An innovative medical image synthesis based on dual GAN deep neural networks for improved segmentation quality

Beji, Ahmed; Blaiech, Ahmed Ghazi; Said, Mourad; Abdallah, Asma Ben; Bedoui, Mohamed Hédi

doi:10.1007/s10489-022-03682-2

Cited by 9 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the wide application of Generative Adversarial Networks (GAN) in image generation (Skandarani et al, 2023), these problems are expected to be solved. In recent years GAN has been widely used in medical image tasks such as image segmentation (Beji et al, 2023;Dash et al, 2023;Skandarani et al, 2023;Zhong et al, 2023), lesion classification (Chen et al, 2023;Fan et al, 2023), and lesion detection (Esmaeili et al, 2023;Vyas & Rajendran, 2023). And the study of GAN in medical image synthesis tasks has dominated.…”

Section: Introductionmentioning

confidence: 99%

NC2C-TransCycleGAN: Non-Contrast to Contrast-Enhanced CT Image Synthesis Using Transformer CycleGAN

Hou,

Liu,

Zhang

et al. 2024

View full text Add to dashboard Cite

Background: Lung cancer poses a great threat to human life and health. Although the density differences between lesions and normal tissues shown on enhanced CT images is very helpful for doctors to characterize and detect lesions, contrast agents and radiation may cause harm to the health of patients with lung cancer. By learning the mapping relationship between plain CT image and enhanced CT image through deep learning methods, high quality synthetic CECT image results can be generated based on plain scan CT image. It has great potential to help save treatment time and cost of lung cancer patients, reduce radiation dose and expand the medical image dataset in the field of deep learning. Methods: In this study, plain and enhanced CT images of 71 lung cancer patients were retrospectively collected. The data from 58 lung cancer patients were randomly assigned to the training set, and the other 13 cases formed the test set. The Convolution Vison Transformer structure and PixelShuffle operation were combined with CycleGAN, respectively, to help generate clearer images. After random erasing, image scaling and flipping to enhance the training data, paired plain and enhanced CT slices of each patient are input into the network as input and labeled, respectively, for model training.Finally, the peak signal-to-noise ratio, structural similarity and mean square error are used to evaluate the image quality and similarity. Results: The performance of our proposed method is compared with CycleGAN and Pix2Pix on the test set, respectively. The results show that the SSIM value of the enhanced CT images generated by the proposed method improve by 2.00% and 1.39%, the PSNR values improve by 2.05% and 1.71%, and the MSE decreases by 12.50% and 8.53%, respectively, compared with Pix2Pix and CycleGAN. Conclusions: The experimental results show that the improved algorithm based on CylceGAN proposed in this paper can synthesize high-quality lung cancer synthetic enhanced CT images, which is helpful to expand the lung cancer image data set in the deep learning research. More importantly, this method can help lung cancer patients save medical treatment time and cost.

show abstract

Section: Introductionmentioning

confidence: 99%

NC2C-TransCycleGAN: Non-Contrast to Contrast-Enhanced CT Image Synthesis Using Transformer CycleGAN

Hou,

Liu,

Zhang

et al. 2024

View full text Add to dashboard Cite

show abstract

“…However, existing research methods have many defects and shortcomings. On one hand, traditional image segmentation methods often fail to effectively process images in complex backgrounds, and cannot effectively recognize and segment key features of the images [29][30][31][32]. On the other hand, existing GANs may encounter issues such as low quality of generated images and unstable model training when dealing with image segmentation in complex backgrounds.…”

Section: Introductionmentioning

confidence: 99%

Image Segmentation in Complex Backgrounds using an Improved Generative Adversarial Network

Wang,

Zhang

2024

ijacsa

View full text Add to dashboard Cite

As technologyadvances, solving image segmentation challenges in complex backgrounds has become a key issue across various fields. Traditional image segmentation methods underperform in addressing these challenges, and existing generative adversarial networks (GANs) also face several problems when applied in complex environments, such as low generation quality and unstable model training. To address these issues, this study introduces an improved GAN approach for image segmentation in complex backgrounds. This method encompasses preprocessing of complex background image datasets, feature reduction encoding based on cerebellar neural networks, image data augmentation in complex backgrounds, and the application of an improved GAN. In this paper, new generator and discriminator network structures are designed and image data enhancement is implemented through self-play learning. Experimental results demonstrate significant improvements in image segmentation tasks in various complex backgrounds, enhancing the accuracy and robustness of segmentation. This research offers new insights and methodologies for image processing in complex backgrounds, holding substantial theoretical and practical significance.

show abstract

“…Pathologists play a key role in this process. Although data annotation can be metic-ulous, computer-aided diagnosis based on deep learning significantly improves the diagnostic efficiency of pathologists [6]. The analysis of images of different diseases can further improve the efficiency of computer-aided diagnosis [7] [8].…”

Section: Introductionmentioning

confidence: 99%

Breast Cancer Histopathology Images Classification Through Multi-View Augmented Contrastive Learning and Pre-Learning Knowledge Distillation

Si,

Jia,

Jiang

2024

IEEE Access

View full text Add to dashboard Cite

Breast cancer is one of the most common malignant tumors in women, and accurate classification of benign and malignant breast cancer histopathology images is critical for diagnosis and treatment. Knowledge distillation techniques have recently received considerable attention for enabling cost-effective image classification of breast cancer histopathology images. However, there are still challenges, including the inefficient extraction of global and local features from breast cancer histopathology images by the teacher network, and the over-prioritization of feature fusion within the same encoder layer, which tends to neglect valuable information from adjacent encoder layers during knowledge extraction. To address these challenges, we propose a method that combines multi-view augmented contrastive learning and pre-learning knowledge distillation. Multi-view augmented contrastive learning improves the ability of the teacher network to extract global and local features. Pre-learning knowledge distillation merges features from adjacent encoder layers of the teacher network, reducing feature loss between these layers. Empirical experiments demonstrate the effectiveness of our proposed method in classifying histopathology images of benign and malignant breast cancer, achieving excellent results on the BreakHis dataset. These results confirm our method as an effective tool for the classification of benign and malignant breast cancer histopathology images.INDEX TERMS Knowledge distillation, contrastive learning, breast cancer histopathology image, global feature, local feature.

show abstract

An innovative medical image synthesis based on dual GAN deep neural networks for improved segmentation quality

Cited by 9 publications

References 29 publications

NC2C-TransCycleGAN: Non-Contrast to Contrast-Enhanced CT Image Synthesis Using Transformer CycleGAN

NC2C-TransCycleGAN: Non-Contrast to Contrast-Enhanced CT Image Synthesis Using Transformer CycleGAN

Image Segmentation in Complex Backgrounds using an Improved Generative Adversarial Network

Breast Cancer Histopathology Images Classification Through Multi-View Augmented Contrastive Learning and Pre-Learning Knowledge Distillation

Contact Info

Product

Resources

About