Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks

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

doi:10.1016/j.nicl.2020.102445

Cited by 39 publications

(36 citation statements)

References 37 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From FLAIR, the number and the total volume in milliliters of all hyperintense lesions were determined by an automatic algorithm based on convolutional neural networks. 29 All results were manually corrected by two experienced technical raters. Differences in the corrections were resolved by consensus in a second reading phase.…”

Section: Methodsmentioning

confidence: 99%

T-Cell Specificity Influences Disease Heterogeneity in Multiple Sclerosis

Cruciani

Puthenparampil

Tomas-Ojer

et al. 2021

Neurol Neuroimmunol Neuroinflamm

Self Cite

View full text Add to dashboard Cite

Background and ObjectivesEncouraged by the enormous progress that the identification of specific autoantigens added to the understanding of neurologic autoimmune diseases, we undertook here an in-depth study of T-cell specificities in the autoimmune disease multiple sclerosis (MS), for which the spectrum of responsible autoantigens is not fully defined yet. The identification of target antigens in MS is crucial for therapeutic strategies aimed to induce antigen-specific tolerance. In addition, knowledge of relevant T-cell targets can improve our understanding of disease heterogeneity, a hallmark of MS that complicates clinical management.MethodsThe proliferative response and interferon gamma (IFN-γ) release of CSF-infiltrating CD4+ T cells from patients with MS against several autoantigens was used to identify patients with different intrathecal T-cell specificities. Fresh CSF-infiltrating and paired circulating lymphocytes in these patients were characterized in depth by ex vivo immunophenotyping and transcriptome analysis of relevant T-cell subsets. Further examination of these patients included CSF markers of inflammation and neurodegeneration and a detailed characterization with respect to demographic, clinical, and MRI features.ResultsBy testing CSF-infiltrating CD4+ T cells from 105 patients with MS against seven long-known myelin and five recently described GDP-l-fucose synthase peptides, we identified GDP-l-fucose synthase and myelin oligodendrocyte glycoprotein (35-55) responder patients. Immunophenotyping of CSF and paired blood samples in these patients revealed a significant expansion of an effector memory (CCR7− CD45RA−) CD27− Th1 CD4+ cell subset in GDP-l-fucose synthase responders. Subsequent transcriptome analysis of this subset demonstrated expression of Th1 and cytotoxicity-associated genes. Patients with different intrathecal T-cell specificities also differ regarding inflammation- and neurodegeneration-associated biomarkers, imaging findings, expression of HLA class II alleles, and seasonal distribution of the time of the lumbar puncture.DiscussionOur observations reveal an association between autoantigen reactivity and features of disease heterogeneity that strongly supports an important role of T-cell specificity in MS pathogenesis. These data have the potential to improve patient classification in clinical practice and to guide the development of antigen-specific tolerization strategies.

show abstract

Section: Methodsmentioning

confidence: 99%

T-Cell Specificity Influences Disease Heterogeneity in Multiple Sclerosis

Cruciani

Puthenparampil

Tomas-Ojer

et al. 2021

Neurol Neuroimmunol Neuroinflamm

Self Cite

View full text Add to dashboard Cite

show abstract

“…The visual identification of new lesions in MRI requires the mental processing of a large amount of 3D information and it is common for radiologists to miss notable lesions emerging from one acquisition to another, even for highly-experienced radiologists ( 7 ). The segmentation module thus aims at automatically extracting candidate new lesions that will then be highlighted in a dedicated viewer accessible to experts.…”

Section: Methodsmentioning

confidence: 99%

“…It is worth noting that we do not think these results are intrinsically related to our segmentation module. Indeed, while being built on state-of-the-art solutions and exhibiting satisfying performances, it may be replaced by other recent methods of the literature [e.g., (7)(8)(9)(10)]. Our aim is not to show the superiority of our segmentation module but to evidence the potential impact of using state-of-the-art segmentation methods on MS clinical practice.…”

Section: Automated New Lesion Segmentation Tools Provide a Relevant And Valuable Aid For Cliniciansmentioning

confidence: 99%

“…An annual follow-up by brain MRI is therefore currently recommended, at least during the first year of treatment ( 5 , 6 ), and the comparison of annual MRI scans is frequently performed by the radiologists and neurologists in charge of the follow-up of MS patients. However, this comparison is a complex and mentally demanding task that often leads to an underestimation of lesion accumulation, even for most experienced radiologists ( 7 ). Consequently, there is a need for dedicated systems that can provide clinicians, regardless of their level of expertise, an aid for accurate and robust detection of new FLAIR MS lesions.…”

Section: Introductionmentioning

confidence: 99%

“…More recently, standardization of MR imaging acquisitions and data-transfer protocols as well as advances in computer vision methods have offered the premises for an end-to-end workflow for computer-aided comparative analysis of longitudinal MRI data. In particular, thanks to the development of deep learning techniques, powerful tools for the automatic segmentation of new MS lesions have been proposed in the context of academic research on the one hand [e.g., ( 7 , 9 , 10 )], and integrated into commercial products on the other hand ( 11 ). However, the added-value of these tools in clinical practice is not well-documented, especially regarding therapeutic strategy and disability progression.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Combès

Kerbrat

Pasquier³

et al. 2021

Front. Med.

View full text Add to dashboard Cite

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.

show abstract

A Multicenter Longitudinal MRI Study Assessing LeMan‐PV Software Accuracy in the Detection of White Matter Lesions in Multiple Sclerosis Patients

Todea

Melie‐García

Baraković

et al. 2023

Magnetic Resonance Imaging

View full text Add to dashboard Cite

BackgroundDetecting new and enlarged lesions in multiple sclerosis (MS) patients is needed to determine their disease activity. LeMan‐PV is a software embedded in the scanner reconstruction system of one vendor, which automatically assesses new and enlarged white matter lesions (NELs) in the follow‐up of MS patients; however, multicenter validation studies are lacking.PurposeTo assess the accuracy of LeMan‐PV for the longitudinal detection NEL white‐matter MS lesions in a multicenter clinical setting.Study TypeRetrospective, longitudinal.SubjectsA total of 206 patients with a definitive MS diagnosis and at least two follow‐up MRI studies from five centers participating in the Swiss Multiple Sclerosis Cohort study. Mean age at first follow‐up = 45.2 years (range: 36.9–52.8 years); 70 males.Field Strength/SequenceFluid attenuated inversion recovery (FLAIR) and T1‐weighted magnetization prepared rapid gradient echo (T1‐MPRAGE) sequences at 1.5 T and 3 T.AssessmentThe study included 313 MRI pairs of datasets. Data were analyzed with LeMan‐PV and compared with a manual “reference standard” provided by a neuroradiologist. A second rater (neurologist) performed the same analysis in a subset of MRI pairs to evaluate the rating‐accuracy. The Sensitivity (Se), Specificity (Sp), Accuracy (Acc), F1‐score, lesion‐wise False‐Positive‐Rate (aFPR), and other measures were used to assess LeMan‐PV performance for the detection of NEL at 1.5 T and 3 T. The performance was also evaluated in the subgroup of 123 MRI pairs at 3 T.Statistical TestsIntraclass correlation coefficient (ICC) and Cohen's kappa (CK) were used to evaluate the agreement between readers.ResultsThe interreader agreement was high for detecting new lesions (ICC = 0.97, Pvalue < 10−20, CK = 0.82, P value = 0) and good (ICC = 0.75, P value < 10−12, CK = 0.68, P value = 0) for detecting enlarged lesions. Across all centers, scanner field strengths (1.5 T, 3 T), and for NEL, LeMan‐PV achieved: Acc = 61%, Se = 65%, Sp = 60%, F1‐score = 0.44, aFPR = 1.31. When both follow‐ups were acquired at 3 T, LeMan‐PV accuracy was higher (Acc = 66%, Se = 66%, Sp = 66%, F1‐score = 0.28, aFPR = 3.03).Data ConclusionIn this multicenter study using clinical data settings acquired at 1.5 T and 3 T, and variations in MRI protocols, LeMan‐PV showed similar sensitivity in detecting NEL with respect to other recent 3 T multicentric studies based on neural networks. While LeMan‐PV performance is not optimal, its main advantage is that it provides automated clinical decision support integrated into the radiological‐routine flow.Evidence Level4Technical EfficacyStage 2

show abstract

Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks

Cited by 39 publications

References 37 publications

T-Cell Specificity Influences Disease Heterogeneity in Multiple Sclerosis

T-Cell Specificity Influences Disease Heterogeneity in Multiple Sclerosis

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

A Multicenter Longitudinal MRI Study Assessing LeMan‐PV Software Accuracy in the Detection of White Matter Lesions in Multiple Sclerosis Patients

Contact Info

Product

Resources

About