Vanderbilt University, 2301 Vanderbilt Place, Nashville, 37235, United States.
Vanderbilt University, 2301 Vanderbilt Place, Nashville, 37235, United States.
Med Image Anal. 2023 Aug;88:102852. doi: 10.1016/j.media.2023.102852. Epub 2023 May 27.
Field-of-view (FOV) tissue truncation beyond the lungs is common in routine lung screening computed tomography (CT). This poses limitations for opportunistic CT-based body composition (BC) assessment as key anatomical structures are missing. Traditionally, extending the FOV of CT is considered as a CT reconstruction problem using limited data. However, this approach relies on the projection domain data which might not be available in application. In this work, we formulate the problem from the semantic image extension perspective which only requires image data as inputs. The proposed two-stage method identifies a new FOV border based on the estimated extent of the complete body and imputes missing tissues in the truncated region. The training samples are simulated using CT slices with complete body in FOV, making the model development self-supervised. We evaluate the validity of the proposed method in automatic BC assessment using lung screening CT with limited FOV. The proposed method effectively restores the missing tissues and reduces BC assessment error introduced by FOV tissue truncation. In the BC assessment for large-scale lung screening CT datasets, this correction improves both the intra-subject consistency and the correlation with anthropometric approximations. The developed method is available at https://github.com/MASILab/S-EFOV.
视野（FOV）组织截断超出肺部在常规肺部筛查 CT 中很常见。这对基于 CT 的机会性身体成分（BC）评估构成了限制，因为关键的解剖结构缺失。传统上，通过使用有限的数据扩展 CT 的 FOV 被认为是 CT 重建问题。然而，这种方法依赖于投影域数据，而在应用中可能无法获得这些数据。在这项工作中，我们从语义图像扩展的角度来表述这个问题，该方法只需要图像数据作为输入。所提出的两阶段方法基于对完整身体的估计范围来确定新的 FOV 边界，并对截断区域中缺失的组织进行插补。使用 FOV 中具有完整身体的 CT 切片模拟训练样本，使模型开发具有自监督性。我们评估了所提出的方法在使用有限 FOV 的肺部筛查 CT 中进行自动 BC 评估的有效性。所提出的方法有效地恢复了缺失的组织，并减少了 FOV 组织截断引起的 BC 评估误差。在大规模肺部筛查 CT 数据集的 BC 评估中，这种校正提高了个体内的一致性和与人体测量近似值的相关性。所开发的方法可在 https://github.com/MASILab/S-EFOV 上获得。
