Semi-Supervised Deep Learning for Multi-Tissue Segmentation from Multi-Contrast MRI

Anwar, Syed Muhammad; Irmakci, Ismail; Torigian, Drew A.; Jambawalikar, Sachin; Papadakis, Georgios Z.; Akgün, Can; Akçakaya, Mehmet; Bağcı, Ulaş

doi:10.1007/s11265-020-01612-4

Cited by 9 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…found in the literature. Such studies which used deep learning methods to discriminate thigh and leg tissues from MRI scans obtained very high accuracy performances, namely DSC of 0.97, 0.94 and 0.80 [4] and 0.96, 0.92 and 0.93 [3] for muscle, fat and inter-muscular adipose tissue respectively. In our study, however, as in [9] we used a different approach as we started from ground truth segmentation of muscles based on their anatomy, resulting in a network capable of replicating the manual segmentation of muscles ROIs done by hand.…”

Section: Discussionmentioning

confidence: 99%

“…In particular, recent studies applied diverse approaches including variational segmentation methods combined with statistical clustering-based techniques on T1-weighted scans [10,22], machine-learning classification techniques on intensity-based features extracted from multi-contrast Dixon scans [29], Deep Neural Networks (DNN) methods based on convolutional architectures combined with variational contour detector on T1-w scans [30] and DNN methods based on an encoder-decoder U-net architecture [27] combined with a clustering algorithm on T2 and proton density (PD) maps from multi spin echo scans [3]. Finally, Anwar et al applied a semi-supervised deep learning approach based on an encoder-decoder architecture on multi-contrast Dixon scans [4]. This latter work provided a unified framework to automatically segment both the multiple tissues regions and the edges of the fascia lata, which separates the adipose tissue domain into subcutaneous and inter-muscular.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning for automatic segmentation of thigh and leg muscles

Agosti

Shaqiri²,

Paoletti³

et al. 2021

Magn Reson Mater Phy

View full text Add to dashboard Cite

Objective In this study we address the automatic segmentation of selected muscles of the thigh and leg through a supervised deep learning approach. Material and methods The application of quantitative imaging in neuromuscular diseases requires the availability of regions of interest (ROI) drawn on muscles to extract quantitative parameters. Up to now, manual drawing of ROIs has been considered the gold standard in clinical studies, with no clear and universally accepted standardized procedure for segmentation. Several automatic methods, based mainly on machine learning and deep learning algorithms, have recently been proposed to discriminate between skeletal muscle, bone, subcutaneous and intermuscular adipose tissue. We develop a supervised deep learning approach based on a unified framework for ROI segmentation. Results The proposed network generates segmentation maps with high accuracy, consisting in Dice Scores ranging from 0.89 to 0.95, with respect to “ground truth” manually segmented labelled images, also showing high average performance in both mild and severe cases of disease involvement (i.e. entity of fatty replacement). Discussion The presented results are promising and potentially translatable to different skeletal muscle groups and other MRI sequences with different contrast and resolution.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep learning for automatic segmentation of thigh and leg muscles

Agosti

Shaqiri²,

Paoletti³

et al. 2021

Magn Reson Mater Phy

View full text Add to dashboard Cite

show abstract

“…Distinction between adipose and healthy muscle tissue was performed using the same networks and the corresponding DSC values were also high, i.e., 0.91 ( 66 ) and 0.94 ± 0.07 ( 65 ) for muscle detection. Recently, impressive DSC scores of 0.97 were obtained with an improved U-Net structure using residual connections and dense blocks ( 67 ). However, such a classification did not allow to distinguish perimuscular and intramuscular adipose tissue.…”

Section: Deep Learning-based Segmentation Methodsmentioning

confidence: 99%

“…In that case, each image does not have to be annotated before the network training phase and one can increase the database without a human intervention for the labeling process. Anwar et al ( 67 ) proposed to use a CED on unlabeled data to create labels and thus enlarge their dataset. However, unlabeled data are not always available especially for the study of rare diseases.…”

Section: Deep Learning-based Segmentation Methodsmentioning

confidence: 99%

Overview of MR Image Segmentation Strategies in Neuromuscular Disorders

et al. 2021

View full text Add to dashboard Cite

Neuromuscular disorders are rare diseases for which few therapeutic strategies currently exist. Assessment of therapeutic strategies efficiency is limited by the lack of biomarkers sensitive to the slow progression of neuromuscular diseases (NMD). Magnetic resonance imaging (MRI) has emerged as a tool of choice for the development of qualitative scores for the study of NMD. The recent emergence of quantitative MRI has enabled to provide quantitative biomarkers more sensitive to the evaluation of pathological changes in muscle tissue. However, in order to extract these biomarkers from specific regions of interest, muscle segmentation is mandatory. The time-consuming aspect of manual segmentation has limited the evaluation of these biomarkers on large cohorts. In recent years, several methods have been proposed to make the segmentation step automatic or semi-automatic. The purpose of this study was to review these methods and discuss their reliability, reproducibility, and limitations in the context of NMD. A particular attention has been paid to recent deep learning methods, as they have emerged as an effective method of image segmentation in many other clinical contexts.

show abstract

“…Several studies have proposed either semi‐automated or fully automated methods in segmenting muscles on MRI images 16–22 . These automations have been mainly applied to whole limb muscles.…”

Section: Introductionmentioning

confidence: 99%

Automation of Quantifying Axonal Loss in Patients with Peripheral Neuropathies through Deep Learning Derived Muscle Fat Fraction

Chen

Moiseev

Kong

et al. 2021

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Axonal loss denervates muscle, leading to an increase of fat accumulation in the muscle. Therefore, fat fraction (FF) in whole limb muscle using MRI has emerged as a monitoring biomarker for axonal loss in patients with peripheral neuropathies. In this study, we are testing whether deep learning‐based model can automate quantification of the FF in individual muscles. While individual muscle is smaller with irregular shape, manually segmented muscle MRI images have been accumulated in this lab; and make the deep learning feasible. Purpose To automate segmentation on muscle MRI images through deep learning for quantifying individual muscle FF in patients with peripheral neuropathies. Study Type Retrospective. Subjects 24 patients and 19 healthy controls. Field Strength/Sequences 3T; Interleaved 3D GRE. Assessment A 3D U‐Net model was implemented in segmenting muscle MRI images. This was enabled by leveraging a large set of manually segmented muscle MRI images. B1+ and B1− maps were used to correct image inhomogeneity. Accuracy of the automation was evaluated using Pixel Accuracy (PA), Dice Coefficient (DC) in binary masks; and Bland‐Altman and Pearson correlation by comparing FF values between manual and automated methods. Statistical Tests PA and DC were reported with their median value and standard deviation. Two methods were compared using the ± 95% confidence intervals (CI) of Bland‐Altman analysis and the Pearson’s coefficient (r2). Results DC values were from 0.83 ± 0.17 to 0.98 ± 0.02 in thigh and from 0.63 ± 0.18 to 0.96 ± 0.02 in calf muscles. For FF values, the overall ± 95% CI and r2 were [0.49, –0.56] and 0.989 in thigh and [0.84, –0.71] and 0.971 in the calf. Data Conclusion Automated results well agreed with the manual results in quantifying FF for individual muscles. This method mitigates the formidable time consumption and intense labor in manual segmentations; and enables the use of individual muscle FF as outcome measures in upcoming longitudinal studies. Level of Evidence 3 Technical Efficacy Stage 1

show abstract

Semi-Supervised Deep Learning for Multi-Tissue Segmentation from Multi-Contrast MRI

Cited by 9 publications

References 24 publications

Deep learning for automatic segmentation of thigh and leg muscles

Deep learning for automatic segmentation of thigh and leg muscles

Overview of MR Image Segmentation Strategies in Neuromuscular Disorders

Automation of Quantifying Axonal Loss in Patients with Peripheral Neuropathies through Deep Learning Derived Muscle Fat Fraction

Contact Info

Product

Resources

About