Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Revisiting weakly supervised tabular anomaly detection from a cell-level perspective.

Jiahui Wang1, Zhen Peng1, Xujing Jia1

  • 1School of Computer Science and Technology, Xi'an Jiaotong University, China.

Neural Networks : the Official Journal of the International Neural Network Society
|June 4, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Overview Of Cell Separation And Isolation01:20

Overview Of Cell Separation And Isolation

Cell separation was first achieved in 1964 by S. H. Seal, who separated large tumor cells from the smaller blood cells using filtration. Two years later, Pohl and Hawk performed experiments on how cells respond differently to a nonuniform electric field based on the cell type. Such observations were the inception of cell separation methods, which allow isolating a single cell type from a heterogeneous sample.
Cellular Adaptation IV: Dysplasia and Metaplasia01:24

Cellular Adaptation IV: Dysplasia and Metaplasia

DysplasiaDysplasia refers to abnormal changes in the size, shape, and organization of mature cells, characterized by pleomorphism, nuclear abnormalities, and increased mitotic activity. It commonly affects epithelial tissues, including the cervix, gastrointestinal tract, respiratory mucosa, and endometrium. Although it may occur alongside hyperplasia, dysplasia is not a true adaptive response but a preneoplastic change with potential to progress to cancer.When confined above the basement...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Modulation of smoker brain activity and functional connectivity by tDCS: A go/no-go task-state fMRI study.

Heliyon·2023
Same author

The main strategies for soil pollution apportionment: A review of the numerical methods.

Journal of environmental sciences (China)·2023
Same author

<i>Bacillus velezensis</i> ZN-S10 Reforms the Rhizosphere Microbial Community and Enhances Tomato Resistance to TPN.

Plants (Basel, Switzerland)·2023
Same author

Effect of optimized thrombus aspiration on myocardial perfusion and prognosis in acute ST-segment elevation myocardial infarction patients with primary percutaneous coronary intervention.

Frontiers in cardiovascular medicine·2023
Same author

Erratum: [Corrigendum] Effects of histone deacetylase inhibitors on ATP‑binding cassette transporters in lung cancer A549 and colorectal cancer HCT116 cells.

Oncology letters·2023
Same author

Sulforaphene Inhibits Periodontitis through Regulating Macrophage Polarization <i>via</i> Upregulating Dendritic Cell Immunoreceptor.

Journal of agricultural and food chemistry·2023
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces Trail, a new framework for cell anomaly detection in tabular data. Trail identifies specific abnormal cells, offering a more detailed understanding of data anomalies than traditional sample-level methods.

Area of Science:

  • Data Science
  • Machine Learning

Background:

  • Weakly supervised tabular anomaly detection leverages limited labels and abundant unlabeled data.
  • Existing methods focus on sample-level anomaly detection, lacking cell-specific insights.
  • Tabular data's cell structure offers potential for finer-grained anomaly identification.

Purpose of the Study:

  • To shift tabular anomaly detection from sample-level to cell-level analysis.
  • To develop a weakly supervised framework for cell anomaly detection.
  • To quantify abnormality at the individual cell level, even with imprecise sample-level labels.

Main Methods:

  • Proposed a novel weakly supervised framework named Trail.
  • Employed adaptive sparse topology learning and masked tabular modeling for discriminative representations.
Keywords:
Tabular anomaly detectionWeakly supervised learning

Related Experiment Videos

  • Utilized multiple instance learning (MIL) to score deviant cells in abnormal samples.

    • Main Results:

    • Trail quantifies abnormality at the cell level, moving beyond sample-level scores.
    • Achieved effectiveness across ten benchmark datasets, validated by AUC-ROC and AUC-PR metrics.
    • Demonstrated intuitive comprehension of tabular anomalies at the cell granularity.

    Conclusions:

    • Trail advances fine-grained cell anomaly detection in tabular data.
    • The framework provides interpretable insights into anomaly locations and severity.
    • Encourages future research in cell anomaly detection and annotated dataset development.