[论文解读] Volumetric Lung Nodule Segmentation using Adaptive ROI with Multi-View Residual Learning

Muhammad Usman, Byoung-Dai Lee+3 more|arXiv (Cornell University)|Dec 31, 2019

Lung Cancer Diagnosis and Treatment参考文献 41被引用 6

一句话总结

本文提出一种两阶段、半自动的3D肺结节分割方法，利用放射科医生提供的2D ROI，通过自适应ROI（A-ROI）和多视角残差U-Net，在冠状面、矢状面和轴向面上动态检测结节。该方法在LIDC-IDRI数据集上实现了87.55的3D分割Dice分数，优于现有最先进方法，显著减少了人工工作量，并提升了对各类结节类型的鲁棒性。

ABSTRACT

Accurate quantification of pulmonary nodules can greatly assist the early diagnosis of lung cancer, which can enhance patient survival possibilities. A number of nodule segmentation techniques have been proposed, however, all of the existing techniques rely on radiologist 3-D volume of interest (VOI) input or use the constant region of interest (ROI) and only investigate the presence of nodule voxels within the given VOI. Such approaches restrain the solutions to investigate the nodule presence outside the given VOI and also include the redundant structures into VOI, which may lead to inaccurate nodule segmentation. In this work, a novel semi-automated approach for 3-D segmentation of nodule in volumetric computerized tomography (CT) lung scans has been proposed. The proposed technique can be segregated into two stages, at the first stage, it takes a 2-D ROI containing the nodule as input and it performs patch-wise investigation along the axial axis with a novel adaptive ROI strategy. The adaptive ROI algorithm enables the solution to dynamically select the ROI for the surrounding slices to investigate the presence of nodule using deep residual U-Net architecture. The first stage provides the initial estimation of nodule which is further utilized to extract the VOI. At the second stage, the extracted VOI is further investigated along the coronal and sagittal axis with two different networks and finally, all the estimated masks are fed into the consensus module to produce the final volumetric segmentation of nodule. The proposed approach has been rigorously evaluated on the LIDC dataset, which is the largest publicly available dataset. The result suggests that the approach is significantly robust and accurate as compared to the previous state of the art techniques.

研究动机与目标

• 通过最小化放射科医生对3D体积感兴趣区域（VOI）的手动输入，减少其工作负担。
• 克服固定或放射科医生提供的VOI可能遗漏结节或包含非结节结构的局限性。
• 通过在多平面CT扫描中实现动态、自适应的结节搜索，提升分割精度。
• 开发一种稳健的半自动框架，自动估计VOI并融合多视角预测以生成最终分割结果。
• 提升对各类结节类型（包括细微、毛刺状或非附着性结节）的性能。

提出的方法

• 该方法以放射科医生提供的2D轴向ROI作为输入，启动结节检测。
• 自适应ROI（A-ROI）算法利用深度残差U-Net，在相邻轴向切片间动态调整区域大小和位置，以检测结节存在。
• 检测到的结节区域用于从CT扫描中自动提取3D VOI以进行进一步分析。
• 在VOI上应用两个额外的残差U-Net，沿冠状面和矢状面进行分块分割。
• 通过共识模块融合轴向、冠状面和矢状面的分割掩码，生成最终的3D分割结果。
• 该框架利用多视角学习，通过捕捉来自多个正交视角的结节几何特征，提升鲁棒性和精度。

实验结果

研究问题

• RQ1 半自动方法能否通过用2D ROI替代3D VOI输入，在保持高分割精度的同时减轻放射科医生负担？
• RQ2 自适应ROI学习能否提升对在初始2D ROI范围外延伸的结节的检测能力？
• RQ3 与单平面方法相比，使用轴向、冠状面和矢状面的多视角分割是否能提升3D结节边界精度？
• RQ4 共识模块能否有效融合多视角预测，生成更鲁棒、更准确的最终分割结果？
• RQ5 该方法在各类结节类型（包括细微、非附着性或毛刺状结节）上的表现如何？

主要发现

• 所提方法在LIDC-IDRI数据集上实现了87.55的平均Dice相似系数（DSC），优于以往最先进方法。
• 轴向视图分割的DSC为85.29，得益于自适应ROI和残差学习的改进。
• 共识模块显著提升了最终分割性能，使DSC从轴向视图的85.29提升至最终输出的87.55。
• 该方法成功检测到超出初始2D ROI范围的结节，自适应ROIs在切片间动态调整，完整捕获了结节范围。
• 视觉分析证实了其在具有挑战性的病例中表现稳健，包括非附着性、细微及边界模糊的结节。
• 该方法在各类结节形态上表现出强泛化能力，体现在对不同结节特征（如边缘、球形度和纹理）的性能保持一致。