[论文解读] Transfer Learning based Detection of Diabetic Retinopathy from Small Dataset

Misgina Tsighe Hagos, Shri Kant|arXiv (Cornell University)|May 17, 2019

Retinal Imaging and Analysis被引用 82

一句话总结

本文展示了使用预训练的 Inception-V3 模型在一个较小子采样的 Kaggle 数据集上检测糖尿病视网膜病变，并解决医学影像分类中训练数据不足的问题。

ABSTRACT

Annotated training data insufficiency remains to be one of the challenges of applying deep learning in medical data classification problems. Transfer learning from an already trained deep convolutional network can be used to reduce the cost of training from scratch and to train with small training data for deep learning. This raises the question of whether we can use transfer learning to overcome the training data insufficiency problem in deep learning based medical data classifications. Deep convolutional networks have been achieving high performance results on the ImageNet Large Scale Visual Recognition Competition (ILSVRC) image classification challenge. One example is the Inception-V3 model that was the first runner up on the ILSVRC 2015 challenge. Inception modules that help to extract different sized features of input images in one level of convolution are the unique features of the Inception-V3. In this work, we have used a pretrained Inception-V3 model to take advantage of its Inception modules for Diabetic Retinopathy detection. In order to tackle the labelled data insufficiency problem, we sub-sampled a smaller version of the Kaggle Diabetic Retinopathy classification challenge dataset for model training, and tested the model's accuracy on a previously unseen data subset. Our technique could be used in other deep learning based medical image classification problems facing the challenge of labeled training data insufficiency.

研究动机与目标

• 激发深度学习在医学影像分类中标注训练数据不足的挑战。
• 提出一种使用预训练的 Inception-V3 模型进行 DR 检测的迁移学习方法。
• 证明对 Kaggle DR 数据集的较小版本进行子采样仍然可以在未见数据上获得有用的模型性能。

提出的方法

• 利用预训练的 Inception-V3 卷积神经网络，利用其 Inception 模块提取视网膜图像特征。
• 由于标注数据有限，对 Kaggle 糖尿病视网膜病变数据集进行较小版本的子采样以创建训练集。
• 在子采样数据上训练模型，并在先前未见的数据子集上评估其准确性。
• 利用迁移学习降低医学影像分类问题从零开始训练的需求。

实验结果

研究问题

• RQ1 从预训练的 Inception-V3 网络进行的迁移学习是否能够克服糖尿病视网膜病变检测中的数据不足？
• RQ2 在较小子采样的 DR 数据集上训练的模型对未见数据的泛化能力如何？
• RQ3 在低数据情形下，Inception-V3 是否适合提取用于 DR 分类的多尺度视网膜特征？

主要发现

• 可以使用一个预训练的 Inception-V3 模型在较小的数据集上应用于糖尿病视网膜病变检测。
• 在子采样数据集上进行训练并结合迁移学习，使在未见数据子集上的评估成为可能。
• 该方法展示了在其他面临标注数据限制的医学图像分类中的潜在适用性。