Deep learning-based image segmentation model using an MRI-based convolutional neural network for physiological evaluation of the heart

Xu, Wanni; Shi, Jianshe; Lin, Yunling; Liu, Chao; Xie, Weifang; Liu, Huifang; Huang, Siyu; Zhu, Daxin; Su, Lianta; Huang, Yifeng; Ye, Yuguang; Huang, Jianlong

doi:10.3389/fphys.2023.1148717

Cited by 5 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, it increases the stability of the learning process in the network. Xu et al, [52] used a U-Net network to perform image segmentation on MRI scan images, with the goal of improving physiological evaluation of the heart. The authors note that while deep learning-based models have improved segmentation accuracy compared to traditional methods, they still face challenges in fully differentiating the left and right ventricles from the myocardium, and training can be complex.…”

Section: A Batch Normalization Techniquesmentioning

confidence: 99%

“…These augmented images help the model to learn more robust and invariant features, making it less sensitive to slight changes in image orientation, position, or scale that can occur in real-world clinical settings. Moreover, data augmentation can also be beneficial in addressing class imbalance issues, as generating more samples of underrepresented classes can help to mitigate the bias towards majority classes [52].…”

Section: E Data Augmentation Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Deep Transfer Learning Optimization Techniques for Medical Image Classifcation - A Survey

Kariuki¹,

Gikunda²,

Wandeto³

2023

Preprint

View full text Add to dashboard Cite

<p>Medical image classification is not only a complex task but also a challenging one due to the heterogeneous nature of medical data. Deep transfer learning has proven to be a viable technique for medical image classification throughout the years, mostly because it is able to leverage knowledge from pre-trained models learned from large-scale datasets, improved performance, minimal training and overcoming the disadvantage of small data sets. This paper offers a succinct review of the cutting-edge deep transfer learning optimization approaches for medical image classification. The paper begins with an overview of convolutional neural networks (CNN) and transfer learning techniques, such as relation-based, feature, parameter and instance-based transfer learning. Then, the study examines classical classifiers, such as Resnet, VGG, Alexnet, Googlenet, and Inception, and compare their performance on medical image classification tasks. The study also presents optimization techniques, including batch normalization, regularization, and weight initialization, data augmentation and the kernel mathematical formulations. Finally, the study unearths various challenges that arise when using deep transfer learning for medical image classification as well as potential future approaches for this field.</p>

show abstract

Section: A Batch Normalization Techniquesmentioning

confidence: 99%

Section: E Data Augmentation Techniquesmentioning

confidence: 99%

Deep Transfer Learning Optimization Techniques for Medical Image Classifcation - A Survey

Kariuki¹,

Gikunda²,

Wandeto³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…6 U-shaped symmetric convolutional networks (CNN) models have demonstrates state-of-the-art accuracy in segmentation tasks. 7,8,9 The shifted-window (Swin) transformer 10 and MLP-Mixer 6 have also demonstrated state-ofthe-art performance in different 3D segmentation tasks. In this paper, we propose an SBP-MLP Mixer network for efficient segmentation in cardiac MRI scans.…”

Section: Introductionmentioning

confidence: 99%

Cardiac MRI segmentation using block-partitioned transformer with global-local information integration

Abouei,

Pan,

et al. 2024

Medical Imaging 2024: Clinical and Biomedical Imaging

View full text Add to dashboard Cite

In this work, we aimed to develop a deep-learning algorithm for segmentation of cardiac magnetic resonance image (MRI) to facilitate contouring of left ventricle (LV), right ventricle (RV), and Myocardium (Myo). We proposed a shifting block partition multilayer perceptron (SBP-MLP) network built upon a symmetric U-shaped encoder-decoder network. We evaluated this proposed network on a public cardiac MRI dataset, ACDC training dataset. The network performance was quantitatively evaluated using Hausdorff distance (HD), mean surface distance (MSD) and residual mean square distance (RMS) as well as Dice score coefficient, sensitivity, and precision. The performance of the proposed network was compared with two other state-of-the-art networks known as dynamic UNet and Swin-UNetr. Our proposed network achieved the following quantitative metrics as HD = 1.521±0.090 mm, MSD = 0.287±0.080 mm, RMSD = 0.738±0.315 mm. as well as Dice = 0.948±0.020, precision = 0.946±0.017, sensitivity = 0.951±0.027. The proposed network showed statistically significant improvement compared to the Swin-UNetr and dynamic UNet algorithms across most metrics for the three segments. The SBP-MLP showed superior segmentation performance, as evidenced by higher Dice score and lower HD relative to competing methods. Overall, the proposed SBP-MLP demonstrates comparable or superior performance to competing methods. This robust method has the potential for implementation in clinical workflows for cardiac segmentation and analysis.

show abstract

“…Different deep learning models have been proposed for automatic image segmentation, the majority of which have been focused on the chambers of the heart, including the LV, RV, and LA. A residual convolutional neural network was proposed to better use spatial aspects of cardiac MR data to improve cardiac segmentation accuracy (Liu et al 2020, Xu et al 2023. A fully convolutional neural network is an end-to-end pixel-wise segmentation and a variant of convolutional neural network (CNNs) aiming to achieve further improvements in segmentation performance by optimizing the network structure to enhance the feature learning capacity for segmentation and investigating different loss functions.…”

Section: Introductionmentioning

confidence: 99%

Cardiac MRI segmentation using shifted-window multilayer perceptron mixer networks

Abouei,

Pan,

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Purpose: In this work, we proposed a deep-learning segmentation algorithm for cardiac magnetic resonance imaging (MRI) to aid in contouring of the left ventricle (LV), right ventricle (RV), and Myocardium (Myo). Methods: We proposed a shifted window multilayer perceptron (Swin-MLP) mixer network which is built upon a 3D U-shaped symmetric encoder-decoder structure. We evaluated our proposed network using public data from 100 individuals. The network performance was quantitatively evaluated using 3D volume similarity between the ground truth contours and the predictions using Dice score coefficient, sensitivity, and precision as well as 2D surface similarity using Hausdorff distance (HD), mean surface distance (MSD) and residual mean square distance (RMSD). We benchmarked the performance against two other current leading edge networks known as Dynamic UNet and Swin-UNetr on the same public dataset. Results: The proposed network achieved the following volume similarity metrics when averaged over three cardiac segments: Dice = 0.952±0.017, precision = 0.948±0.016, sensitivity = 0.956±0.022. The average surface similarities were HD = 1.521±0.121 mm, MSD = 0.266±0.075 mm, and RMSD = 0.668±0.288 mm. The network shows statistically significant improvement in comparison to the Dynamic UNet and Swin-UNetr algorithms for most volumetric and surface metrics with p-value less than 0.05. Overall, the proposed Swin-MLP mixer network demonstrates better or comparable performance than competing methods. Conclusions: The proposed Swin-MLP mixer network demonstrates more accurate segmentation performance compared to current leading edge methods. This robust method demonstrates the potential to streamline clinical workflows for multiple applications.

show abstract

Deep learning-based image segmentation model using an MRI-based convolutional neural network for physiological evaluation of the heart

Cited by 5 publications

References 26 publications

Deep Transfer Learning Optimization Techniques for Medical Image Classifcation - A Survey

Deep Transfer Learning Optimization Techniques for Medical Image Classifcation - A Survey

Cardiac MRI segmentation using block-partitioned transformer with global-local information integration

Cardiac MRI segmentation using shifted-window multilayer perceptron mixer networks

Contact Info

Product

Resources

About