Rustom Faris, Moroze Ezekiel, Parva Pedram, Ogmen Haluk, Yazdanbakhsh Arash
Computational Neuroscience and Vision Lab, Neuroscience Program, Boston University, Boston, MA, 02215, USA.
Department of Radiology, VA Boston Healthcare System, Boston, MA, 02132, USA.
Biol Methods Protoc. 2024 Nov 19;9(1):bpae080. doi: 10.1093/biomethods/bpae080. eCollection 2024.
Convolutional neural networks (CNNs) are powerful tools that can be trained on image classification tasks and share many structural and functional similarities with biological visual systems and mechanisms of learning. In addition to serving as a model of biological systems, CNNs possess the convenient feature of transfer learning where a network trained on one task may be repurposed for training on another, potentially unrelated, task. In this retrospective study of public domain MRI data, we investigate the ability of neural network models to be trained on brain cancer imaging data while introducing a unique camouflage animal detection transfer learning step as a means of enhancing the networks' tumor detection ability. Training on glioma and normal brain MRI data, post-contrast T1-weighted and T2-weighted, we demonstrate the potential success of this training strategy for improving neural network classification accuracy. Qualitative metrics such as feature space and DeepDreamImage analysis of the internal states of trained models were also employed, which showed improved generalization ability by the models following camouflage animal transfer learning. Image saliency maps further this investigation by allowing us to visualize the most important image regions from a network's perspective while learning. Such methods demonstrate that the networks not only 'look' at the tumor itself when deciding, but also at the impact on the surrounding tissue in terms of compressions and midline shifts. These results suggest an approach to brain tumor MRIs that is comparable to that of trained radiologists while also exhibiting a high sensitivity to subtle structural changes resulting from the presence of a tumor.
卷积神经网络（CNNs）是强大的工具，可用于图像分类任务的训练，并且在结构和功能上与生物视觉系统及学习机制有许多相似之处。除了作为生物系统的模型外，卷积神经网络还具有迁移学习的便利特性，即在一项任务上训练的网络可重新用于另一项可能不相关的任务的训练。在这项对公共领域MRI数据的回顾性研究中，我们研究了神经网络模型在脑癌成像数据上进行训练的能力，同时引入了一个独特的伪装动物检测迁移学习步骤，以此作为增强网络肿瘤检测能力的一种手段。我们在胶质瘤和正常脑MRI数据（增强后T1加权和T2加权）上进行训练，证明了这种训练策略在提高神经网络分类准确率方面的潜在成功。我们还采用了定性指标，如对训练模型内部状态的特征空间和深度梦境图像分析，结果表明模型在伪装动物迁移学习后具有更好的泛化能力。图像显著性图通过让我们在学习过程中从网络的角度可视化最重要的图像区域，进一步推动了这项研究。这些方法表明，网络在做出决策时不仅“查看”肿瘤本身，还会考虑肿瘤对周围组织在压迫和中线移位方面的影响。这些结果表明了一种针对脑肿瘤MRI的方法，该方法与训练有素的放射科医生的方法相当，同时对肿瘤存在导致的细微结构变化也具有高敏感性。
