LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 159

Search options

  1. Article: Editorial: Advances in AI methods for computational pathology.

    Qi, Xin / Kong, Jun / Xing, Fuyong / Wang, Guotai / Zhu, Zhuotun

    Frontiers in medicine

    2022  Volume 9, Page(s) 974857

    Language English
    Publishing date 2022-09-21
    Publishing country Switzerland
    Document type Editorial
    ZDB-ID 2775999-4
    ISSN 2296-858X
    ISSN 2296-858X
    DOI 10.3389/fmed.2022.974857
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  2. Article ; Online: HAMIL: High-Resolution Activation Maps and Interleaved Learning for Weakly Supervised Segmentation of Histopathological Images.

    Zhong, Lanfeng / Wang, Guotai / Liao, Xin / Zhang, Shaoting

    IEEE transactions on medical imaging

    2023  Volume 42, Issue 10, Page(s) 2912–2923

    Abstract: Semantic segmentation of histopathological images is important for automatic cancer diagnosis, and it is challenged by time-consuming and labor-intensive annotation process that obtains pixel-level labels for training. To reduce annotation costs, Weakly ... ...

    Abstract Semantic segmentation of histopathological images is important for automatic cancer diagnosis, and it is challenged by time-consuming and labor-intensive annotation process that obtains pixel-level labels for training. To reduce annotation costs, Weakly Supervised Semantic Segmentation (WSSS) aims to segment objects by only using image or patch-level classification labels. Current WSSS methods are mostly based on Class Activation Map (CAM) that usually locates the most discriminative object part with limited segmentation accuracy. In this work, we propose a novel two-stage weakly supervised segmentation framework based on High-resolution Activation Maps and Interleaved Learning (HAMIL). First, we propose a simple yet effective Classification Network with High-resolution Activation Maps (HAM-Net) that exploits a lightweight classification head combined with Multiple Layer Fusion (MLF) of activation maps and Monte Carlo Augmentation (MCA) to obtain precise foreground regions. Second, we use dense pseudo labels generated by HAM-Net to train a better segmentation model, where three networks with the same structure are trained with interleaved learning: The agreement between two networks is used to highlight reliable pseudo labels for training the third network, and at the same time, the two networks serve as teachers for guiding the third network via knowledge distillation. Extensive experiments on two public histopathological image datasets of lung cancer demonstrated that our proposed HAMIL outperformed state-of-the-art weakly supervised and noisy label learning methods, respectively. The code is available at https://github.com/HiLab-git/HAMIL.
    MeSH term(s) Humans ; Lung Neoplasms ; Monte Carlo Method ; Semantics ; Supervised Machine Learning ; Image Processing, Computer-Assisted
    Language English
    Publishing date 2023-10-02
    Publishing country United States
    Document type Journal Article ; Research Support, Non-U.S. Gov't
    ZDB-ID 622531-7
    ISSN 1558-254X ; 0278-0062
    ISSN (online) 1558-254X
    ISSN 0278-0062
    DOI 10.1109/TMI.2023.3269798
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  3. Article ; Online: Analysis of the adsorption and fixation process of ammonium nitrogen in arable soil by biochar based on molecular dynamics simulation.

    Lu, Jikai / Li, Yan / Wang, Bing / Hou, Bingyan / Du, Guotai / Si, Hongyu

    The Science of the total environment

    2024  Volume 930, Page(s) 172815

    Abstract: The ammonia nitrogen in arable land soil is susceptible to environmental and anthropogenic influences, leading to nutrient loss. This study utilized indoor soil column leaching experiments, combined with adsorption mathematical models, traditional ... ...

    Abstract The ammonia nitrogen in arable land soil is susceptible to environmental and anthropogenic influences, leading to nutrient loss. This study utilized indoor soil column leaching experiments, combined with adsorption mathematical models, traditional characterization methods, and molecular dynamics simulation methods, to analyze the effects of biochar on changes in ammonium ions in different soil layers and leachate of arable land soil. The study found that applying biochar at a ratio of 10 % to arable land soil could effectively increase the ammonium ion content in the 0-10 cm soil layer by 1.57-2.36 times and reduce loss by 44.83-72.27 %. The adsorption and fixation process of biochar is controlled by electrostatic attraction and ion exchange processes. Interactions between molecules, electrostatic forces, and system internal energy also have certain effects on the process. Near the structure of C
    Language English
    Publishing date 2024-04-26
    Publishing country Netherlands
    Document type Journal Article
    ZDB-ID 121506-1
    ISSN 1879-1026 ; 0048-9697
    ISSN (online) 1879-1026
    ISSN 0048-9697
    DOI 10.1016/j.scitotenv.2024.172815
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  4. Article: Advancements in elucidating the pathogenesis of actinic keratosis: present state and future prospects.

    Wang, Zhongzhi / Wang, Xiaolie / Shi, Yuanyang / Wu, Siyu / Ding, Yu / Yao, Guotai / Chen, Jianghan

    Frontiers in medicine

    2024  Volume 11, Page(s) 1330491

    Abstract: Solar keratosis, also known as actinic keratosis (AK), is becoming increasingly prevalent. It is a benign tumor that develops in the epidermis. Individuals with AK typically exhibit irregular, red, scaly bumps or patches as a result of prolonged exposure ...

    Abstract Solar keratosis, also known as actinic keratosis (AK), is becoming increasingly prevalent. It is a benign tumor that develops in the epidermis. Individuals with AK typically exhibit irregular, red, scaly bumps or patches as a result of prolonged exposure to UV rays. These growths primarily appear on sun-exposed areas of the skin such as the face, scalp, and hands. Presently, dermatologists are actively studying AK due to its rising incidence rate in the United States. However, the underlying causes of AK remain poorly understood. Previous research has indicated that the onset of AK involves various mechanisms including UV ray-induced inflammation, oxidative stress, complex mutagenesis, resulting immunosuppression, inhibited apoptosis, dysregulated cell cycle, altered cell proliferation, tissue remodeling, and human papillomavirus (HPV) infection. AK can develop in three ways: spontaneous regression, persistence, or progression into invasive cutaneous squamous cell carcinoma (cSCC). Multiple risk factors and diverse signaling pathways collectively contribute to its complex pathogenesis. To mitigate the risk of cancerous changes associated with long-term UV radiation exposure, prompt identification, management, and prevention of AK are crucial. The objective of this review is to elucidate the primary mechanisms underlying AK malignancy and identify potential treatment targets for dermatologists in clinical settings.
    Language English
    Publishing date 2024-03-19
    Publishing country Switzerland
    Document type Journal Article ; Review
    ZDB-ID 2775999-4
    ISSN 2296-858X
    ISSN 2296-858X
    DOI 10.3389/fmed.2024.1330491
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  5. Article ; Online: Editorial for special issue on explainable and generalizable deep learning methods for medical image computing.

    Wang, Guotai / Zhang, Shaoting / Huang, Xiaolei / Vercauteren, Tom / Metaxas, Dimitris

    Medical image analysis

    2022  Volume 84, Page(s) 102727

    MeSH term(s) Humans ; Deep Learning ; Image Processing, Computer-Assisted/methods ; Algorithms
    Language English
    Publishing date 2022-12-08
    Publishing country Netherlands
    Document type Editorial
    ZDB-ID 1356436-5
    ISSN 1361-8423 ; 1361-8431 ; 1361-8415
    ISSN (online) 1361-8423 ; 1361-8431
    ISSN 1361-8415
    DOI 10.1016/j.media.2022.102727
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  6. Article ; Online: Small molecule inhibitors targeting m

    Feng, Guotai / Wu, Yongya / Hu, Yuan / Shuai, Wen / Yang, Xiao / Li, Yong / Ouyang, Liang / Wang, Guan

    Journal of hematology & oncology

    2024  Volume 17, Issue 1, Page(s) 30

    Abstract: As the most common form of epigenetic regulation by RNA, ... ...

    Abstract As the most common form of epigenetic regulation by RNA, N
    MeSH term(s) Humans ; Neoplasms/drug therapy ; Adenosine/analogs & derivatives ; Adenosine/metabolism ; Small Molecule Libraries/pharmacology ; Small Molecule Libraries/therapeutic use ; Antineoplastic Agents/therapeutic use ; Antineoplastic Agents/pharmacology ; Epigenesis, Genetic/drug effects ; Animals
    Chemical Substances Adenosine (K72T3FS567) ; N-methyladenosine (CLE6G00625) ; Small Molecule Libraries ; Antineoplastic Agents
    Language English
    Publishing date 2024-05-06
    Publishing country England
    Document type Journal Article ; Review ; Research Support, Non-U.S. Gov't
    ZDB-ID 2429631-4
    ISSN 1756-8722 ; 1756-8722
    ISSN (online) 1756-8722
    ISSN 1756-8722
    DOI 10.1186/s13045-024-01546-5
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  7. Article ; Online: Electrospinning/3D printing drug-loaded antibacterial polycaprolactone nanofiber/sodium alginate-gelatin hydrogel bilayer scaffold for skin wound repair.

    Song, Yongteng / Hu, Qingxi / Liu, Suihong / Wang, Yahao / Zhang, Haiguang / Chen, Jianghan / Yao, Guotai

    International journal of biological macromolecules

    2024  , Page(s) 129705

    Abstract: Skin injuries and defects, as a common clinical issue, still cannot be perfectly repaired at present, particularly large-scale and infected skin defects. Therefore, in this work, a drug-loaded bilayer skin scaffold was developed for repairing full- ... ...

    Abstract Skin injuries and defects, as a common clinical issue, still cannot be perfectly repaired at present, particularly large-scale and infected skin defects. Therefore, in this work, a drug-loaded bilayer skin scaffold was developed for repairing full-thickness skin defects. Briefly, amoxicillin (AMX) was loaded on polycaprolactone (PCL) nanofiber via electrospinning to form the antibacterial nanofiber membrane (PCL-AMX) as the outer layer of scaffold to mimic epidermis. To maintain wound wettability and promote wound healing, external human epidermal growth factor (rhEGF) was loaded in sodium alginate-gelatin to form the hydrogel structure (SG-rhEGF) via 3D printing as inner layer of scaffold to mimic dermis. AMX and rhEGF were successfully loaded into the scaffold. The scaffold exhibited excellent physicochemical properties, with elongation at break and tensile modulus were 102.09 ± 6.74 % and 206.83 ± 32.10 kPa, respectively; the outer layer was hydrophobic (WCA was 112.09 ± 4.67°), while the inner layer was hydrophilic (WCA was 48.87 ± 5.52°). Meanwhile, the scaffold showed excellent drug release and antibacterial characteristics. In vitro and in vivo studies indicated that the fabricated scaffold could enhance cell adhesion and proliferation, and promote skin wound healing, with favorable biocompatibility and great potential for skin regeneration and clinical application.
    Language English
    Publishing date 2024-01-23
    Publishing country Netherlands
    Document type Journal Article
    ZDB-ID 282732-3
    ISSN 1879-0003 ; 0141-8130
    ISSN (online) 1879-0003
    ISSN 0141-8130
    DOI 10.1016/j.ijbiomac.2024.129705
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  8. Article ; Online: FPL+: Filtered Pseudo Label-based Unsupervised Cross-Modality Adaptation for 3D Medical Image Segmentation.

    Wu, Jianghao / Guo, Dong / Wang, Guotai / Yue, Qiang / Yu, Huijun / Li, Kang / Zhang, Shaoting

    IEEE transactions on medical imaging

    2024  Volume PP

    Abstract: Adapting a medical image segmentation model to a new domain is important for improving its cross-domain transferability, and due to the expensive annotation process, Unsupervised Domain Adaptation (UDA) is appealing where only unlabeled images are needed ...

    Abstract Adapting a medical image segmentation model to a new domain is important for improving its cross-domain transferability, and due to the expensive annotation process, Unsupervised Domain Adaptation (UDA) is appealing where only unlabeled images are needed for the adaptation. Existing UDA methods are mainly based on image or feature alignment with adversarial training for regularization, and they are limited by insufficient supervision in the target domain. In this paper, we propose an enhanced Filtered Pseudo Label (FPL+)-based UDA method for 3D medical image segmentation. It first uses cross-domain data augmentation to translate labeled images in the source domain to a dual-domain training set consisting of a pseudo source-domain set and a pseudo target-domain set. To leverage the dual-domain augmented images to train a pseudo label generator, domain-specific batch normalization layers are used to deal with the domain shift while learn the domain-invariant structure features, generating high-quality pseudo labels for target-domain images. We then combine labeled source-domain images and target-domain images with pseudo labels to train a final segmentor, where image-level weighting based on uncertainty estimation and pixel-level weighting based on dual-domain consensus are proposed to mitigate the adverse effect of noisy pseudo labels. Experiments on three public multi-modal datasets for Vestibular Schwannoma, brain tumor and whole heart segmentation show that our method surpassed ten state-of-the-art UDA methods, and it even achieved better results than fully supervised learning in the target domain in some cases.
    Language English
    Publishing date 2024-04-11
    Publishing country United States
    Document type Journal Article
    ZDB-ID 622531-7
    ISSN 1558-254X ; 0278-0062
    ISSN (online) 1558-254X
    ISSN 0278-0062
    DOI 10.1109/TMI.2024.3387415
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  9. Article ; Online: Correction to: Resveratrol inhibits the expression of RYR2 and is a potential treatment for pancreatic cancer.

    Jiang, He / Wang, Guotai / Gu, Jingtao / Xiao, Ying / Wang, Pengli / Huang, Xin / Sha, Huanchen / Wang, Zheng / Ma, Qingyong

    Naunyn-Schmiedeberg's archives of pharmacology

    2023  Volume 396, Issue 7, Page(s) 1591–1593

    Language English
    Publishing date 2023-04-24
    Publishing country Germany
    Document type Published Erratum
    ZDB-ID 121471-8
    ISSN 1432-1912 ; 0028-1298
    ISSN (online) 1432-1912
    ISSN 0028-1298
    DOI 10.1007/s00210-023-02499-1
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  10. Article ; Online: Construction of ZnIn

    Sun, Guotai / Tai, Zige / Li, Fan / Ye, Qian / Wang, Ting / Fang, Zhiyu / Jia, Lichao / Liu, Wei / Wang, Hongqiang

    Small (Weinheim an der Bergstrasse, Germany)

    2023  Volume 19, Issue 27, Page(s) e2207758

    Abstract: It is facing a tremendous challenge to develop the desirable hybrids for photocatalytic ... ...

    Abstract It is facing a tremendous challenge to develop the desirable hybrids for photocatalytic H
    Language English
    Publishing date 2023-03-25
    Publishing country Germany
    Document type Journal Article
    ZDB-ID 2168935-0
    ISSN 1613-6829 ; 1613-6810
    ISSN (online) 1613-6829
    ISSN 1613-6810
    DOI 10.1002/smll.202207758
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

To top