Tang Yutao, Guo Yongze, Wang Huayu, Song Ting, Lu Yao
School of Computer Science and Engineering, Sun-Yat sen University, Guanghzou 510006, China.
The Third Affiliated Hospital of Guangzhou Medical University, Guanghzou 510150, China.
Bioengineering (Basel). 2025 Jan 6;12(1):36. doi: 10.3390/bioengineering12010036.
The consistency regularization method is a widely used semi-supervised method that uses regularization terms constructed from unlabeled data to improve model performance. Poor-quality target predictions in regularization terms produce noisy gradient flows during training, resulting in a degradation in model performance. Recent semi-supervised methods usually filter out low-confidence target predictions to alleviate this problem, but also prevent the model from learning features from unlabeled data in low-confidence regions. Specifically, in medical imaging and other cross-domain scenarios, models are prone to producing large numbers of low-confidence predictions. To improve the quality of target predictions while utilizing unlabeled data more efficiently, we propose an uncertainty-aware semi-supervised method that incorporates the breast anatomical prior, for pectoral muscle segmentation. Our method has a typical teacher-student dual model structure, where uncertainty is used to distinguish between high- and low-confidence predictions in the teacher model output. A low-confidence prediction refinement module was designed to refine the low-confidence predictions by incorporating high-confidence predictions and a learned anatomical prior. The anatomical prior, as regularization of the target predictions, was learned from annotations and an auxiliary task. The final target predictions are a combination of high-confidence teacher predictions and refined low-confidence predictions. The proposed method was evaluated on a dataset containing 635 data points from three data centers. Compared with the baseline method, the proposed method showed an average improvement in DICE index of 1.76, an average reduction in IoU index of 3.21, and an average reduction in HD index of 5.48. The experimental results show that our method generalizes well to the test set and outperforms other methods in all evaluation metrics.
一致性正则化方法是一种广泛使用的半监督方法，它使用从未标记数据构建的正则化项来提高模型性能。正则化项中质量较差的目标预测在训练期间会产生有噪声的梯度流，导致模型性能下降。最近的半监督方法通常会过滤掉低置信度的目标预测以缓解此问题，但这也会阻止模型从未标记数据的低置信度区域学习特征。具体而言，在医学成像和其他跨域场景中，模型容易产生大量低置信度预测。为了在更有效地利用未标记数据的同时提高目标预测的质量，我们提出了一种不确定性感知半监督方法，该方法结合了乳房解剖学先验知识用于胸肌分割。我们的方法具有典型的师生双模型结构，其中不确定性用于区分教师模型输出中的高置信度和低置信度预测。设计了一个低置信度预测细化模块，通过合并高置信度预测和学习到的解剖学先验知识来细化低置信度预测。解剖学先验知识作为目标预测的正则化项，是从注释和辅助任务中学习得到的。最终的目标预测是高置信度教师预测和细化后的低置信度预测的组合。该方法在一个包含来自三个数据中心的635个数据点的数据集上进行了评估。与基线方法相比，该方法的DICE指数平均提高了1.76，IoU指数平均降低了3.21，HD指数平均降低了5.48。实验结果表明，我们的方法在测试集上具有良好的泛化能力，并且在所有评估指标上均优于其他方法。
