深度学习辅助磁共振与手术显微镜图像中脑肿瘤类型的分割与分类
本研究利用 Mask R-CNN 架构处理手术显微镜视频和术前磁共振图像,评估其对脑膜瘤、转移瘤和高别胶质瘤的分割与分类性能。Mask R-CNN Resnet101 的精确率、召回率、DICE 和 Jaccard 指数分别为 96%、93%、91% 和 84%,Resnet50 分别为 94%、89%、89% 和 82%;病理估计的 DICE 范围为 94%-95%,准确率为 98%。作者认为结果有前景,并强调多样化数据集对训练和优化深度学习模型的重要性。
要点
- Mask R-CNN Resnet101 的精确率、召回率、DICE、Jaccard 指数分别为 96%、93%、91%、84%。
- Mask R-CNN Resnet50 的精确率、召回率、DICE、Jaccard 指数分别为 94%、89%、89%、82%。
- 病理估计的 DICE 范围为 94%-95%,准确率为 98%。
核心结论
- 深度学习与神经外科手术的结合标志着医学科学的变革阶段,结果有前景,并强调多样化数据集对训练和优化这些深度学习模型的重要性。
研究设计与样本
- 研究采用 Mask R-CNN 架构,使用 Resnet101 和 Resnet50 骨干网络,处理手术显微镜视频和术前磁共振图像数据,并从磁共振成像和手术显微镜图像训练深度学习模型,将每位患者的分类结果以加权平均方式合并。
主要发现
- Mask R-CNN Resnet101 架构的精确率、召回率、DICE 和 Jaccard 指数分别为 96%、93%、91% 和 84%。
- Mask R-CNN Resnet50 架构的精确率、召回率、DICE 和 Jaccard 指数分别为 94%、89%、89% 和 82%。
- 模型在病理估计中达到 94%-95% 的 DICE 分数范围和 98% 的准确率。
- 算法在区分脑膜瘤、转移瘤和高别胶质瘤方面表现出显著能力。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVE: The primary aim of this research was to harness the capabilities of deep learning to enhance neurosurgical procedures, focusing on accurate tumor boundary delineation and classification. Through advanced diagnostic tools, we aimed to offer surgeons a more insightful perspective during surgeries, improving surgical outcomes and patient care. METHODS: The study deployed the Mask R-convolutional neural network (CNN) architecture, leveraging its sophisticated features to process and analyze data from surgical microscope videos and preoperative magnetic resonance images. Resnet101 and Resnet50 backbone networks are used in the Mask R-CNN method, and experimental results are given. We subsequently tested its performance across various metrics, such as accuracy, precision, recall, dice coefficient (DICE), and Jaccard index. Deep learning models were trained from magnetic resonance imaging and surgical microscope images, and the classification result obtained for each patient was combined with the weighted average. RESULTS: The algorithm exhibited remarkable capabilities in distinguishing among meningiomas, metastases, and high-grade glial tumors. Specifically, for the Mask R-CNN Resnet 101 architecture, precision, recall, DICE, and Jaccard index values were recorded as 96%, 93%, 91%, and 84%, respectively. Conversely, for the Mask R-CNN Resnet 50 architecture, these values stood at 94%, 89%, 89%, and 82%. Additionally, the model achieved an impressive DICE score range of 94%-95% and an accuracy of 98% in pathology estimation. CONCLUSIONS: As illustrated in our study, the confluence of deep learning with neurosurgical procedures marks a transformative phase in medical science. The results are promising but underscore diverse data sets' significance for training and refining these deep learning models.
引用
- Cekic E, Pinar E, Pinar M, et al. Deep Learning-Assisted Segmentation and Classification of Brain Tumor Types on Magnetic Resonance and Surgical Microscope Images. World Neurosurg. 2023. PMID: 38030068. doi:10.1016/j.wneu.2023.11.073
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。