Li Haoyan, Chen Zhenpeng, Gao Shuaiyi, Hu Jiaqi, Yang Zhihao, Peng Yun, Sun Jihang
Department of Radiology, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, No. 56, Nanlishi Road, Xicheng District, Beijing 100045, China.
Qingdao Academy of Chinese Medical Sciences, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China.
Tomography. 2025 Apr 27;11(5):51. doi: 10.3390/tomography11050051.
: To evaluate the medical image segmentation performance of monochromatic images in various energy levels. : The low-density module (25 mm in diameter, 6 Hounsfield Unit (HU) in density difference from background) from the ACR464 phantom was scanned at both 10 mGy and 5 mGy dose levels. Virtual monoenergetic images (VMIs) at different energy levels of 40, 50, 60, 68, 74, and 100 keV were generated. The images at 10 mGy reconstructed with 50% adaptive statistical iterative reconstruction veo (ASIR-V50%) were used to train an image segmentation model based on U-Net. The evaluation set used 5 mGy VMIs reconstructed with various reconstruction algorithms: FBP, ASIR-V50%, ASIR-V100%, deep learning image reconstruction (DLIR) with low (DLIR-L), medium (DLIR-M), and high (DLIR-H) strength levels. U-Net was employed as a tool to compare algorithm performance. Image noise and segmentation metrics, such as the DICE coefficient, intersection over union (IOU), sensitivity, and Hausdorff distance, were calculated to assess both image quality and segmentation performance. : DLIR-M and DLIR-H consistently achieved lower image noise and better segmentation performance, with the highest results observed at 60 keV, and DLIR-H had the lowest image noise across all energy levels. The performance metrics, including IOU, DICE, and sensitivity, were ranked in descending order with energy levels of 60 keV, 68 keV, 50 keV, 74 keV, 40 keV, and 100 keV. Specifically, at 60 keV, the average IOU values for each reconstruction method were 0.60 for FBP, 0.67 for ASIR-V50%, 0.68 for ASIR-V100%, 0.72 for DLIR-L, 0.75 for DLIR-M, and 0.75 for DLIR-H. The average DICE values were 0.75, 0.80, 0.82, 0.83, 0.85, and 0.86. The sensitivity values were 0.93, 0.91, 0.96, 0.95, 0.98, and 0.98. : For low-density, non-enhancing objects under a low dose, the 60 keV VMIs performed better in automatic segmentation. DLIR-M and DLIR-H algorithms delivered the best results, whereas DLIR-H provided the lowest image noise and highest sensitivity.
评估不同能量水平下单色图像的医学图像分割性能。方法：对美国放射学会（ACR）464体模中的低密度模块（直径25毫米，与背景的密度差为6亨氏单位（HU））分别在10毫戈瑞和5毫戈瑞剂量水平下进行扫描。生成了40、50、60、68、74和100千电子伏特不同能量水平的虚拟单能图像（VMI）。使用50%自适应统计迭代重建veo（ASIR-V50%）重建的10毫戈瑞图像来训练基于U-Net的图像分割模型。评估集使用了通过各种重建算法重建的5毫戈瑞VMI：滤波反投影（FBP）、ASIR-V50%、ASIR-V100%、低（DLIR-L）、中（DLIR-M）和高（DLIR-H）强度水平的深度学习图像重建（DLIR）。采用U-Net作为工具比较算法性能。计算图像噪声和分割指标，如骰子系数、交并比（IOU）、灵敏度和豪斯多夫距离，以评估图像质量和分割性能。结果：DLIR-M和DLIR-H始终实现了更低的图像噪声和更好的分割性能，在60千电子伏特时结果最高，并且DLIR-H在所有能量水平下具有最低的图像噪声。包括IOU、骰子系数和灵敏度在内的性能指标按60千电子伏特、68千电子伏特、50千电子伏特、74千电子伏特、40千电子伏特和100千电子伏特的能量水平降序排列。具体而言，在60千电子伏特时，每种重建方法的平均IOU值分别为：FBP为0.60、ASIR-V50%为0.67、ASIR-V100%为0.68、DLIR-L为0.72、DLIR-M为0.75、DLIR-H为0.75。平均骰子系数分别为0.75、0.80、0.82、0.83、0.85和0.86。灵敏度值分别为0.93、0.91、0.96、0.95、0.98和0.98。结论：对于低剂量下的低密度、无强化物体，60千电子伏特的VMI在自动分割方面表现更好。DLIR-M和DLIR-H算法产生了最佳结果，而DLIR-H提供了最低的图像噪声和最高的灵敏度。
