Saliency Based Deep Neural Network for Automatic Detection of Gadolinium-Enhancing Multiple Sclerosis Lesions in Brain MRI

Durso-Finley, Joshua; Arnold, Douglas L.

doi:10.1007/978-3-030-46640-4_11

Cited by 4 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among these, some pipelines focus on detecting contrast-enhancing (CE) lesions since these are indicative of active disease. Gadolinium (Gad) is commonly used in the context of MS. Durso-finley et al [23] and Coronado et al [18] present to detect Gad lesions using pre-and post-contrast T1-weighted images. Brugnara et al [12] propose a network to detect both CE lesions and T2/FLAIR-hyperintense lesions and report the performance separately.…”

Section: Methods For Subtypes Of Ms Lesionsmentioning

confidence: 99%

“…Hu et al [35] included 3D spatial attention blocks in the decoding stage. Durso-Finley et al [23] used a saliency-based attention module before the U-Net structure to make the network realize the difference between pre-and post-contrast T1-w images and thus focus on the contrast-enhancing lesions. Hou et al [34] proposed a cross-attention block that combines spatial attention and channel attention.…”

Section: Network Architecturementioning

confidence: 99%

“…Using private datasets makes it difficult to compare algorithms but has the advantage of including more subjects than currently available in public datasets. Some proprietary datasets can be of a quite large scale (e.g., 6830 multi-channel MRI [23]). For such large datasets, the "ground truth" labels are usually created by automated or semi-automated algorithms and corrected by experts [46,23].…”

Section: Datasetsmentioning

confidence: 99%

“…Some proprietary datasets can be of a quite large scale (e.g., 6830 multi-channel MRI [23]). For such large datasets, the "ground truth" labels are usually created by automated or semi-automated algorithms and corrected by experts [46,23].…”

Section: Datasetsmentioning

confidence: 99%

See 3 more Smart Citations

Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methods

Zhang

Oguz

2020

Preprint

View full text Add to dashboard Cite

Lesion segmentation is a core task for quantitative analysis of MRI scans of Multiple Sclerosis patients. The recent success of deep learning techniques in a variety of medical image analysis applications has renewed community interest in this challenging problem and led to a burst of activity for new algorithm development. In this survey, we investigate the supervised CNN-based methods for MS lesion segmentation. We decouple these reviewed works into their algorithmic components and discuss each separately. For methods that provide evaluations on public benchmark datasets, we report comparisons between their results.

show abstract

Section: Methods For Subtypes Of Ms Lesionsmentioning

confidence: 99%

Section: Network Architecturementioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methods

Zhang

Oguz

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…More recently the development of convolutional neural net (CNN) based algorithms has resulted in improved segmentation accuracy ( Brosch et al, 2016 ; Aslani et al, 2019a , b ; Coronado et al, 2020 ; Gabr et al, 2020 ; Krüger et al, 2020 ; McKinley et al, 2020 , 2021 ; Narayana et al, 2020a , b ; Fenneteau et al, 2021 ). In particular, networks based on the U-Net architecture with an encoder-decoder structure have yielded excellent results for segmentation of FLAIR lesions ( Duong et al, 2019 ; La Rosa et al, 2020 ; Narayana et al, 2020a , b ; Fenneteau et al, 2021 ; McKinley et al, 2021 ) and lesion enhancement ( Coronado et al, 2020 ; Durso-Finley et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

3D U-Net for automated detection of multiple sclerosis lesions: utility of transfer learning from other pathologies

Wahlig,

Nedelec,

Weiss

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

Background and purposeDeep learning algorithms for segmentation of multiple sclerosis (MS) plaques generally require training on large datasets. This manuscript evaluates the effect of transfer learning from segmentation of another pathology to facilitate use of smaller MS-specific training datasets. That is, a model trained for detection of one type of pathology was re-trained to identify MS lesions and active demyelination.Materials and methodsIn this retrospective study using MRI exams from 149 patients spanning 4/18/2014 to 7/8/2021, 3D convolutional neural networks were trained with a variable number of manually-segmented MS studies. Models were trained for FLAIR lesion segmentation at a single timepoint, new FLAIR lesion segmentation comparing two timepoints, and enhancing (actively demyelinating) lesion segmentation on T1 post-contrast imaging. Models were trained either de-novo or fine-tuned with transfer learning applied to a pre-existing model initially trained on non-MS data. Performance was evaluated with lesionwise sensitivity and positive predictive value (PPV).ResultsFor single timepoint FLAIR lesion segmentation with 10 training studies, a fine-tuned model demonstrated improved performance [lesionwise sensitivity 0.55 ± 0.02 (mean ± standard error), PPV 0.66 ± 0.02] compared to a de-novo model (sensitivity 0.49 ± 0.02, p = 0.001; PPV 0.32 ± 0.02, p < 0.001). For new lesion segmentation with 30 training studies and their prior comparisons, a fine-tuned model demonstrated similar sensitivity (0.49 ± 0.05) and significantly improved PPV (0.60 ± 0.05) compared to a de-novo model (sensitivity 0.51 ± 0.04, p = 0.437; PPV 0.43 ± 0.04, p = 0.002). For enhancement segmentation with 20 training studies, a fine-tuned model demonstrated significantly improved overall performance (sensitivity 0.74 ± 0.06, PPV 0.69 ± 0.05) compared to a de-novo model (sensitivity 0.44 ± 0.09, p = 0.001; PPV 0.37 ± 0.05, p = 0.001).ConclusionBy fine-tuning models trained for other disease pathologies with MS-specific data, competitive models identifying existing MS plaques, new MS plaques, and active demyelination can be built with substantially smaller datasets than would otherwise be required to train new models.

show abstract

Multiple Sclerosis Lesion Segmentation - A Survey of Supervised CNN-Based Methods

Zhang

Oguz

2021

Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries

View full text Add to dashboard Cite

Saliency Based Deep Neural Network for Automatic Detection of Gadolinium-Enhancing Multiple Sclerosis Lesions in Brain MRI

Cited by 4 publications

References 13 publications

Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methods

Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methods

3D U-Net for automated detection of multiple sclerosis lesions: utility of transfer learning from other pathologies

Multiple Sclerosis Lesion Segmentation - A Survey of Supervised CNN-Based Methods

Contact Info

Product

Resources

About