Simultaneous left atrium anatomy and scar segmentations via deep learning in multiview information with attention

Yang, Guang; Chen, Jun; Gao, Zhifan; Li, Shuo; Ni, Hao; Angelini, Elsa D.; Wong, Tom; Mohiaddin, Raad H.; Nyktari, Eva; Wage, Ricardo; Xu, Lei; Zhang, Yanping; Du, Xiujuan; Zhang, Heye; Firmin, David; Keegan, Jennifer

doi:10.1016/j.future.2020.02.005

Cited by 84 publications

(53 citation statements)

References 43 publications

(66 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the very small are occupied by the inner ear in the whole MRI volume, the performance of our model might be further improved by applying bounding box detection 33 or shape identification 34 prior to automated segmentation especially for abnormal cases.…”

Section: Discussionmentioning

confidence: 99%

Deep learning for the fully automated segmentation of the inner ear on MRI

Vaidyanathan

Lubbe

Leijenaar³

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Segmentation of anatomical structures is valuable in a variety of tasks, including 3D visualization, surgical planning, and quantitative image analysis. Manual segmentation is time-consuming and deals with intra and inter-observer variability. To develop a deep-learning approach for the fully automated segmentation of the inner ear in MRI, a 3D U-net was trained on 944 MRI scans with manually segmented inner ears as reference standard. The model was validated on an independent, multicentric dataset consisting of 177 MRI scans from three different centers. The model was also evaluated on a clinical validation set containing eight MRI scans with severe changes in the morphology of the labyrinth. The 3D U-net model showed precise Dice Similarity Coefficient scores (mean DSC-0.8790) with a high True Positive Rate (91.5%) and low False Discovery Rate and False Negative Rates (14.8% and 8.49% respectively) across images from three different centers. The model proved to perform well with a DSC of 0.8768 on the clinical validation dataset. The proposed auto-segmentation model is equivalent to human readers and is a reliable, consistent, and efficient method for inner ear segmentation, which can be used in a variety of clinical applications such as surgical planning and quantitative image analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning for the fully automated segmentation of the inner ear on MRI

Vaidyanathan

Lubbe

Leijenaar³

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Future work should test and assess the ability of the algorithms on different microscopes and with the use of multiple wavelengths of laser light on optically-cleared thick tissue sections to obtain three-dimensional (3D) information 41 , 42 . In addition, adding attention-based methods to the deep learning approach could help feature recognition and minimize background variability 43 , 44 . Fourth, the brain sections were visually scanned by users to find and acquire a digital image for each CMH.…”

Section: Discussionmentioning

confidence: 99%

Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages

Crouzet

Jeong

Chae

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Cerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.

show abstract

“…Within MCAB, we firstly concatenated the outputs of two encoders at each depth and added a convolutional block that was of the same setting as the encoder to allow the model to disentangle the latent relationship between the information between the two channels. Then, the convoluted data stream went through an attention block [ 23 ] before being delivered to the decoder at each depth.…”

Section: Methodsmentioning

confidence: 99%

Fast and Automated Segmentation for the Three-Directional Multi-Slice Cine Myocardial Velocity Mapping

Hatipoğlu

Alonso-Álvarez

et al. 2021

Diagnostics

Self Cite

View full text Add to dashboard Cite

Three-directional cine multi-slice left ventricular myocardial velocity mapping (3Dir MVM) is a cardiac magnetic resonance (CMR) technique that allows the assessment of cardiac motion in three orthogonal directions. Accurate and reproducible delineation of the myocardium is crucial for accurate analysis of peak systolic and diastolic myocardial velocities. In addition to the conventionally available magnitude CMR data, 3Dir MVM also provides three orthogonal phase velocity mapping datasets, which are used to generate velocity maps. These velocity maps may also be used to facilitate and improve the myocardial delineation. Based on the success of deep learning in medical image processing, we propose a novel fast and automated framework that improves the standard U-Net-based methods on these CMR multi-channel data (magnitude and phase velocity mapping) by cross-channel fusion with an attention module and the shape information-based post-processing to achieve accurate delineation of both epicardial and endocardial contours. To evaluate the results, we employ the widely used Dice Scores and the quantification of myocardial longitudinal peak velocities. Our proposed network trained with multi-channel data shows superior performance compared to standard U-Net-based networks trained on single-channel data. The obtained results are promising and provide compelling evidence for the design and application of our multi-channel image analysis of the 3Dir MVM CMR data.

show abstract

Simultaneous left atrium anatomy and scar segmentations via deep learning in multiview information with attention

Cited by 84 publications

References 43 publications

Deep learning for the fully automated segmentation of the inner ear on MRI

Deep learning for the fully automated segmentation of the inner ear on MRI

Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages

Fast and Automated Segmentation for the Three-Directional Multi-Slice Cine Myocardial Velocity Mapping

Contact Info

Product

Resources

About