[论文解读] Automatic Liver Segmentation from CT Images Using Deep Learning Algorithms: A Comparative Study

K. E. Sengun, YILMAZ Çetin+3 more|arXiv (Cornell University)|Jan 25, 2021

Radiomics and Machine Learning in Medical Imaging参考文献 22被引用 7

一句话总结

本研究在商业软件'LiverVision'的标准化框架下，评估了U-Net和SegNet等深度学习架构在CT图像中自动肝脏分割的性能。结果表明，两种模型均实现了高精度，但SegNet在减少假阳性方面表现更优，证明了全自动、高精度肝脏分割在手术规划中的可行性。

ABSTRACT

Medical imaging has been employed to support medical diagnosis and treatment. It may also provide crucial information to surgeons to facilitate optimal surgical preplanning and perioperative management. Essentially, semi-automatic organ and tumor segmentation has been studied by many researchers. Recently, with the development of Deep Learning (DL) algorithms, automatic organ segmentation has been gathered lots of attention from the researchers. This paper addresses to propose the most efficient DL architectures for Liver segmentation by adapting and comparing state-of-the-art DL frameworks, studied in different disciplines. These frameworks are implemented and adapted into a Commercial software, 'LiverVision'. It is aimed to reveal the most effective and accurate DL architecture for fully automatic liver segmentation. Equal conditions were provided to all architectures in the experiments so as to measure the effectiveness of algorithms accuracy, and Dice coefficient metrics were also employed to support comparative analysis. Experimental results prove that 'U-Net' and 'SegNet' have been superior in line with the experiments conducted considering the concepts of time, cost, and effectiveness. Considering both architectures, 'SegNet' was observed to be more successful in eliminating false-positive values. Besides, it was seen that the accuracy metric used to measure effectiveness in image segmentation alone was not enough. Results reveal that DL algorithms are able to automate organ segmentation from DICOM images with high accuracy. This contribution is critical for surgical preplanning and motivates author to apply this approach to the different organs and field of medicine.

研究动机与目标

• 评估并比较最先进的深度学习架构在CT图像中自动肝脏分割的性能。
• 在相同实验条件下，将这些模型集成并适配至商业软件平台'LiverVision'中。
• 根据准确率、Dice系数、处理时间及计算成本，识别出最有效的深度学习架构。
• 评估传统准确率指标是否足以评估医学影像中的分割性能。
• 为将类似自动化分割方法应用于其他器官及医学应用奠定基础。

提出的方法

• 将最先进的深度学习模型——U-Net和SegNet——适配并集成至'LiverVision'商业软件平台中。
• 使用标准预处理和数据增强技术，在CT图像数据集上对模型进行训练与验证。
• 确保所有模型在输入归一化、分辨率和训练协议等方面保持相同的实验条件。
• 以Dice系数为主要分割性能指标，同时结合准确率和推理时间进行评估。
• 以DICOM格式的CT图像作为输入，其真实分割结果由专家手动标注。
• 采用一致的评估协议对各模型进行对比分析，确保公平的性能基准测试。

实验结果

研究问题

• RQ1 在相同条件下，U-Net与SegNet中哪种深度学习架构在肝脏CT图像分割中达到最高准确率？
• RQ2 在肝脏分割任务中，U-Net与SegNet在假阳性检测率方面有何差异？
• RQ3 与仅使用准确率相比，Dice系数在多大程度上与临床实用性相关？
• RQ4 商业软件平台能否有效集成并部署最先进的深度学习模型，以实现自动化器官分割？
• RQ5 不同深度学习架构之间，在计算成本、推理时间与分割性能之间存在何种权衡？

主要发现

• SegNet在减少假阳性分割错误方面表现优于U-Net。
• U-Net与SegNet均实现了较高的Dice系数，表明其与真实分割结果重叠度高。
• 仅使用准确率指标不足以评估分割效果，因其未考虑空间一致性或假阳性问题。
• SegNet在处理复杂肝脏边界和低对比度区域时表现出更强的泛化能力与鲁棒性。
• 本研究证实，深度学习模型可对DICOM格式的CT图像实现高精度、高可靠的肝脏自动分割。
• 将这些模型集成至'LiverVision'平台，可实现临床术前规划中的实际部署。