DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods and obtains strong aggregate tail-class performance, particularly for Tooth Discoloration and Ulcers, indicating that DAPR improves aggregate class-balanced learning under the evaluated dataset, annotation ratio, and backbone configuration.
Abstract
Oral disease image classification can support computer-assisted assessment of intraoral images. However, obtaining large-scale annotated medical data is expensive, while real-world oral disease datasets often exhibit severe long-tailed distributions, where minority disease categories contain only limited samples. Existing semi-supervised learning methods commonly rely on fixed-threshold pseudo labels and may produce prediction distributions dominated by majority classes, resulting in class bias and pseudo-label noise accumulation under long-tailed settings. To address these issues, we propose DAPR, a Distribution-Aware and Adaptive Pseudo-Label Refinement framework for long-tailed semi-supervised oral disease classification. DAPR employs Dynamic Category Distribution Modeling (DCDM) to track the evolving prediction distribution of unlabeled samples and generate distribution-aware soft pseudo labels. A class-adaptive dynamic thresholding (CADT) mechanism was further introduced to improve minority-class sample utilization. In addition, Relation-aware Representation Learning (RRL) aligns semantic and feature relationships to enhance feature discrimination. Experiments using stratified five-fold cross-validation on a long-tailed oral disease dataset show that DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods under the evaluated setting. DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods and obtains strong aggregate tail-class performance, particularly for Tooth Discoloration and Ulcers. These results indicate that DAPR improves aggregate class-balanced learning under the evaluated dataset, annotation ratio, and backbone configuration.
Prelocalized focal liver lesion classification from multi-phase magnetic resonance imaging remains challenging in multi-center clinical practice because lesion-level annotation is limited, imaging protocols vary across institutions, and routine unlabeled data may contain categories outside the predefined training taxonomy. Existing semi-supervised methods usually assume a closed label space and can therefore be affected by unreliable pseudo-labels when unknown or weakly supported lesions appear in the unlabeled pool. These challenges are closely related to out-of-distribution (OOD) effects caused by category mismatch and clinical distribution shift. To address this problem, we propose OOD-aware Reliability Learning (ORL), a semi-supervised framework for prelocalized liver lesion classification under sparse annotation, partial label-space mismatch, and multi-center distribution shift. ORL learns a compact known-class reference manifold using Prototype-Constrained Representation Learning (PCRL), estimates sample-wise manifold support through Transport-derived Compatibility Estimation (TCE) with Asymmetric Relaxed Optimal Transport (AROT), and combines this support with classifier confidence and prototype affinity to regulate pseudo-label learning. The framework also learns an amortized reliability predictor for inference-time support scoring and reliability-based case ranking after lesion localization. We evaluated ORL on a multi-center liver magnetic resonance imaging cohort and selected retrospective stress settings, including external-center evaluation, unlabeled-pool contamination, missing-phase testing, and composite OOD-oriented score analyses. ORL improved known-category classification over representative semi-supervised baselines and maintained better performance under contamination and distribution shift. These results indicate that manifold support estimation can improve label-efficient prelocalized liver lesion classification and may improve reliability-based case ranking after lesion localization in the evaluated retrospective setting.
Yuling Pu, Wei Xia, Lin Deng et al.· Computerized Medical Imaging...· 0 citations
BACKGROUND AND OBJECTIVES
Vulnerable carotid plaques can lead to stroke or TIA; thus, classifying these plaques by ultrasound is crucial. Deep learning improves classification, but requires large labeled datasets, and expert annotation is labor-intensive. Training with limited labeled data alongside unlabeled data can boost deep learning in ultrasound plaque classification, and pseudo-label-based semi-supervised learning provides a viable approach. However, current pseudo-label-based methods overly focus on individual sample confidence, neglecting inter-sample relationships, resulting in data underutilization and imbalanced pseudo-label distribution.
METHODS
To address this issue, we propose a novel deep semi-supervised learning algorithm utilizing global and local pseudo-label filtering (GLPF) to enhance the classification of carotid ultrasound images. Global feature pseudo-label filtering uses the feature distribution of labeled samples to adjust the bias in feature extraction for unlabeled samples caused by unreliable pseudo-labels. Local feature pseudo-label filtering utilizes the local similarity between samples along with the model's confidence in predictions to provide reliable pseudo-labels for samples near the decision boundary. Furthermore, to alleviate the impact of imbalanced pseudo-label distribution, pseudo-label balance correction is proposed to dynamically adjust the learning difficulty of each class based on the number of pseudo-labels.
RESULTS
The experiments were evaluated on 1270 ultrasound carotid plaque images from Zhongnan Hospital of Wuhan University. The results demonstrate our model's superiority over advanced semi-supervised methods (i.e., MixMatch, FixMatch, FlexMatch, AdaMatch and FreeMatch) when labeled data is available at 10%, 30%, and 50% of the total.
CONCLUSIONS
These findings highlight the efficacy and precision of the GLPF algorithm in classifying carotid plaques with limited labeled training data, indicating its potential for identifying vulnerable carotid plaques in clinical practice.
Ran Zhou, Wei Deng, Wenjie Yu et al.· Comput. Methods Programs Bio...· 0 citations
LDIBR performs instance-adaptive imputation conditioned on instance features and the binary observation mask, and learns a prior, a reliability-gated correction, and entry-wise fusion weights to produce a normalized imputed distribution.
Xiang-Cheng Sun, Miaogen Ling, Han Qin et al.· 0 citations
A data-driven semi-supervised framework for imbalanced binary image classification that does not depend on data augmentation, enabling reliable utilization of unlabeled data without introducing augmentation induced noise is introduced.
M. Neethu, S. S. Vinod Chandra· International Journal of Dat...· 0 citations
This work proposes a label-free selection criterion built on SUDO, a framework for evaluating clinical AI systems without ground-truth annotations, and shows that AURCC can be used to rank a variety of vision-language models on chest X-ray classification across three inter-hospital shift scenarios, under zero-shot and MLP-probe regimes.
Juan Iñaki Larrea, L. Mansilla, Enzo Ferrante· 0 citations
Experiments show that IRRL achieves balanced classification performance, with favorable F1-score and Matthews Correlation Coefficient results that reflect improved minority-class recognition quality, and robustness and consistency of the proposed representation learning strategy.
M. Cheng, C. Liu, L. Gu· medRxiv· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
