Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China.
Department of Neurosurgery, Cologne Medical Center, University Witten, Cologne, Germany.
Int J Comput Assist Radiol Surg. 2018 Aug;13(8):1187-1199. doi: 10.1007/s11548-018-1806-7. Epub 2018 Jun 13.
Probe-based confocal laser endomicroscopy (pCLE) enables in vivo, in situ tissue characterisation without changes in the surgical setting and simplifies the oncological surgical workflow. The potential of this technique in identifying residual cancer tissue and improving resection rates of brain tumours has been recently verified in pilot studies. The interpretation of endomicroscopic information is challenging, particularly for surgeons who do not themselves routinely review histopathology. Also, the diagnosis can be examiner-dependent, leading to considerable inter-observer variability. Therefore, automatic tissue characterisation with pCLE would support the surgeon in establishing diagnosis as well as guide robot-assisted intervention procedures.
The aim of this work is to propose a deep learning-based framework for brain tissue characterisation for context aware diagnosis support in neurosurgical oncology. An efficient representation of the context information of pCLE data is presented by exploring state-of-the-art CNN models with different tuning configurations. A novel video classification framework based on the combination of convolutional layers with long-range temporal recursion has been proposed to estimate the probability of each tumour class. The video classification accuracy is compared for different network architectures and data representation and video segmentation methods.
We demonstrate the application of the proposed deep learning framework to classify Glioblastoma and Meningioma brain tumours based on endomicroscopic data. Results show significant improvement of our proposed image classification framework over state-of-the-art feature-based methods. The use of video data further improves the classification performance, achieving accuracy equal to 99.49%.
This work demonstrates that deep learning can provide an efficient representation of pCLE data and accurately classify Glioblastoma and Meningioma tumours. The performance evaluation analysis shows the potential clinical value of the technique.
基于探针的共聚焦激光内窥镜检查（pCLE）能够在不改变手术环境的情况下对体内原位组织进行特征分析，并简化肿瘤外科手术流程。最近的试点研究证实了该技术在识别残留癌组织和提高脑肿瘤切除率方面的潜力。然而，内窥镜信息的解读具有挑战性，特别是对于那些本身不常规审查组织病理学的外科医生而言。此外，诊断可能依赖于检查者，从而导致相当大的观察者间变异性。因此，pCLE 的自动组织特征分析将支持外科医生做出诊断，并指导机器人辅助干预程序。
本研究旨在提出一种基于深度学习的脑实质特征分析框架，以便为神经外科肿瘤学中的上下文感知诊断提供支持。通过探索具有不同调整配置的最先进的 CNN 模型，提出了一种有效的 pCLE 数据上下文信息表示方法。提出了一种基于卷积层与长程时间递归相结合的新型视频分类框架，以估计每个肿瘤类别的概率。比较了不同网络架构、数据表示和视频分割方法的视频分类准确性。
我们展示了所提出的深度学习框架在基于内窥镜数据对脑胶质瘤和脑膜瘤进行分类的应用。结果表明，我们提出的图像分类框架明显优于最先进的基于特征的方法。使用视频数据进一步提高了分类性能，达到了 99.49%的准确率。
这项工作表明，深度学习可以为 pCLE 数据提供有效的表示，并准确地对脑胶质瘤和脑膜瘤进行分类。性能评估分析显示了该技术的潜在临床价值。
