a Monte Carlo-resampled split-sample cross-validation (100 validation sets) using two data sets: the first obtained from the Johns Hopkins Hospital (JHH) on a Philips 3 Tesla (3T) scanner (n = 94) and a second collected at the Brigham and Women's Hospital (BWH) using a Siemens 3T scanner (n = 40). By means of the proposed automated technique, in the JHH data we found an average reduction in subject-level absolute error of 0.1 mL per one mL increase in manual volume. Using Bland-Altman analysis, we found that volumetric bias associated with group-level thresholding was mitigated when applying TAPAS. The BWH data showed similar absolute error estimates using group-level thresholding or TAPAS likely since Bland-Altman analyses indicated no systematic biases associated with group or TAPAS volume estimates. The current study presents the first validated fully automated method for subject-specific threshold prediction to segment brain lesions.

Multiple Sclerosis Lesions Segmentation in Magnetic Resonance Imaging using Ensemble Support Vector Machine (ESVM)

Background

Multiple Sclerosis (MS) syndrome is a type of Immune-Mediated disorder in the central nervous system (CNS) which destroys myelin sheaths, and results in plaque (lesion) formation in the brain. From the clinical point of view, investigating and monitoring information such as position, volume, number, and changes of these plaques are integral parts of the controlling process this disease over a period. Visualizing MS lesions in vivo with Magnetic Resonance Imaging (MRI) has a key role in observing the course of the disease.

Material and Methods

In this analytical study, two different processing methods were present in this study in order to make an effort to detect and localize lesions in the patients' FLAIR (Fluid-attenuated inversion recovery) images. Segmentation was performed using Ensemble Support Vector Machine (SVM) classification. The trained data was randomly divided into five equal sections, and each section was fed into the computer as an input to one of the SVM classifiers that led to five different SVM structures.

Results

To evaluate results of segmentation, some criteria have been investigated such as Dice, Jaccard, sensitivity, specificity, PPV and accuracy. Both modes of ESVM, including first and second ones have similar results. Dice criterion was satisfied much better with specialist's work and it is observed that Dice average has 0.57±.15 and 0.6±.12 values in the first and second approach, respectively.

Conclusion

An acceptable overlap between those results reported by the neurologist and the ones obtained from the automatic segmentation algorithm was reached using an appropriate pre-processing in the proposed algorithm. Post-processing analysis further reduced false positives using morphological operations and also improved the evaluation criteria, including sensitivity and positive predictive value.

Automated Detection and Segmentation of Multiple Sclerosis Lesions Using Ultra-High-Field MP2RAGE

OBJECTIVES

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.

MATERIALS AND METHODS

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.

RESULTS

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.

CONCLUSIONS

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.

Automated volumetric assessment with artificial neural networks might enable a more accurate assessment of disease burden in patients with multiple sclerosis

OBJECTIVES

Patients with multiple sclerosis (MS) regularly undergo MRI for assessment of disease burden. However, interpretation may be time consuming and prone to intra- and interobserver variability. Here, we evaluate the potential of artificial neural networks (ANN) for automated volumetric assessment of MS disease burden and activity on MRI.

METHODS

A single-institutional dataset with 334 MS patients (334 MRI exams) was used to develop and train an ANN for automated identification and volumetric segmentation of T2/FLAIR-hyperintense and contrast-enhancing (CE) lesions. Independent testing was performed in a single-institutional longitudinal dataset with 82 patients (266 MRI exams). We evaluated lesion detection performance (F1 scores), lesion segmentation agreement (DICE coefficients), and lesion volume agreement (concordance correlation coefficients [CCC]). Independent evaluation was performed on the public ISBI-2015 challenge dataset.

RESULTS

The F1 score was maximized in the training set at a detection threshold of 7 mm³ for T2/FLAIR lesions and 14 mm³ for CE lesions. In the training set, mean F1 scores were 0.867 for T2/FLAIR lesions and 0.636 for CE lesions, as compared to 0.878 for T2/FLAIR lesions and 0.715 for CE lesions in the test set. Using these thresholds, the ANN yielded mean DICE coefficients of 0.834 and 0.878 for segmentation of T2/FLAIR and CE lesions in the training set (fivefold cross-validation). Corresponding DICE coefficients in the test set were 0.846 for T2/FLAIR lesions and 0.908 for CE lesions, and the CCC was ≥ 0.960 in each dataset.

CONCLUSIONS

Our results highlight the capability of ANN for quantitative state-of-the-art assessment of volumetric lesion load on MRI and potentially enable a more accurate assessment of disease burden in patients with MS.

KEY POINTS

• Artificial neural networks (ANN) can accurately detect and segment both T2/FLAIR and contrast-enhancing MS lesions in MRI data. • Performance of the ANN was consistent in a clinically derived dataset, with patients presenting all possible disease stages in MRI scans acquired from standard clinical routine rather than with high-quality research sequences. • Computer-aided evaluation of MS with ANN could streamline both clinical and research procedures in the volumetric assessment of MS disease burden as well as in lesion detection.

Automatic detection of lesion load change in Multiple Sclerosis using convolutional neural networks with segmentation confidence

The detection of new or enlarged white-matter lesions is a vital task in the monitoring of patients undergoing disease-modifying treatment for multiple sclerosis. However, the definition of 'new or enlarged' is not fixed, and it is known that lesion-counting is highly subjective, with high degree of inter- and intra-rater variability. Automated methods for lesion quantification, if accurate enough, hold the potential to make the detection of new and enlarged lesions consistent and repeatable. However, the majority of lesion segmentation algorithms are not evaluated for their ability to separate radiologically progressive from radiologically stable patients, despite this being a pressing clinical use-case. In this paper, we explore the ability of a deep learning segmentation classifier to separate stable from progressive patients by lesion volume and lesion count, and find that neither measure provides a good separation. Instead, we propose a method for identifying lesion changes of high certainty, and establish on an internal dataset of longitudinal multiple sclerosis cases that this method is able to separate progressive from stable time-points with a very high level of discrimination (AUC = 0.999), while changes in lesion volume are much less able to perform this separation (AUC = 0.71). Validation of the method on two external datasets confirms that the method is able to generalize beyond the setting in which it was trained, achieving an accuracies of 75 % and 85 % in separating stable and progressive time-points.

SegAE: Unsupervised white matter lesion segmentation from brain MRIs using a CNN autoencoder

White matter hyperintensities (WMHs) of presumed vascular origin are frequently observed in magnetic resonance images (MRIs) of the elderly. Detection and quantification of WMHs is important to help doctors make diagnoses and evaluate prognosis of their elderly patients, and once quantified, these can act as biomarkers in clinical research studies. Manual delineation of WMHs can be both time-consuming and inconsistent, hence, automatic segmentation methods are often preferred. However, fully automatic methods can be challenging to construct due to the variability in lesion load, placement of lesions, and voxel intensities. Several state-of-the-art lesion segmentation methods based on supervised Convolutional Neural Networks (CNNs) have been proposed. These approaches require manually delineated lesions for training the parameters of the network. Here we present a novel approach for WMH segmentation using a CNN trained in an unsupervised manner, by reconstructing multiple MRI sequences as weighted sums of segmentations of WMHs and tissues present in the images. After training, our method can be used to segment new images that are not part of the training set to provide fast and robust segmentation of WMHs in a matter of seconds per subject. Comparisons with state-of-the-art WMH segmentation methods evaluated on ground truth manual labels from two distinct data sets and six different scanners indicate that the proposed method works well at generating accurate WMH segmentations without the need for manual delineations.

Comparing lesion segmentation methods in multiple sclerosis: Input from one manually delineated subject is sufficient for accurate lesion segmentation

PURPOSE

Accurate lesion segmentation is important for measurements of lesion load and atrophy in subjects with multiple sclerosis (MS). International MS lesion challenges show a preference of convolutional neural networks (CNN) strategies, such as nicMSlesions. However, since the software is trained on fairly homogenous training data, we aimed to test the performance of nicMSlesions in an independent dataset with manual and other automatic lesion segmentations to determine whether this method is suitable for larger, multi-center studies.

METHODS

Manual lesion segmentation was performed in fourteen subjects with MS on sagittal 3D FLAIR images from a 3T GE whole-body scanner with 8-channel head coil. We compared five different categories of automated lesion segmentation methods for their volumetric and spatial agreement with manual segmentation: (i) unsupervised, untrained (LesionTOADS); (ii) supervised, untrained (LST-LPA and nicMSlesions with default settings); (iii) supervised, untrained with threshold adjustment (LST-LPA optimized for current data); (iv) supervised, trained with leave-one-out cross-validation on fourteen subjects with MS (nicMSlesions and BIANCA); and (v) supervised, trained on a single subject with MS (nicMSlesions). Volumetric accuracy was determined by the intra-class correlation coefficient (ICC) and spatial accuracy by Dice's similarity index (SI). Volumes and SI were compared between methods using repeated measures ANOVA or Friedman tests with post-hoc pairwise comparison.

RESULTS

The best volumetric and spatial agreement with manual was obtained with the supervised and trained methods nicMSlesions and BIANCA (ICC absolute agreement > 0.968 and median SI > 0.643) and the worst with the unsupervised, untrained method LesionTOADS (ICC absolute agreement = 0.140 and median SI = 0.444). Agreement with manual in the single-subject network training of nicMSlesions was poor for input with low lesion volumes (i.e. two subjects with lesion volumes ≤ 3.0 ml). For the other twelve subjects, ICC varied from 0.593 to 0.973 and median SI varied from 0.535 to 0.606. In all cases, the single-subject trained nicMSlesions segmentations outperformed LesionTOADS, and in almost all cases it also outperformed LST-LPA.

CONCLUSION

Input from only one subject to re-train the deep learning CNN nicMSlesions is sufficient for adequate lesion segmentation, with on average higher volumetric and spatial agreement with manual than obtained with the untrained methods LesionTOADS and LST-LPA.

Convolutional neural networks for multi-class brain disease detection using MRI images

The brain disorders may cause loss of some critical functions such as thinking, speech, and movement. So, the early detection of brain diseases may help to get the timely best treatment. One of the conventional methods used to diagnose these disorders is the magnetic resonance imaging (MRI) technique. Manual diagnosis of brain abnormalities is time-consuming and difficult to perceive the minute changes in the MRI images, especially in the early stages of abnormalities. Proper selection of the features and classifiers to obtain the highest performance is a challenging task. Hence, deep learning models have been widely used for medical image analysis over the past few years. In this study, we have employed the AlexNet, Vgg-16, ResNet-18, ResNet-34, and ResNet-50 pre-trained models to automatically classify MR images in to normal, cerebrovascular, neoplastic, degenerative, and inflammatory diseases classes. We have also compared their classification performance with pre-trained models, which are the state-of-art architectures. We have obtained the best classification accuracy of 95.23% ± 0.6 with the ResNet-50 model among the five pre-trained models. Our model is ready to be tested with huge MRI images of brain abnormalities. The outcome of the model will also help the clinicians to validate their findings after manual reading of the MRI images.

Multiple Sclerosis Lesion Segmentation with Tiramisu and 2.5D Stacked Slices

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.

Longitudinal analysis of white matter and cortical lesions in multiple sclerosis

PURPOSE

The goals of this study were to assess the performance of a novel lesion segmentation tool for longitudinal analyses, as well as to validate the generated lesion progression map between two time points using conventional and non-conventional MR sequences.

MATERIAL AND METHODS

The lesion segmentation approach was evaluated with (LeMan-PV) and without (LeMan) the partial volume framework using "conventional" and "non-conventional" MR imaging in a two-year follow-up prospective study of 32 early RRMS patients. Manual segmentations of new, enlarged, shrunken, and stable lesions were used to evaluate the performance of the method variants. The true positive rate was estimated for those lesion evolutions in both white matter and cortex. The number of false positives was compared with two strategies for longitudinal analyses. New lesion tissue volume estimation was evaluated using Bland-Altman plots. Wilcoxon signed-rank test was used to evaluate the different setups.

RESULTS

The best median of the true positive rate was obtained using LeMan-PV with non-conventional sequences (P < .05): 87%, 87%, 100%, 83%, for new, enlarged, shrunken, and stable WM lesions, and 50%, 60%, 50%, 80%, for new, enlarged, shrunken, and stable cortical lesions, respectively. Most of the missed lesions were below the mean lesion size in each category. Lesion progression maps presented a median of 0 false positives (range:0-9) and the partial volume framework improved the volume estimation of new lesion tissue.

CONCLUSION

LeMan-PV exhibited the best performance in the detection of new, enlarged, shrunken and stable WM lesions. The method showed lower performance in the detection of cortical lesions, likely due to their low occurrence, small size and low contrast with respect to surrounding tissues. The proposed lesion progression map might be useful in clinical trials or clinical routine.

Brain and lesion segmentation in multiple sclerosis using fully convolutional neural networks: A large-scale study

OBJECTIVE

To investigate the performance of deep learning (DL) based on fully convolutional neural network (FCNN) in segmenting brain tissues in a large cohort of multiple sclerosis (MS) patients.

METHODS

We developed a FCNN model to segment brain tissues, including T2-hyperintense MS lesions. The training, validation, and testing of FCNN were based on ~1000 magnetic resonance imaging (MRI) datasets acquired on relapsing-remitting MS patients, as a part of a phase 3 randomized clinical trial. Multimodal MRI data (dual-echo, FLAIR, and T1-weighted images) served as input to the network. Expert validated segmentation was used as the target for training the FCNN. We cross-validated our results using the leave-one-center-out approach.

RESULTS

We observed a high average (95% confidence limits) Dice similarity coefficient for all the segmented tissues: 0.95 (0.92-0.98) for white matter, 0.96 (0.93-0.98) for gray matter, 0.99 (0.98-0.99) for cerebrospinal fluid, and 0.82 (0.63-1.0) for T2 lesions. High correlations between the DL segmented tissue volumes and ground truth were observed (R² > 0.92 for all tissues). The cross validation showed consistent results across the centers for all tissues.

CONCLUSION

The results from this large-scale study suggest that deep FCNN can automatically segment MS brain tissues, including lesions, with high accuracy.

Applying causal models to explore the mechanism of action of simvastatin in progressive multiple sclerosis

Understanding the mode of action of drugs is a challenge with conventional methods in clinical trials. Here, we aimed to explore whether simvastatin effects on brain atrophy and disability in secondary progressive multiple sclerosis (SPMS) are mediated by reducing cholesterol or are independent of cholesterol. We applied structural equation models to the MS-STAT trial in which 140 patients with SPMS were randomized to receive placebo or simvastatin. At baseline, after 1 and 2 years, patients underwent brain magnetic resonance imaging; their cognitive and physical disability were assessed on the block design test and Expanded Disability Status Scale (EDSS), and serum total cholesterol levels were measured. We calculated the percentage brain volume change (brain atrophy). We compared two models to select the most likely one: a cholesterol-dependent model with a cholesterol-independent model. The cholesterol-independent model was the most likely option. When we deconstructed the total treatment effect into indirect effects, which were mediated by brain atrophy, and direct effects, simvastatin had a direct effect (independent of serum cholesterol) on both the EDSS, which explained 69% of the overall treatment effect on EDSS, and brain atrophy, which, in turn, was responsible for 31% of the total treatment effect on EDSS [β = -0.037; 95% credible interval (CI) = -0.075, -0.010]. This suggests that simvastatin's beneficial effects in MS are independent of its effect on lowering peripheral cholesterol levels, implicating a role for upstream intermediate metabolites of the cholesterol synthesis pathway. Importantly, it demonstrates that computational models can elucidate the causal architecture underlying treatment effects in clinical trials of progressive MS.

Automated segmentation of changes in FLAIR-hyperintense white matter lesions in multiple sclerosis on serial magnetic resonance imaging

Longitudinal analysis of white matter lesion changes on serial MRI has become an important parameter to study diseases with white-matter lesions. Here, we build on earlier work on cross-sectional lesion segmentation; we present a fully automatic pipeline for serial analysis of FLAIR-hyperintense white matter lesions. Our algorithm requires three-dimensional gradient echo T1- and FLAIR- weighted images at 3 Tesla as well as available cross-sectional lesion segmentations of both time points. Preprocessing steps include lesion filling and intrasubject registration. For segmentation of lesion changes, initial lesion maps of different time points are fused; herein changes in intensity are analyzed at the voxel level. Significance of lesion change is estimated by comparison with the difference distribution of FLAIR intensities within normal appearing white matter. The method is validated on MRI data of two time points from 40 subjects with multiple sclerosis derived from two different scanners (20 subjects per scanner). Manual segmentation of lesion increases served as gold standard. Across all lesion increases, voxel-wise Dice coefficient (0.7) as well as lesion-wise detection rate (0.8) and false-discovery rate (0.2) indicate good overall performance. Analysis of scans from a repositioning experiment in a single patient with multiple sclerosis did not yield a single false positive lesion. We also introduce the lesion change plot as a descriptive tool for the lesion change of individual patients with regard to both number and volume. An open source implementation of the algorithm is available at http://www.statistical-modeling.de/lst.html.

•

Quantification of white matter lesion changes is important in multiple sclerosis.

•

We developed and validated an algorithm for automated detection of lesion changes.

•

Our algorithm requires T1-weighted and FLAIR images derived at 3 T as well as available cross-sectional lesion segmentations.

•

With data from 2 different scanners, the tool showed good agreement with manual tracing.

•

An open-source application is available.