Global and local pseudo-label filtering for semi-supervised carotid plaque classification from ultrasound
Ran Zhou1, Wei Deng1, Wenjie Yu1
1School of Computer Science and Artificial Intelligence, Hubei University of Technology, Wuhan, 430068, Hubei, China.
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.
