The Effects of Different Adaptive Statistical Iterative Reconstruction-V and Convolution Kernel Parameters on Auto-Segmentation Stability in CT Images
-
摘要: 目的 探究不同多模型迭代重建算法( ASiR-V)与卷积核重建算法参数对基于深度学习的CT自动分割稳定性的影响。 方法 选取20例行盆腔放疗的病人,采用不同的重建参数建立CT影像数据集,利用深度学习神经网络对3个软组织器官(膀胱、肠袋、小肠)和5个骨性器官(左、右股骨头,左、右股骨,骨盆)进行自动分割,并以滤波反投影CT的分割结果为参考,比较不同重建CT上自动分割结果的DSC系数和Hausdorff距离。 结果 器官的自动分割受ASiR-V参数影响较大,受卷积核参数影响较小,且在软组织中更加明显。 结论 基于深度学习的自动分割稳定性会受到CT图像重建算法参数选择的影响,在实际应用中需在图像质量与分割质量中寻求平衡,或者改进分割网络来提高自动分割的稳定性。Abstract: Objective The study aims to investigate the effects of different adaptive statistical iterative reconstruction-V( ASiR-V) and convolution kernel parameters on stability of CT auto-segmentation which is based on deep learning. Method Twenty patients who have received pelvic radiotherapy were selected and different reconstruction parameters were used to establish CT images dataset. Then structures including three soft tissue organs (bladder, bowelbag, small intestine) and five bone organs (left and right femoral head, left and right femur, pelvic) were segmented automatically by deep learning neural network. Performance was evaluated by dice similarity coefficient( DSC) and Hausdorff distance, using filter back projection(FBP) as the reference. Results Auto-segmentation of deep learning is greatly affected by ASIR-V, but less affected by convolution kernel, especially in soft tissues. Conclusion The stability of auto-segmentation is affected by parameter selection of reconstruction algorithm. In practical application, it is necessary to find a balance between image quality and segmentation quality, or improve segmentation network to enhance the stability of auto-segmentation.
-
Keywords:
- CT reconstruction algorithm /
- ASiR-V /
- convolution kernel /
- auto-segmentation
-
-
[1] LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis[J]. Med Image Anal, 2017, 42(9): 60-88.
[2] 余行, 蒋家良, 何奕松, 等. 利用卷积神经网络对CT图像进行定位的可行性研究[J]. 中国医疗器械杂志, 2019, 43(6): 478-482. [3] 傅玉川, 余行. 医学影像自动分割技术在放射治疗中的应用及发展趋势[J]. 中国医疗器械杂志, 2020, 44(5): 420-424. [4] VAN DIJK L V, VAN DEN BOSCH L, ALJABAR P, et al. Improving automatic delineation for head and neck organs at risk by deep learning contouring[J]. Radiother Oncol, 2020, 142: 115-123.
[5] AHN S H, YEO A U, KIM K H, et al. Comparative clinical evaluation of atlas and deep-learning-based auto-segmentation of organ structures in liver cancer[J]. Radiat Oncol, 2019, 14(1): 1-13.
[6] CARDENAS C E, YANG J, ANDERSON B M, et al. Advances in auto-segmentation[J]. Semin Radiat Oncol, 2019, 29(3): 185-197.
[7] LIM K, KWON H, CHO J, et al. Initial phantom study comparing image quality in computed tomography using adaptive statistical iterative reconstruction and new adaptive statistical iterative reconstruction V[J]. J Comput Assist Tomo, 2015, 39(3): 443-448.
[8] KWON H, CHO J, OH J, et al. The adaptive statistical iterative reconstruction-V technique for radiation dose reduction in abdominal CT: comparison with the adaptive statistical iterative reconstruction technique[J]. Brit J Radiol, 2015, 88(1054): 20150463.
[9] OHKUBO M, WADA S, KAYUGAWA A, et al. Image filtering as an alternative to the application of a different reconstruction kernel in CT imaging: feasibility study in lung cancer screening[J]. Med Phys, 2011, 38(7): 3915- 3923.
[10] ZHAO W, ZHANG W, SUN Y, et al. Convolution kernel and iterative reconstruction affect the diagnostic performance of radiomics and deep learning in lung adenocarcinoma pathological subtypes[J]. Thorac Cancer, 2019, 10(10): 1893-1903.
[11] BLAZIS S P, DICKERSCHEID D B M, LINSEN P V M, et al. Effect of CT reconstruction settings on the performance of a deep learning based lung nodule CAD system[J]. Eur J Radiol, 2021, 136: 109526.
[12] 何奕松, 蒋家良, 余行, 等. 影像分割中Dice系数和Hausdorff距离的比较[J]. 中国医学物理学杂志, 2019, 36(11): 1307-1311. [13] ELDESOKY A R, YATES E S, NYENG T B, et al. Internal and external validation of an ESTRO delineation guideline–dependent automated segmentation tool for loco-regional radiation therapy of early breast cancer[J]. Radiother Oncol, 2016, 121(3): 424-430.
[14] GEYER L L, SCHOEPF U J, MEINEL F G, et al. State of the art: iterative CT reconstruction techniques[J]. Radiology, 2015, 276(2): 339-357.
[15] 高宇. 迭代重建算法的研究进展[J]. 中国医疗设备, 2013, 28(3): 23-25. [16] CHEN L, JIN C, LI J, et al. Image quality comparison of two adaptive statistical iterative reconstruction (ASiR, ASiR-V) algorithms and filtered back projection in routine liver CT[J]. Brit J Radiol, 2018, 91(1088): 20170655.
[17] LI H, DOLLY S, CHEN H C, et al. A comparative study based on image quality and clinical task performance for CT reconstruction algorithms in radiotherapy[J]. J Appl Clin Med Phys, 2016, 17(4): 377-390.
[18] PRICE R G,VANCE S,CATTANEO R,et al. Characterization of a commercial hybrid iterative and model‐ based reconstruction algorithm in radiation oncology[J]. Med Phys, 2014, 41: 081907.
[19] MILLER C, MITTELSTAEDT D, BLACK N, et al. Impact of CT reconstruction algorithm on auto‐ segmentation performance[J]. J Appl Clin Med Phys, 2019, 20(9): 95- 103.
[20] JU Z, WU Q, YANG W, et al. Automatic segmentation of pelvic organs-at-risk using a fusion network model based on limited training samples[J]. Acta Oncol, 2020, 59(8): 93
-
期刊类型引用(2)
1. 王诗瑜,刘义军,魏巍,李贝贝,王旭,童小雨. Revolution CT剂量匹配技术对肝脏脂肪含量测量值的影响. 放射学实践. 2024(04): 534-539 . 百度学术
2. 刘叶红,程龙,时飞跃,王敏,赵环宇,魏晓为. 基于标记点结构体积比确定原始等中心纵向位置的方法研究. 中国医疗设备. 2023(07): 1-6+16 . 百度学术
其他类型引用(1)
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
- 被引次数: 3