Lee Seul Bi, Hong Youngtaek, Cho Yeon Jin, Jeong Dawun, Lee Jina, Choi Jae Won, Hwang Jae Yeon, Lee Seunghyun, Choi Young Hun, Cheon Jung-Eun
Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea.
CONNECT-AI R&D Center, Yonsei University College of Medicine, Seoul 03080, Republic of Korea.
Bioengineering (Basel). 2024 Nov 30;11(12):1212. doi: 10.3390/bioengineering11121212.
We assessed the feasibility of using deep learning-based image harmonization to improve the reproducibility of radiomics features in abdominal CT scans. In CT imaging, harmonization adjusts images from different institutions to ensure consistency despite variations in scanners and acquisition protocols. This process is essential because such differences can lead to variability in radiomics features, affecting reproducibility and accuracy. Harmonizing images minimizes these inconsistencies, supporting more reliable and clinically applicable results across diverse settings. A pre-trained harmonization algorithm was applied to 63 dual-energy abdominal CT images, which were reconstructed into four different types, and 10 regions of interest (ROIs) were analyzed. From the original 455 radiomics features per ROI, 387 were used after excluding redundant features. Reproducibility was measured using the intraclass correlation coefficient (ICC), with a threshold of ICC ≥ 0.85 indicating acceptable reproducibility. The region-based analysis revealed significant improvements in reproducibility post-harmonization, especially in vessel features, which increased from 14% to 69%. Other regions, including the spleen, kidney, muscle, and liver parenchyma, also saw notable improvements, although air reproducibility slightly decreased from 95% to 94%, impacting only a few features. In patient-based analysis, reproducible features increased from 18% to 65%, with an average of 179 additional reproducible features per patient after harmonization. These results demonstrate that deep learning-based harmonization can significantly enhance the reproducibility of radiomics features in abdominal CT, offering promising potential for advancing radiomics development and its clinical applications.
我们评估了使用基于深度学习的图像协调技术来提高腹部CT扫描中放射组学特征可重复性的可行性。在CT成像中，协调可对来自不同机构的图像进行调整，以确保尽管扫描仪和采集协议存在差异，但图像仍具有一致性。这一过程至关重要，因为这些差异可能导致放射组学特征的变异性，从而影响可重复性和准确性。图像协调可将这些不一致性降至最低，从而在不同环境中支持更可靠且临床适用的结果。一种预训练的协调算法被应用于63幅双能腹部CT图像，这些图像被重建为四种不同类型，并对10个感兴趣区域（ROI）进行了分析。在排除冗余特征后，从每个ROI最初的455个放射组学特征中，使用了387个。使用组内相关系数（ICC）来衡量可重复性，ICC≥0.85的阈值表示可接受的可重复性。基于区域的分析显示，协调后可重复性有显著提高，尤其是血管特征，从14%增加到了69%。其他区域，包括脾脏、肾脏、肌肉和肝实质，也有明显改善，尽管空气的可重复性从95%略有下降至94%，但仅影响少数特征。在基于患者的分析中，可重复特征从18%增加到65%，协调后每位患者平均增加179个可重复特征。这些结果表明，基于深度学习的协调可显著提高腹部CT中放射组学特征的可重复性，为推进放射组学发展及其临床应用提供了有前景的潜力。
