Discover Community Create You

Loading publication...

Noodle always counts identifier-free feature events for service operation. With your permission, Google Analytics can also estimate audience and engagement. Search text, publication identifiers, cookies, IP addresses and browser fingerprints are never included in Noodle's first-party event counters.

Privacy details

Article

Decomposition based curriculum-style self-training for source-free universal domain adaptation in computational pathology.

Neural networks : the official journal of the International Neural Network Society - 1 Aug 2026

Liu Wentao, Ni Zhiwei, Zhu Xuhui, Chen Qian, Ni Liping, Xia Pingfan

Abstract excerpt

Computational pathology models serve as crucial tools for clinical tasks such as tissue typing, alleviating the burden of manual screening of whole slide images. The stringent ethical regulations on source data, along with agnostic covariate and label co-shifts, substantially hinder the cross-institute deployment. In this dilemma, recently emerging source-free universal domain adaptation (SF-UniDA) aims to...

Read the complete abstract on PubMed

Topics

Share this publication in a Topic to start or enrich a Post.

Share to Clustering Algorithms
Share to Colorectal Neoplasms

Methodology Data sources Editorial policy Privacy About Contact Helena Bioinformatics

Share to Machine Learning

Share to Neural Networks, Computer

Share to Normal Distribution

Share to Phenotype

Source

Identifiers

PMID: 41807903
DOI: 10.1016/j.neunet.2026.108805

Provenance

PubMed metadata and Literature Corpus relationships. Corpus snapshot updated 8 Sept 2026.

Related research

Semantic proximity does not establish scientific evidence.

Research trail→

Click a neighbor to travelStep 1 · 12 closest

Decomposition based curriculum-style self-training for source-free universal domain adaptation in computational pathology.PMID 41807903Read ↗

Cluster-based histopathology phenotype representation learning by self-supervised multi-class-token hierarchical ViT.Semantic proximity Read ↗

Hybrid unsupervised representation learning and pseudo-label supervised self-distillation for rare disease imaging phenotype classification with dispersion-aware imbalance correction.Semantic proximity Read ↗

Flexible and Highly-Efficient Feature Perception for Molecular Traits Prediction via Self-interactive Deep LearningSemantic proximity Read ↗

A foundation model for generalizable cancer diagnosis and survival prediction from histopathological imagesSemantic proximity Read ↗

Cracks in the Foundation: How Data-Hungry and Sensitive to Domain Shift are Vision Foundation Models for Computational Pathology?Semantic proximity Read ↗

M4: Multi-proxy multi-gate mixture of experts network for multiple instance learning in histopathology image analysis.Semantic proximity Read ↗

Prediction of microsatellite instability in colorectal cancer based on tissue phenotypes inferred from pathological whole slide images using self-distillation.Semantic proximity Read ↗

Learning Interpretable Microscopic Features of Tumor by Multi-task Adversarial CNNs Improves GeneralizationSemantic proximity Read ↗

Image model embeddings for digital pathology and drug development via self-supervised learningSemantic proximity Read ↗

Histopathological Domain Adaptation with Generative Adversarial Networks Bridging the Domain Gap Between Thyroid Cancer Histopathology DatasetsSemantic proximity Read ↗

A Survey of Generalization and Adaptation in Medical Imaging Foundation ModelsSemantic proximity Read ↗

Patch-level phenotype identification via weakly supervised neuron selection in sparse autoencoders for CLIP-derived pathology embeddings.Semantic proximity Read ↗

⌁Select a neighboring publication to make it the new centre.