| 1. |
|
|
| 2. |
- Cheng, Ran, et al.
(författare)
-
In Vitro and in Vivo Evaluation of C-11-Labeled Azetidinecarboxylates for Imaging Monoacylglycerol Lipase by PET Imaging Studies
- 2018
-
Ingår i: Journal of Medicinal Chemistry. - : American Chemical Society (ACS). - 0022-2623 .- 1520-4804. ; 61:6, s. 2278-2291
-
Tidskriftsartikel (refereegranskat)abstract
- Monoacylglycerol lipase (MAGL) is the principle enzyme for metabolizing endogenous cannabinoid ligand 2-arachidonoyglycerol (2-AG). Blockade of MAGL increases 2-AG levels, resulting in subsequent activation of the endocannabinoid system, and has emerged as a novel therapeutic strategy to treat drug addiction, inflammation, and neurodegenerative diseases. Herein we report a new series of MAGL inhibitors, which were radiolabeled by site-specific labeling technologies, including C-11-carbonylation and spirocyclic iodonium ylide (SCIDY) radio fluorination. The lead compound [C-11]10 (MAGL-0519) demonstrated high specific binding and selectivity in vitro and in vivo. We also observed unexpected washout kinetics with these irreversible radiotracers, in which in vivo evidence for turnover of the covalent residue was unveiled between MAGL and azetidine carboxylates. This work may lead to new directions for drug discovery and PET tracer development based on azetidine carboxylate inhibitor scaffold.
|
|
| 3. |
- Jiang, Linhai, et al.
(författare)
-
Controlled Synthesis of CeO2/Graphene Nanocomposites with Highly Enhanced Optical and Catalytic Properties
- 2012
-
Ingår i: The Journal of Physical Chemistry C. - : American Chemical Society (ACS). - 1932-7447 .- 1932-7455. ; 116:21, s. 11741-11745
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper, CeO2 nanocubes with the (200)-terminated surface/graphene sheet composites have been prepared successfully by a simple hydrothermal method. It is found that the CeO2 nanocubes with high crystallinity and specific exposed surface are well dispersed on well-exfoliated graphene surface. The (200)-terminated surface/graphene sheet composites modified electrode showed much higher sensitivity and excellent selectivity in its catalytic performance compared to a CeO2 nanoparticle-modified electrode. The photoluminescence intensity of the CeO2 anchored on graphene is about 30 times higher than that of pristine CeO2 crystals in air. The higher oxygen vacancy concentration in CeO2 is supposed to be an important cause for the higher photoluminescence and better electrochemical catalytic performance observed in the (200)-terminated surface/graphene sheet composites. Such ingenious design of supported well-dispersed catalysts in nanostructured ceria catalysts, synthesized in one step with an exposed high-activity surface, is important for technical applications and theoretical investigations.
|
|
| 4. |
- Ran, Hang, et al.
(författare)
-
3D human pose and shape estimation via de-occlusion multi-task learning
- 2023
-
Ingår i: Neurocomputing. - Amsterdam : Elsevier. - 0925-2312 .- 1872-8286. ; 548
-
Tidskriftsartikel (refereegranskat)abstract
- Three-dimensional human pose and shape estimation is to compute a full human 3D mesh given a single image. The contamination of features caused by occlusion usually degrades its performance significantly. Recent progress in this field typically addressed the occlusion problem implicitly. By contrast, in this paper, we address it explicitly using a simple yet effective de-occlusion multi-task learning network. Our key insight is that feature for mesh parameter regression should be noiseless. Thus, in the feature space, our method disentangles the occludee that represents the noiseless human feature from the occluder. Specifically, a spatial regularization and an attention mechanism are imposed in the backbone of our network to disentangle the features into different channels. Furthermore, two segmentation tasks are proposed to supervise the de-occlusion process. The final mesh model is regressed by the disentangled occlusion-aware features. Experiments on both occlusion and non-occlusion datasets are conducted, and the results prove that our method is superior to the state-of-the-art methods on two occlusion datasets, while achieving competitive performance on a non-occlusion dataset. We also demonstrate that the proposed de-occlusion strategy is the main factor to improve the robustness against occlusion. The code is available at https://github.com/qihangran/De-occlusion_MTL_HMR. © 2023
|
|
| 5. |
- Ran, Hang, et al.
(författare)
-
Learning optimal inter-class margin adaptively for few-shot class-incremental learning via neural collapse-based meta-learning
- 2024
-
Ingår i: Information Processing & Management. - London : Elsevier. - 0306-4573 .- 1873-5371. ; 61:3
-
Tidskriftsartikel (refereegranskat)abstract
- Few-Shot Class-Incremental Learning (FSCIL) aims to learn new classes incrementally with a limited number of samples per class. It faces issues of forgetting previously learned classes and overfitting on few-shot classes. An efficient strategy is to learn features that are discriminative in both base and incremental sessions. Current methods improve discriminability by manually designing inter-class margins based on empirical observations, which can be suboptimal. The emerging Neural Collapse (NC) theory provides a theoretically optimal inter-class margin for classification, serving as a basis for adaptively computing the margin. Yet, it is designed for closed, balanced data, not for sequential or few-shot imbalanced data. To address this gap, we propose a Meta-learning- and NC-based FSCIL method, MetaNC-FSCIL, to compute the optimal margin adaptively and maintain it at each incremental session. Specifically, we first compute the theoretically optimal margin based on the NC theory. Then we introduce a novel loss function to ensure that the loss value is minimized precisely when the inter-class margin reaches its theoretically best. Motivated by the intuition that “learn how to preserve the margin” matches the meta-learning's goal of “learn how to learn”, we embed the loss function in base-session meta-training to preserve the margin for future meta-testing sessions. Experimental results demonstrate the effectiveness of MetaNC-FSCIL, achieving superior performance on multiple datasets. The code is available at https://github.com/qihangran/metaNC-FSCIL. © 2024 The Author(s)
|
|
| 6. |
- Tian, Songsong, et al.
(författare)
-
A survey on few-shot class-incremental learning
- 2024
-
Ingår i: Neural Networks. - Oxford : Elsevier. - 0893-6080 .- 1879-2782. ; 169, s. 307-324
-
Forskningsöversikt (refereegranskat)abstract
- Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental learning, focusing on introducing FSCIL from two perspectives, while reviewing over 30 theoretical research studies and more than 20 applied research studies. From the theoretical perspective, we provide a novel categorization approach that divides the field into five subcategories, including traditional machine learning methods, meta learning-based methods, feature and feature space-based methods, replay-based methods, and dynamic network structure-based methods. We also evaluate the performance of recent theoretical research on benchmark datasets of FSCIL. From the application perspective, FSCIL has achieved impressive achievements in various fields of computer vision such as image classification, object detection, and image segmentation, as well as in natural language processing and graph. We summarize the important applications. Finally, we point out potential future research directions, including applications, problem setups, and theory development. Overall, this paper offers a comprehensive analysis of the latest advances in FSCIL from a methodological, performance, and application perspective. © 2023 The Author(s)
|
|
| 7. |
- Tian, Songsong, et al.
(författare)
-
Continuous transfer of neural network representational similarity for incremental learning
- 2023
-
Ingår i: Neurocomputing. - Amsterdam : Elsevier. - 0925-2312 .- 1872-8286. ; 545
-
Tidskriftsartikel (refereegranskat)abstract
- The incremental learning paradigm in machine learning has consistently been a focus of academic research. It is similar to the way in which biological systems learn, and reduces energy consumption by avoiding excessive retraining. Existing studies utilize the powerful feature extraction capabilities of pre-trained models to address incremental learning, but there remains a problem of insufficient utilization of neural network feature knowledge. To address this issue, this paper proposes a novel method called Pre-trained Model Knowledge Distillation (PMKD) which combines knowledge distillation of neural network representations and replay. This paper designs a loss function based on centered kernel alignment to transfer neural network representations knowledge from the pre-trained model to the incremental model layer-by-layer. Additionally, the use of memory buffer for Dark Experience Replay helps the model retain past knowledge better. Experiments show that PMKD achieved superior performance on various datasets and different buffer sizes. Compared to other methods, our class incremental learning accuracy reached the best performance. The open-source code is published athttps://github.com/TianSongS/PMKD-IL. © 2023 The Author(s)
|
|
| 8. |
- Zhang, Ming-Ran, et al.
(författare)
-
Prognostic role of the lymph node ratio in node positive colorectal cancer: a meta-analysis
- 2016
-
Ingår i: Oncotarget. - : IMPACT JOURNALS LLC. - 1949-2553. ; 7:45, s. 72898-72907
-
Tidskriftsartikel (refereegranskat)abstract
- The lymph node ratio (LNR) (i. e. the number of metastatic lymph nodes divided by the number of totally resected lymph nodes) has recently emerged as an important prognostic factor in colorectal cancer (CRC). However, the tumor node metastasis (TNM) staging system for colorectal cancer does not consider it as a prognostic parameter. Therefore, we conducted a meta-analysis to evaluate the prognostic role of the LNR in node positive CRC. A systematic search was performed in PubMed, Embase and the Cochrane Library for relevant studies up to November 2015. As a result, a total of 75,838 node positive patients in 33 studies were included in this meta-analysis. Higher LNR was significantly associated with shorter overall survival (OS) (HR = 1.91; 95% CI 1.71-2.14; P = 0.0000) and disease free survival (DFS) (HR = 2.75; 95% CI: 2.14-3.53; P = 0.0000). Subgroup analysis showed similar results. Based on these results, LNR was an independent predictor of survival in colorectal cancer patients and should be considered as a parameter in future oncologic staging systems.
|
|
| 9. |
-
- 2019
-
Tidskriftsartikel (refereegranskat)
|
|
