论文标题
使用ImageNet对医学图像分析的转移学习研究的范围审查
A scoping review of transfer learning research on medical image analysis using ImageNet
论文作者
论文摘要
目的：使用卷积神经网络（CNN）采用转移学习（TL），在非医疗图像数据集上进行了良好培训，近年来显示了医学图像分析的有希望的结果。我们旨在进行范围审查，以确定这些研究并根据问题描述，输入，方法论和结果总结它们的特征。材料和方法：搜索相关研究，MEDLINE，IEEE和ACM数字库。两名研究人员独立审查了文章，以确定资格并根据研究方案定义了先验的数据。结果：筛选了8,421篇文章后，有102篇符合纳入标准。在22个解剖区域（18％），乳房（14％）和大脑（12％）的研究中，有最常见的研究。在72％的微调TL研究中，与特征提取的TL研究的15％进行了数据增强。 Inception模型是与乳房相关的研究中最常用的（50％），而VGGNET在眼睛（44％），皮肤（50％）和牙齿（57％）研究中是常见的。最常用的模型是肺部研究的Alexnet（42％）和Densenet（38％）。成立模型是分析超声（55％），内窥镜检查（57％）和骨骼系统X射线（57％）的最常用于研究的研究。 VGGNET是眼底最常见的（42％）和光学相干断层扫描图像（50％）。 Alexnet是脑MRI（36％）和乳房X射线（50％）的最常见模型。 35％的研究将其模型与其他训练有素的CNN模型进行了比较，其中33％提供了可视化的解释。讨论：本研究确定了用于数据制备，方法论选择和输出评估的文献中最普遍的实施轨道。此外，我们确定了医学图像分析研究中存在的一些关键研究差距。
Objective: Employing transfer learning (TL) with convolutional neural networks (CNNs), well-trained on non-medical ImageNet dataset, has shown promising results for medical image analysis in recent years. We aimed to conduct a scoping review to identify these studies and summarize their characteristics in terms of the problem description, input, methodology, and outcome. Materials and Methods: To identify relevant studies, MEDLINE, IEEE, and ACM digital library were searched. Two investigators independently reviewed articles to determine eligibility and to extract data according to a study protocol defined a priori. Results: After screening of 8,421 articles, 102 met the inclusion criteria. Of 22 anatomical areas, eye (18%), breast (14%), and brain (12%) were the most commonly studied. Data augmentation was performed in 72% of fine-tuning TL studies versus 15% of the feature-extracting TL studies. Inception models were the most commonly used in breast related studies (50%), while VGGNet was the common in eye (44%), skin (50%) and tooth (57%) studies. AlexNet for brain (42%) and DenseNet for lung studies (38%) were the most frequently used models. Inception models were the most frequently used for studies that analyzed ultrasound (55%), endoscopy (57%), and skeletal system X-rays (57%). VGGNet was the most common for fundus (42%) and optical coherence tomography images (50%). AlexNet was the most frequent model for brain MRIs (36%) and breast X-Rays (50%). 35% of the studies compared their model with other well-trained CNN models and 33% of them provided visualization for interpretation. Discussion: This study identified the most prevalent tracks of implementation in the literature for data preparation, methodology selection and output evaluation for medical image analysis. Also, we identified several critical research gaps existing in the TL studies on medical image analysis.
