TG-Net: Combining transformer and GAN for nasopharyngeal carcinoma tumor segmentation based on total-body uEXPLORER PET/CT scanner

Huang, Zhengyong; Tang, Si; Chen, Zixiang; Wang, Guoshuai; Shen, Hao; Zhou, Yun; Wang, Haining; Fan, Wei; Liang, Dong; Hu, Yingying; Hu, Zhanli

doi:10.1016/j.compbiomed.2022.105869

Cited by 20 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, more precise identification of tumors often leads to more precise radiotherapy. Huang et al demonstrated that PET/CT parameters could accurately delineate the target tumor for NPC radiotherapy [ 21 ]. Altogether, we hypothesized that based on the results of PET/CT, patients may receive more accurate surgical coverage and precise radiotherapy, which could render the improved prognosis.…”

Section: Discussionmentioning

confidence: 99%

Prognostic value of pre-treatment [18F] FDG PET/CT in recurrent nasopharyngeal carcinoma without distant metastasis

Dong,

Wang,

Dai

et al. 2024

BMC Cancer

View full text Add to dashboard Cite

Background [18 F]-Fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) has the ability to detect local and/or regional recurrence as well as distant metastasis. We aimed to evaluate the prognosis value of PET/CT in locoregional recurrent nasopharyngeal (lrNPC). Methods A total of 451 eligible patients diagnosed with recurrent I-IVA (rI-IVA) NPC between April 2009 and December 2015 were retrospectively included in this study. The differences in overall survival (OS) of lrNPC patients with and without PET/CT were compared in the I-II, III-IVA, r0-II, and rIII-IVA cohorts, which were grouped by initial staging and recurrent staging (according to MRI). Results In the III-IVA and rIII-IVA NPC patients, with PET/CT exhibited significantly higher OS rates in the univariate analysis (P = 0.045; P = 0.009; respectively). Multivariate analysis revealed that with PET/CT was an independent predictor of OS in the rIII-IVA cohort (hazard ratio [HR] = 0.476; 95% confidence interval [CI]: 0.267 to 0.847; P = 0.012). In the rIII-IVA NPC, patients receiving PET/CT sacns before salvage surgery had a better prognosis compared with MRI alone (P = 0.036). The recurrent stage (based on PET/CT) was an independent predictor of OS. (r0-II versus [vs]. rIII-IVA; HR = 0.376; 95% CI: 0.150 to 0.938; P = 0.036). Conclusion The present study showed that with PET/CT could improve overall survival for rIII-IVA NPC patients. PET/CT appears to be an effective method for assessing rTNM staging.

show abstract

Section: Discussionmentioning

confidence: 99%

Prognostic value of pre-treatment [18F] FDG PET/CT in recurrent nasopharyngeal carcinoma without distant metastasis

Dong,

Wang,

Dai

et al. 2024

BMC Cancer

View full text Add to dashboard Cite

show abstract

“…A mixup was used to augment the training data, which has been shown to improve the robustness and generalization of the model (29)(30)(31). To do so, 2 individual images were mixed randomly over the network training with a certain weight:…”

Section: Data Augmentationmentioning

confidence: 99%

Attention-based dual-branch deep network for sparse-view computed tomography image reconstruction

Gao¹,

Su²,

Zhang³

et al. 2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: The widespread application of X-ray computed tomography (CT) imaging in medical screening makes radiation safety a major concern for public health. Sparse-view CT is a promising solution to reduce the radiation dose. However, the reconstructed CT images obtained using sparse-view CT may suffer severe streaking artifacts and structural information loss. Methods: In this study, a novel attention-based dual-branch end-to-end deep network based on the attention mechanism. More specifically, an attention-based dual-branch network (ADB-Net) is proposed to solve the problem of CT image reconstruction. In this network, downsampled sinogram input is processed through 2 parallel branches (CT branch and signogram branch) of the ADB-Net to independently extract the distinct, high-level feature maps. These feature maps are fused in a specified attention module from 3 perspectives (channel, plane, and spatial) to allow complementary optimizations that can mitigate the streaking artifacts and the structure loss in sparse-view CT imaging. Results: Numerical simulations, an anthropomorphic thorax phantom, and in vivo preclinical experiments were conducted to verify the sparse-view CT imaging performance of the ADB-Net. The proposed network achieved a root-mean-square error (RMSE) of 20.6160, a structural similarity (SSIM) of 0.9257, and a peak signal-to-noise ratio (PSNR) of 38.8246 on numerical data. The visualization results demonstrate that this newly developed network can consistently remove the streaking artifacts while maintaining the fine structures. Conclusions: The proposed attention-based dual-branch deep network, ADB-Net, provides a promising alternative to reconstruct high-quality sparse-view CT images for low-dose CT imaging.

show abstract

“…The expeditious development of deep learning techniques has shown the potential to overcome these limitations (17)(18)(19)(20)(21)(22). Neural networks enable the automatic extraction of features (23), which dramatically overcomes the drawbacks and outperforms traditional medical image segmentation algorithms that rely excessively on the a priori knowledge of medical experts.…”

Section: Introductionmentioning

confidence: 99%

A deep learning model based on the attention mechanism for automatic segmentation of abdominal muscle and fat for body composition assessment

Shen¹,

He²,

Ren³

et al. 2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: Quantitative muscle and fat data obtained through body composition analysis are expected to be a new stable biomarker for the early and accurate prediction of treatment-related toxicity, treatment response, and prognosis in patients with lung cancer. The use of these biomarkers can enable the adjustment of individualized treatment regimens in a timely manner, which is critical to further improving patient prognosis and quality of life. We aimed to develop a deep learning model based on attention for fully automated segmentation of the abdomen from computed tomography (CT) to quantify body composition.Methods: A fully automatic segmentation deep learning model was designed based on the attention mechanism and using U-Net as the framework. Subcutaneous fat, skeletal muscle, and visceral fat were manually segmented by two experts to serve as ground truth labels. The performance of the model was evaluated using Dice similarity coefficients (DSCs) and Hausdorff distance at 95th percentile (HD95). Results:The mean DSC for subcutaneous fat and skeletal muscle were high for both the enhanced CT test set (0.93±0.06 and 0.96±0.02, respectively) and the plain CT test set (0.90±0.09 and 0.95±0.01, respectively).Nevertheless, the model did not perform well in the segmentation performance of visceral fat, especially for the enhanced CT test set. The mean DSC for the enhanced CT test set was 0.87±0.11, while the mean DSC for the plain CT test set was 0.92±0.03. We discuss the reasons for this result.Conclusions: This work demonstrates a method for the automatic outlining of subcutaneous fat, skeletal muscle, and visceral fat areas at L3.

show abstract

TG-Net: Combining transformer and GAN for nasopharyngeal carcinoma tumor segmentation based on total-body uEXPLORER PET/CT scanner

Cited by 20 publications

References 30 publications

Prognostic value of pre-treatment [18F] FDG PET/CT in recurrent nasopharyngeal carcinoma without distant metastasis

Prognostic value of pre-treatment [18F] FDG PET/CT in recurrent nasopharyngeal carcinoma without distant metastasis

Attention-based dual-branch deep network for sparse-view computed tomography image reconstruction

A deep learning model based on the attention mechanism for automatic segmentation of abdominal muscle and fat for body composition assessment

Contact Info

Product

Resources

About