arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.13574eess.IVcs.CV
收藏

医学图像神经网络中知识传递的评价

Evaluating Knowledge Transfer in Neural Network for Medical Images

Public Health Ontario(安大略省公共卫生局);University of Toronto(多伦多大学);Vector Institute(向量研究所)

Sina Akbarian, Laleh Seyyed-Kalantari, Farzad Khalvati, Elham Dolatabadi

摘要:

深度学习和知识转移技术已经渗透到医学成像领域,并被认为是彻底改变诊断成像实践的关键方法。然而,由于缺乏大量带注释的成像数据,将深度学习成功集成到医学成像任务中仍然存在挑战。为了解决这个问题,我们提出了一个师生学习框架,将知识从精心训练的卷积神经网络(CNN)教师转移到学生CNN。在这项研究中,我们探讨了知识转移在医学影像设置的性能。我们研究了当学生网络在一个小数据集(目标数据集)上训练时,以及当教师和学生的域不同时,所提出的网络的性能。CNN模型的性能在三个医学成像数据集上进行了评估,包括糖尿病视网膜病变,CheXpert和ChestX-ray 8。我们的研究结果表明,师生学习框架优于迁移学习的小成像数据集。特别地,师生学习框架将CheXpert(n= 5 k)的小样本上的CNN模型的ROC曲线下面积(AUC)提高了4%,并且将ChestX-ray 8(n=5.6k)提高了9%。除了小的训练数据大小,我们还证明了师生学习框架在医学成像环境中与迁移学习相比的明显优势。我们观察到,教师-学生网络不仅可以提高诊断性能,而且可以在数据集较小时减少过拟合。

英文摘要:

Deep learning and knowledge transfer techniques have permeated the field of medical imaging and are considered as key approaches for revolutionizing diagnostic imaging practices. However, there are still challenges for the successful integration of deep learning into medical imaging tasks due to a lack of large annotated imaging data. To address this issue, we propose a teacher-student learning framework to transfer knowledge from a carefully pre-trained convolutional neural network (CNN) teacher to a student CNN. In this study, we explore the performance of knowledge transfer in the medical imaging setting. We investigate the proposed network's performance when the student network is trained on a small dataset (target dataset) as well as when teacher's and student's domains are distinct. The performances of the CNN models are evaluated on three medical imaging datasets including Diabetic Retinopathy, CheXpert, and ChestX-ray8. Our results indicate that the teacher-student learning framework outperforms transfer learning for small imaging datasets. Particularly, the teacher-student learning framework improves the area under the ROC Curve (AUC) of the CNN model on a small sample of CheXpert (n=5k) by 4% and on ChestX-ray8 (n=5.6k) by 9%. In addition to small training data size, we also demonstrate a clear advantage of the teacher-student learning framework in the medical imaging setting compared to transfer learning. We observe that the teacher-student network holds a great promise not only to improve the performance of diagnosis but also to reduce overfitting when the dataset is small.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑