IEEE J Biomed Health Inform. 2024 Sep;28(9):5360-5369. doi: 10.1109/JBHI.2024.3414389. Epub 2024 Sep 5.
Distinguishing Hashimoto's thyroiditis (HT) lesions from ordinary thyroid tissues is difficult with ultrasound images. Challenges in achieving high performance of HT ultrasound image classification include the low resolution, blurred features and large area of irrelevant noise. To address these problems, we propose a Feature-level Boosting Ensemble Network (FBENet) for HT ultrasound image classification. Specifically, to capture the features of suspicious HT lesions efficiently, an Ensemble Feature Boosting Module (EFBM) is introduced into the feature-level ensemble to boost the blurred features. Then, the spatial attention mechanism is adopted in backbone models to improve the feature focusing performance and representation ability. Furthermore, feature-level ensemble technique is employed in the training process to achieve more comprehensive feature representation ability. Experimentally, FBENet was trained on 6,503 HT ultrasound images, and tested on 1,626 HT ultrasound images with 82.92% accuracy and 89.24% AUC on average.
用超声图像区分桥本甲状腺炎 (HT) 病变与普通甲状腺组织较为困难。实现 HT 超声图像分类高性能面临的挑战包括低分辨率、特征模糊和大面积无关噪声。为了解决这些问题，我们提出了一种用于 HT 超声图像分类的特征级提升集成网络 (FBENet)。具体来说，为了有效地捕捉可疑 HT 病变的特征，在特征级集成中引入了一个集成特征提升模块 (EFBM)，以提升模糊特征。然后，在骨干模型中采用空间注意力机制，提高特征聚焦性能和表示能力。此外，在训练过程中采用特征级集成技术，以实现更全面的特征表示能力。实验中，FBENet 在 6503 张 HT 超声图像上进行训练，并在 1626 张 HT 超声图像上进行测试，平均准确率为 82.92%，AUC 为 89.24%。
