Improving multiple sclerosis lesion segmentation across clinical sites: A federated learning approach with noise-resilient training.

Accurately measuring the evolution of Multiple Sclerosis (MS) with magnetic resonance imaging (MRI) critically informs understanding of disease progression and helps to direct therapeutic strategy. Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. Obtaining sufficient data from a single clinical site is challenging and does not address the heterogeneous need for model robustness. Conversely, the collection of data from multiple sites introduces data privacy concerns and potential label noise due to varying annotation standards. To address this dilemma, we explore the use of the federated learning framework while considering label noise. Our approach enables collaboration among multiple clinical sites without compromising data privacy under a federated learning paradigm that incorporates a noise-robust training strategy based on label correction. Specifically, we introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions, enabling the correction of false annotations based on prediction confidence. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites, enhancing the reliability of the correction process. Extensive experiments conducted on two multi-site datasets demonstrate the effectiveness and robustness of our proposed methods, indicating their potential for clinical applications in multi-site collaborations to train better deep learning models with lower cost in data collection and annotation.

A real-world clinical validation for AI-based MRI monitoring in multiple sclerosis.

Modern management of MS targets No Evidence of Disease Activity (NEDA): no clinical relapses, no magnetic resonance imaging (MRI) disease activity and no disability worsening. While MRI is the principal tool available to neurologists for monitoring clinically silent MS disease activity and, where appropriate, escalating treatment, standard radiology reports are qualitative and may be insensitive to the development of new or enlarging lesions. Existing quantitative neuroimaging tools lack adequate clinical validation. In 397 multi-center MRI scan pairs acquired in routine practice, we demonstrate superior case-level sensitivity of a clinically integrated AI-based tool over standard radiology reports (93.3% vs 58.3%), relative to a consensus ground truth, with minimal loss of specificity. We also demonstrate equivalence of the AI-tool with a core clinical trial imaging lab for lesion activity and quantitative brain volumetric measures, including percentage brain volume loss (PBVC), an accepted biomarker of neurodegeneration in MS (mean PBVC -0.32% vs -0.36%, respectively), whereas even severe atrophy (>0.8% loss) was not appreciated in radiology reports. Finally, the AI-tool additionally embeds a clinically meaningful, experiential comparator that returns a relevant MS patient centile for lesion burden, revealing, in our cohort, inconsistencies in qualitative descriptors used in radiology reports. AI-based image quantitation enhances the accuracy of, and value-adds to, qualitative radiology reporting. Scaled deployment of these tools will open a path to precision management for patients with MS.

Real world validation of an AI-based CT hemorrhage detection tool.

Introduction: Intracranial hemorrhage (ICH) is a potentially life-threatening medical event that requires expedited diagnosis with computed tomography (CT). Automated medical imaging triaging tools can rapidly bring scans containing critical abnormalities, such as ICH, to the attention of radiologists and clinicians. Here, we retrospectively investigated the real-world performance of VeriScout™, an artificial intelligence-based CT hemorrhage detection and triage tool. Methods: Ground truth for the presence or absence of ICH was iteratively determined by expert consensus in an unselected dataset of 527 consecutively acquired non-contrast head CT scans, which were sub-grouped according to the presence of artefact, post-operative features and referral source. The performance of VeriScout™ was compared with the ground truths for all groups. Results: VeriScout™ detected hemorrhage with a sensitivity of 0.92 (CI 0.84-0.96) and a specificity of 0.96 (CI 0.94-0.98) in the global dataset, exceeding the sensitivity of general radiologists (0.88) with only a minor relative decrement in specificity (0.98). Crucially, the AI tool detected 13/14 cases of subarachnoid hemorrhage, a potentially fatal condition that is often missed in emergency department settings. There was no decrement in the performance of VeriScout™ in scans containing artefact or postoperative change. Using an integrated informatics platform, VeriScout™ was deployed into the existing radiology workflow. Detected hemorrhage cases were flagged in the hospital radiology information system (RIS) and relevant, annotated, preview images made available in the picture archiving and communications system (PACS) within 10 min. Conclusion: AI-based radiology worklist prioritization for critical abnormalities, such as ICH, may enhance patient care without adding to radiologist or clinician burden.

Learning from pseudo-labels: deep networks improve consistency in longitudinal brain volume estimation.

Introduction: Brain atrophy is a critical biomarker of disease progression and treatment response in neurodegenerative diseases such as multiple sclerosis (MS). Confounding factors such as inconsistent imaging acquisitions hamper the accurate measurement of brain atrophy in the clinic. This study aims to develop and validate a robust deep learning model to overcome these challenges; and to evaluate its impact on the measurement of disease progression. Methods: Voxel-wise pseudo-atrophy labels were generated using SIENA, a widely adopted tool for the measurement of brain atrophy in MS. Deformation maps were produced for 195 pairs of longitudinal 3D T1 scans from patients with MS. A 3D U-Net, namely DeepBVC, was specifically developed overcome common variances in resolution, signal-to-noise ratio and contrast ratio between baseline and follow up scans. The performance of DeepBVC was compared against SIENA using McLaren test-retest dataset and 233 in-house MS subjects with MRI from multiple time points. Clinical evaluation included disability assessment with the Expanded Disability Status Scale (EDSS) and traditional imaging metrics such as lesion burden. Results: For 3 subjects in test-retest experiments, the median percent brain volume change (PBVC) for DeepBVC and SIENA was 0.105 vs. 0.198% (subject 1), 0.061 vs. 0.084% (subject 2), 0.104 vs. 0.408% (subject 3). For testing consistency across multiple time points in individual MS subjects, the mean (± standard deviation) PBVC difference of DeepBVC and SIENA were 0.028% (± 0.145%) and 0.031% (±0.154%), respectively. The linear correlation with baseline T2 lesion volume were r = -0.288 (p < 0.05) and r = -0.249 (p < 0.05) for DeepBVC and SIENA, respectively. There was no significant correlation of disability progression with PBVC as estimated by either method (p = 0.86, p = 0.84). Discussion: DeepBVC is a deep learning powered brain volume change estimation method for assessing brain atrophy used T1-weighted images. Compared to SIENA, DeepBVC demonstrates superior performance in reproducibility and in the context of common clinical scan variances such as imaging contrast, voxel resolution, random bias field, and signal-to-noise ratio. Enhanced measurement robustness, automation, and processing speed of DeepBVC indicate its potential for utilisation in both research and clinical environments for monitoring disease progression and, potentially, evaluating treatment effectiveness.

Multiple sclerosis lesion segmentation: revisiting weighting mechanisms for federated learning.

Background and introduction: Federated learning (FL) has been widely employed for medical image analysis to facilitate multi-client collaborative learning without sharing raw data. Despite great success, FL's applications remain suboptimal in neuroimage analysis tasks such as lesion segmentation in multiple sclerosis (MS), due to variance in lesion characteristics imparted by different scanners and acquisition parameters. Methods: In this work, we propose the first FL MS lesion segmentation framework via two effective re-weighting mechanisms. Specifically, a learnable weight is assigned to each local node during the aggregation process, based on its segmentation performance. In addition, the segmentation loss function in each client is also re-weighted according to the lesion volume for the data during training. Results: The proposed method has been validated on two FL MS segmentation scenarios using public and clinical datasets. Specifically, the case-wise and voxel-wise Dice score of the proposed method under the first public dataset is 65.20 and 74.30, respectively. On the second in-house dataset, the case-wise and voxel-wise Dice score is 53.66, and 62.31, respectively. Discussions and conclusions: The Comparison experiments on two FL MS segmentation scenarios using public and clinical datasets have demonstrated the effectiveness of the proposed method by significantly outperforming other FL methods. Furthermore, the segmentation performance of FL incorporating our proposed aggregation mechanism can achieve comparable performance to that from centralized training with all the raw data.