Yunlong Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yunlong Gao has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Dong Liang
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
7 shared publications - Zhanli Hu
Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
7 shared publications - Hairong Zheng
Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
6 shared publications - Yongfeng Yang
Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
5 shared publications - Wenjie Zhao
Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
4 shared publications - Xinlan Yang
Central Research Institute, United Imaging Healthcare Group, Shanghai, China
4 shared publications
Latest Publications
- 22 August 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 114
Count-aware diffusion with autoregressive inference for low-count PET reconstruction enhancement
- 22 August 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 114
Count-aware diffusion with autoregressive inference for low-count PET reconstruction enhancement
- 15 June 2026
- Published by American Association for the Advancement of Science (AAAS) in Research
- Vol. 9
TNM-Accountable Whole-Body 3D FDG PET/CT Report Drafting via Structured Impressions and Organ-Wise Exemplar Synthesis
Whole-body 18 F-fluorodeoxyglucose positron emission tomography/computed tomography ( 18 F-FDG PET/CT) is central to lung cancer staging, yet report drafting remains time intensive and error sensitive, as a single mislocalized finding can alter TNM stage and treatment decisions. We cast PET/CT report drafting as TNM-accountable decision support and propose RIDE, a 2-stage dual-modality 3-dimensional framework that separates TNM-critical anchoring from narrative completion. Stage I generates TNM-oriented structured impressions from paired PET and CT volumes; stage II performs hierarchical organ-wise exemplar retrieval and prompts a large language model to synthesize complete Findings and Impression conditioned on these inspectable artifacts. We curate a multicenter whole-body FDG PET/CT cohort of 1,583 patients from 3 hospitals, all referred for suspected or confirmed lung cancer, and evaluate it on a held-out test set of 520 cases, including 276 external cases from 2 independent institutions. RIDE achieves the strongest overall drafting performance and cross-site generalization, improving a clinically grounded competency metric by +20.4 on the external set and maintaining high clinician ratings under shift (mean Likert 4.00 internal; 4.17 external) while also delivering the best TNM staging performance among evaluated baselines. These findings support workflow-decomposed, TNM-accountable PET/CT drafting as a promising decision-support approach for human verification, and prospective studies will be valuable for further characterizing its utility in real-world clinical workflows.
- 15 June 2026
- Published by American Association for the Advancement of Science (AAAS) in Research
- Vol. 9
TNM-Accountable Whole-Body 3D FDG PET/CT Report Drafting via Structured Impressions and Organ-Wise Exemplar Synthesis
Whole-body 18 F-fluorodeoxyglucose positron emission tomography/computed tomography ( 18 F-FDG PET/CT) is central to lung cancer staging, yet report drafting remains time intensive and error sensitive, as a single mislocalized finding can alter TNM stage and treatment decisions. We cast PET/CT report drafting as TNM-accountable decision support and propose RIDE, a 2-stage dual-modality 3-dimensional framework that separates TNM-critical anchoring from narrative completion. Stage I generates TNM-oriented structured impressions from paired PET and CT volumes; stage II performs hierarchical organ-wise exemplar retrieval and prompts a large language model to synthesize complete Findings and Impression conditioned on these inspectable artifacts. We curate a multicenter whole-body FDG PET/CT cohort of 1,583 patients from 3 hospitals, all referred for suspected or confirmed lung cancer, and evaluate it on a held-out test set of 520 cases, including 276 external cases from 2 independent institutions. RIDE achieves the strongest overall drafting performance and cross-site generalization, improving a clinically grounded competency metric by +20.4 on the external set and maintaining high clinician ratings under shift (mean Likert 4.00 internal; 4.17 external) while also delivering the best TNM staging performance among evaluated baselines. These findings support workflow-decomposed, TNM-accountable PET/CT drafting as a promising decision-support approach for human verification, and prospective studies will be valuable for further characterizing its utility in real-world clinical workflows.
- 1 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radiation and Plasma Medical Sciences
- Vol. 10 (3) , 391-400
Dynamic 68 Ga-PSMA Total-Body PET Dual-Parametric Imaging Based on W-Net and an Improved Diffusion Model
Dynamic positron emission tomography (PET) parametric imaging plays a crucial role in the diagnosis of and research on tumors and neurological disorders. However, it requires long-term continuous PET/CT scans, which significantly increase the complexity of imaging and have become one of the main limitations hindering its development and clinical application. To address this issue, we propose a novel approach, namely, a dynamic 68Ga-PSMA total-body PET dual parametric imaging model based on W-Net with an improved diffusion model. We construct W-Net as the backbone network of the model. The differences in the shared downsampling module s and middle layer networks, can be divided into three categories: W-Net 1, W-Net 2, and W-Net 3. Furthermore, we extend the cold diffusion model to generate single-class images to simultaneously produce dynamic 68Ga-PSMA total-body PET K1 and Ki parametric images. Compared to other methods, the K1 parametric images achieved PSNR values improvement of 0.247~4.335 dB and MSE error reduction of 0.00026~0.01288; and for Ki parametric images, PSNR and SSIM metrics were enhanced by 0.106~1.590 dB and 0.002~0.004 respectively, while MSE errors decreased by 0.00003~0.00078. The PCC (Pearson correlation coefficient) value between the generated and original images indicates that they have a strong positive correlation.
- 1 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radiation and Plasma Medical Sciences
- Vol. 10 (3) , 391-400
Dynamic 68 Ga-PSMA Total-Body PET Dual-Parametric Imaging Based on W-Net and an Improved Diffusion Model
Dynamic positron emission tomography (PET) parametric imaging plays a crucial role in the diagnosis of and research on tumors and neurological disorders. However, it requires long-term continuous PET/CT scans, which significantly increase the complexity of imaging and have become one of the main limitations hindering its development and clinical application. To address this issue, we propose a novel approach, namely, a dynamic 68Ga-PSMA total-body PET dual parametric imaging model based on W-Net with an improved diffusion model. We construct W-Net as the backbone network of the model. The differences in the shared downsampling module s and middle layer networks, can be divided into three categories: W-Net 1, W-Net 2, and W-Net 3. Furthermore, we extend the cold diffusion model to generate single-class images to simultaneously produce dynamic 68Ga-PSMA total-body PET K1 and Ki parametric images. Compared to other methods, the K1 parametric images achieved PSNR values improvement of 0.247~4.335 dB and MSE error reduction of 0.00026~0.01288; and for Ki parametric images, PSNR and SSIM metrics were enhanced by 0.106~1.590 dB and 0.002~0.004 respectively, while MSE errors decreased by 0.00003~0.00078. The PCC (Pearson correlation coefficient) value between the generated and original images indicates that they have a strong positive correlation.
- Open Access
- 2 September 2025
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 70 (17) , 175019
Reconstruction of total-body multi parametric images with shortened-duration dynamic [68Ga]Ga-PSMA-11 and [68Ga]Ga-FAPI-04 PET scans
Objective. The lengthy 1 h dynamic positron emission tomography (PET) scans discomfort patients, add motion artifacts, and inflate costs, highlighting the need for tech advancements to reduce scan times. Therefore, we attempted to reconstruct multi-parametric imaging with only 20 min dynamic PET frames through deep learning techniques. Approach. Total-body PET data from 49 subjects (18 [68Ga]Ga-FAPI-04 and 31 [68Ga]Ga-prostate-specific membrane antigen (PSMA)-11) at Renji Hospital were used. We employed the dynamic PET frames prediction, parametric linear fitting and generative adversarial network to form the whole deep learning framework accomplishing reconstruction of multi-parametric images ([68Ga]Ga-FAPI-04: K 1 , DV and v B ; [68Ga]Ga-PSMA-11: K 1 , K i and v B ) from 20 min dynamic PET frames. The peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were used to evaluate the quality of the synthesized results. Statistical analyses, including Pearson correlation coefficient (PCC) and violin plot, were also used for the reconstruction assessments. Main results. The reconstructed multi-parametric images using the proposed technique closely resembled their full-time parametric counterparts, demonstrating high image quality across various tissue types. The reconstructed images resulting from the [68Ga]Ga-FAPI-04 and [68Ga]Ga-PSMA-11 tracers outperform 5 comparison methods, yielding average PSNR values of 35.5535 dB and 36.4040 dB, along with SSIM scores of 0.9798 and 0.9630, respectively. Additionally, the PCCs within the region of interests exhibited strong correlations (above 0.92) with the ground truth. Moreover, the imaging results in the pancreatic and prostate areas matched well with full-time parametric images. Significance. Our approach shortens the scan duration of dynamic PET from above one hour to 20 min, which greatly improves the experience for patients and reduces motion artifacts and costs.
- 2 September 2025
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 70 (17) , 175019
Open AccessReconstruction of total-body multi parametric images with shortened-duration dynamic [68Ga]Ga-PSMA-11 and [68Ga]Ga-FAPI-04 PET scans
Objective. The lengthy 1 h dynamic positron emission tomography (PET) scans discomfort patients, add motion artifacts, and inflate costs, highlighting the need for tech advancements to reduce scan times. Therefore, we attempted to reconstruct multi-parametric imaging with only 20 min dynamic PET frames through deep learning techniques. Approach. Total-body PET data from 49 subjects (18 [68Ga]Ga-FAPI-04 and 31 [68Ga]Ga-prostate-specific membrane antigen (PSMA)-11) at Renji Hospital were used. We employed the dynamic PET frames prediction, parametric linear fitting and generative adversarial network to form the whole deep learning framework accomplishing reconstruction of multi-parametric images ([68Ga]Ga-FAPI-04: K 1 , DV and v B ; [68Ga]Ga-PSMA-11: K 1 , K i and v B ) from 20 min dynamic PET frames. The peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were used to evaluate the quality of the synthesized results. Statistical analyses, including Pearson correlation coefficient (PCC) and violin plot, were also used for the reconstruction assessments. Main results. The reconstructed multi-parametric images using the proposed technique closely resembled their full-time parametric counterparts, demonstrating high image quality across various tissue types. The reconstructed images resulting from the [68Ga]Ga-FAPI-04 and [68Ga]Ga-PSMA-11 tracers outperform 5 comparison methods, yielding average PSNR values of 35.5535 dB and 36.4040 dB, along with SSIM scores of 0.9798 and 0.9630, respectively. Additionally, the PCCs within the region of interests exhibited strong correlations (above 0.92) with the ground truth. Moreover, the imaging results in the pancreatic and prostate areas matched well with full-time parametric images. Significance. Our approach shortens the scan duration of dynamic PET from above one hour to 20 min, which greatly improves the experience for patients and reduces motion artifacts and costs.
- 7 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (10) , 7373-7386
Multistage Diffusion Model With Phase Error Correction for Fast PET Imaging
Fast PET imaging is clinically important for reducing motion artifacts and improving patient comfort. While recent diffusion-based deep learning methods have shown promise, they often fail to capture the true PET degradation process, suffer from accumulated inference errors, introduce artifacts, and require extensive reconstruction iterations. To address these challenges, we propose a novel multistage diffusion framework tailored for fast PET imaging. At the coarse level, we design a multistage structure to approximate the temporal non-linear PET degradation process in a data-driven manner, using paired PET images collected under different acquisition duration. A Phase Error Correction Network (PECNet) ensures consistency across stages by correcting accumulated deviations. At the fine level, we introduce a deterministic cold diffusion mechanism, which simulates intra-stage degradation through interpolation between known acquisition durations—significantly reducing reconstruction iterations to as few as 10. Evaluations on [68Ga]FAPI and [18F]FDG PET datasets demonstrate the superiority of our approach, achieving peak PSNRs of 36.2 dB and 39.0 dB, respectively, with average SSIMs over 0.97. Our framework offers high-fidelity PET imaging with fewer iterations, making it practical for accelerated clinical imaging.
- 7 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (10) , 7373-7386
Multistage Diffusion Model With Phase Error Correction for Fast PET Imaging
Fast PET imaging is clinically important for reducing motion artifacts and improving patient comfort. While recent diffusion-based deep learning methods have shown promise, they often fail to capture the true PET degradation process, suffer from accumulated inference errors, introduce artifacts, and require extensive reconstruction iterations. To address these challenges, we propose a novel multistage diffusion framework tailored for fast PET imaging. At the coarse level, we design a multistage structure to approximate the temporal non-linear PET degradation process in a data-driven manner, using paired PET images collected under different acquisition duration. A Phase Error Correction Network (PECNet) ensures consistency across stages by correcting accumulated deviations. At the fine level, we introduce a deterministic cold diffusion mechanism, which simulates intra-stage degradation through interpolation between known acquisition durations—significantly reducing reconstruction iterations to as few as 10. Evaluations on [68Ga]FAPI and [18F]FDG PET datasets demonstrate the superiority of our approach, achieving peak PSNRs of 36.2 dB and 39.0 dB, respectively, with average SSIMs over 0.97. Our framework offers high-fidelity PET imaging with fewer iterations, making it practical for accelerated clinical imaging.
- 2 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radiation and Plasma Medical Sciences
- Vol. 10 (1) , 16-25
Diffusion-Based Model for Parametric K i Generation From Total-Body Dynamic PET of Short-Duration Scan
Dynamic positron emission tomography (PET) parametric imaging typically requires a 60-minute acquisition period, causing patient discomfort and reducing clinical efficiency. This study explores the feasibility of generating parametric Ki images from 10-minute dynamic PET images acquired in the early or late scanning phases employing a multi-channel feature fusion cold sampling (MCFFCoS) framework. PET data from 103 patients are acquired using the uEXPLORER total-body PET/CT scanner during 60-minute scans. This study conducts deep learning experiments, taking early-phase or late-phase PET images as input, respectively. The generated Ki images are evaluated by visual quality and quantitative metrics, including root mean squared error (RMSE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Volumes of interest (VOIs) analysis is performed using linear regression and Bland-Altman plots. In the quantitative evaluation of total-body data, the parametric Ki images generated from late-phase PET data generally outperform those derived from early-phase data. The analysis of VOIs indicates that the appropriate scanning protocol for PET parametric imaging may vary for different body regions. The deep learning approach is able to generate high-quality parametric Ki images from 10-minute dynamic PET scans, bypassing the requirements of long acquisition time for the estimation of blood input function in kinetic modeling.
- 2 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radiation and Plasma Medical Sciences
- Vol. 10 (1) , 16-25
Diffusion-Based Model for Parametric K i Generation From Total-Body Dynamic PET of Short-Duration Scan
Dynamic positron emission tomography (PET) parametric imaging typically requires a 60-minute acquisition period, causing patient discomfort and reducing clinical efficiency. This study explores the feasibility of generating parametric Ki images from 10-minute dynamic PET images acquired in the early or late scanning phases employing a multi-channel feature fusion cold sampling (MCFFCoS) framework. PET data from 103 patients are acquired using the uEXPLORER total-body PET/CT scanner during 60-minute scans. This study conducts deep learning experiments, taking early-phase or late-phase PET images as input, respectively. The generated Ki images are evaluated by visual quality and quantitative metrics, including root mean squared error (RMSE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Volumes of interest (VOIs) analysis is performed using linear regression and Bland-Altman plots. In the quantitative evaluation of total-body data, the parametric Ki images generated from late-phase PET data generally outperform those derived from early-phase data. The analysis of VOIs indicates that the appropriate scanning protocol for PET parametric imaging may vary for different body regions. The deep learning approach is able to generate high-quality parametric Ki images from 10-minute dynamic PET scans, bypassing the requirements of long acquisition time for the estimation of blood input function in kinetic modeling.
- 18 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radiation and Plasma Medical Sciences
- Vol. 9 (8) , 1062-1073
Dual-Prompt-Enhanced Multiorgan Segmentation Model for Total-Body PET Images
Multi-organ segmentation in total-body PET images is crucial for accurately locating abnormalities and assisting in the observation of corresponding metabolic regions in the human body. Despite the emergence of numerous advanced methods in the field of multi-organ segmentation in recent years, available PET image segmentation techniques remain relatively limited. The complexity and variability of textures in PET images, the varying visibility and contrast of organs due to different metabolic activities, and the challenges posed by blurred organ boundaries in PET images all contribute to the increased difficulty of multi-organ segmentation. In this paper, we propose the Dual-Prompt Enhanced Multi-Organ Segmentation Model (DPESeg) for total-body PET image segmentation. Our approach focuses on enhancing the model’s ability to perceive organ thresholds and shapes by introducing textual and disentangled organ features, thereby improving segmentation accuracy. We validate our model on a dataset of total-body PET images obtained from 110 patients. Both visual and quantitative results demonstrate that DPESeg performs well in the multi-organ segmentation task, with a 2.02% improvement in the Dice coefficient and a 1.90% improvement in the Jaccard index compared to the best-performing comparison algorithm.
- 18 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radiation and Plasma Medical Sciences
- Vol. 9 (8) , 1062-1073
Dual-Prompt-Enhanced Multiorgan Segmentation Model for Total-Body PET Images
Multi-organ segmentation in total-body PET images is crucial for accurately locating abnormalities and assisting in the observation of corresponding metabolic regions in the human body. Despite the emergence of numerous advanced methods in the field of multi-organ segmentation in recent years, available PET image segmentation techniques remain relatively limited. The complexity and variability of textures in PET images, the varying visibility and contrast of organs due to different metabolic activities, and the challenges posed by blurred organ boundaries in PET images all contribute to the increased difficulty of multi-organ segmentation. In this paper, we propose the Dual-Prompt Enhanced Multi-Organ Segmentation Model (DPESeg) for total-body PET image segmentation. Our approach focuses on enhancing the model’s ability to perceive organ thresholds and shapes by introducing textual and disentangled organ features, thereby improving segmentation accuracy. We validate our model on a dataset of total-body PET images obtained from 110 patients. Both visual and quantitative results demonstrate that DPESeg performs well in the multi-organ segmentation task, with a 2.02% improvement in the Dice coefficient and a 1.90% improvement in the Jaccard index compared to the best-performing comparison algorithm.
- 28 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (9) , 5447-5458
MMCA-NET: A Multimodal Cross Attention Transformer Network for Nasopharyngeal Carcinoma Tumor Segmentation Based on a Total-Body PET/CT System
Nasopharyngeal carcinoma (NPC) is a malignant tumor primarily treated by radiotherapy. Accurate delineation of the target tumor is essential for improving the effectiveness of radiotherapy. However, the segmentation performance of current models is unsatisfactory due to poor boundaries, large-scale tumor volume variation, and the labor-intensive nature of manual delineation for radiotherapy. In this paper, MMCA-Net, a novel segmentation network for NPC using PET/CT images that incorporates an innovative multimodal cross attention transformer (MCA-Transformer) and a modified U-Net architecture, is introduced to enhance modal fusion by leveraging cross-attention mechanisms between CT and PET data. Our method, tested against ten algorithms via fivefold cross-validation on samples from Sun Yat-sen University Cancer Center and the public HECKTOR dataset, consistently topped all four evaluation metrics with average Dice similarity coefficients of 0.815 and 0.7944, respectively. Furthermore, ablation experiments were conducted to demonstrate the superiority of our method over multiple baseline and variant techniques. The proposed method has promising potential for application in other tasks.
- 28 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (9) , 5447-5458
MMCA-NET: A Multimodal Cross Attention Transformer Network for Nasopharyngeal Carcinoma Tumor Segmentation Based on a Total-Body PET/CT System
Nasopharyngeal carcinoma (NPC) is a malignant tumor primarily treated by radiotherapy. Accurate delineation of the target tumor is essential for improving the effectiveness of radiotherapy. However, the segmentation performance of current models is unsatisfactory due to poor boundaries, large-scale tumor volume variation, and the labor-intensive nature of manual delineation for radiotherapy. In this paper, MMCA-Net, a novel segmentation network for NPC using PET/CT images that incorporates an innovative multimodal cross attention transformer (MCA-Transformer) and a modified U-Net architecture, is introduced to enhance modal fusion by leveraging cross-attention mechanisms between CT and PET data. Our method, tested against ten algorithms via fivefold cross-validation on samples from Sun Yat-sen University Cancer Center and the public HECKTOR dataset, consistently topped all four evaluation metrics with average Dice similarity coefficients of 0.815 and 0.7944, respectively. Furthermore, ablation experiments were conducted to demonstrate the superiority of our method over multiple baseline and variant techniques. The proposed method has promising potential for application in other tasks.
- 10 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (1) , 1000-1009
Same-Radical Character Association Model in Text Classification
Research has verified that associative learning will improve learning efficiency during the process of recognizing Chinese characters. Therefore, some scholars believe that the associative information guided by radical molecules is the key to ensuring semantic understanding robustness and have incorporated it into their models. However, characters with the same radical are also often associated and widely used as contextual cues to enhance semantic understanding. This indicates that the information of the same radical has a positive effect in learning text. From the perspective of semantic complementarity between characters with the same radical, we drew inspiration and proposed a novel Same-radical Character Association Model (SCAM) for text classification in Chinese. SCAM aims to enhance model learning and training of text classification tasks by integrating same-radical characters. The model can be segmented into three processors, same radical extension processor, critical feature selection processor and cognitive and prediction processor. Experiment results shows the proposed model excels existing system in CNT, TNT and THUC databases, which indicates that integrating same-radical information will improve the Chinese text classification tasks.
- 10 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (1) , 1000-1009
Same-Radical Character Association Model in Text Classification
Research has verified that associative learning will improve learning efficiency during the process of recognizing Chinese characters. Therefore, some scholars believe that the associative information guided by radical molecules is the key to ensuring semantic understanding robustness and have incorporated it into their models. However, characters with the same radical are also often associated and widely used as contextual cues to enhance semantic understanding. This indicates that the information of the same radical has a positive effect in learning text. From the perspective of semantic complementarity between characters with the same radical, we drew inspiration and proposed a novel Same-radical Character Association Model (SCAM) for text classification in Chinese. SCAM aims to enhance model learning and training of text classification tasks by integrating same-radical characters. The model can be segmented into three processors, same radical extension processor, critical feature selection processor and cognitive and prediction processor. Experiment results shows the proposed model excels existing system in CNT, TNT and THUC databases, which indicates that integrating same-radical information will improve the Chinese text classification tasks.