Department of Electrical Engineering, Pohang University of Science and Technology, Pohang, 37673, Republic of Korea.
Manufacturing AI Research Center, Korea Institute of Industrial Technology, Incheon, 21999, Republic of Korea.
Sci Rep. 2024 Feb 29;14(1):4981. doi: 10.1038/s41598-024-55677-3.
Developing a deep-learning-based diagnostic model demands extensive labor for medical image labeling. Attempts to reduce the labor often lead to incomplete or inaccurate labeling, limiting the diagnostic performance of models. This paper (i) constructs an attention-guiding framework that enhances the diagnostic performance of jaw bone pathology by utilizing attention information with partially labeled data; (ii) introduces an additional loss to minimize the discrepancy between network attention and its label; (iii) introduces a trapezoid augmentation method to maximize the utility of minimally labeled data. The dataset includes 716 panoramic radiograph data for jaw bone lesions and normal cases collected and labeled by two radiologists from January 2019 to February 2021. Experiments show that guiding network attention with even 5% of attention-labeled data can enhance the diagnostic accuracy for pathology from 92.41 to 96.57%. Furthermore, ablation studies reveal that the proposed augmentation methods outperform prior preprocessing and augmentation combinations, achieving an accuracy of 99.17%. The results affirm the capability of the proposed framework in fine-grained diagnosis using minimally labeled data, offering a practical solution to the challenges of medical image analysis.
开发基于深度学习的诊断模型需要对医学图像进行大量的标注工作。减少工作量的尝试往往会导致标注不完整或不准确，从而限制模型的诊断性能。本文（i）构建了一个注意力引导框架，利用部分标注数据的注意力信息来提高颌骨病理的诊断性能；（ii）引入了一个额外的损失项，以最小化网络注意力与其标签之间的差异；（iii）引入了梯形增强方法，以最大化最小标注数据的利用效率。该数据集包含了 716 张颌骨病变和正常病例的全景 X 光数据，由两位放射科医生于 2019 年 1 月至 2021 年 2 月采集和标注。实验表明，仅使用 5%的注意力标注数据引导网络注意力，就可以将病理的诊断准确率从 92.41%提高到 96.57%。此外，消融研究表明，所提出的增强方法优于之前的预处理和增强组合，达到了 99.17%的准确率。研究结果证实了该框架在使用最小标注数据进行精细诊断方面的能力，为医学图像分析的挑战提供了一种实用的解决方案。
