利用公开数据集进行商用形变配准系统的准确度评估

Accuracy evaluation of commercial deformation registration systems using public datasets

摘要

目的：利用公开数据集评估商用形变配准系统不同形变配准算法在胸部图像配准中的准确性。方法：通过注册获得美国埃默里大学医学院DIR实验室（www.DIR-lab.com）提供的10例胸部癌症患者4D-CT图像数据集的使用授权，该数据集包含由胸部影像学专家手动识别和配准的解剖标识及其相应的坐标信息，通过比较吸气末时相和呼气末时相图像之间点与点的对应关系，评估RayStation治疗计划系统和MIM软件两种商用系统形变配准算法的配准精度。结果：RayStation系统中生物力学算法以及混合强度算法的Control POI、Control ROI和Focus ROI 3种配准模式以及MIM系统中Image based配准算法的目标配准误差范围分别为：0.20~30.50 mm、0.00~28.20 mm、0.10~31.70 mm，0.00~31.00 mm以及0.09~32.45 mm，通过不同患者和不同配准模式之间的误差分布以及统计学分析可以看出各种配准算法应用于不同患者时有很大的变化，不同的DIR算法给出的匹配结果是有差异的。结论：基于本文的评估方法可进行临床实践中商用形变配准系统形变配准算法几何精度的定量化验证。

Abstract

Objective To evaluate the accuracy of various deformable image registration (DIR) algorithms integrated in commercial systems for thoracic image registration using publicly available datasets. Methods Permission to utilize the 4D-CT image dataset containing 10 thoracic cancer patients, provided by the DIR Lab at Emory University School of Medicine (www.DIR-lab.com), was obtained after official registration. This dataset included anatomical landmarks identified and registered by thoracic imaging experts, together with detailed coordinate lists. Precise point-to-point correspondences between end-inspiratory and end-expiratory phase images were established to evaluate the registration accuracy of different DIR algorithms integrated in the Raystation treatment planning system and MIM software. Results For the RayStation system, the target registration error ranges of the evaluated algorithms were as follows: Biomechanical (0.20-30.50 mm), Control POI (0.00-28.20 mm), Control ROI (0.10-31.70 mm), and Focus ROI (0.00-31.00 mm). For the image based registration algorithm in the MIM system, the target registration error range was 0.09-32.45 mm. The error distribution across patients and registration modes and statistical analysis demonstrated significant inter-patient variability for each registration algorithm. Notably, different DIR algorithms produced markedly varying registration outcomes. Conclusion: The proposed evaluation method enables quantitative verification of the geometric accuracy of DIR algorithms embedded in commercial systems for clinical practice.

关键词

图像形变配准 / 自适应放射治疗 / 四维计算机断层扫描 / 目标配准误差 / 质量控制

Key words

deformable image registration / adaptive radiotherapy / four-dimensiond computed tomography / target registration error / quality control

参考文献

[1] Brock KK, Mutic S, Mcnutt TR, et al. Use of image registration and fusion algorithms and techniques in radiotherapy: report of the AAPM Radiation Therapy Committee Task Group No. 132[J]. Med Phys, 2017, 44(7): e43-e76.

[2] Chetty IJ, Rosu—Bubulac M. Deformable registration for dose accumulation[J]. Semin Radiat Oncol, 2019, 29(3): 198-208.

[3] Oh S, Kim S . Deformable image registration in radiation therapy[J]. Radiat Oncol J, 2017, 35(2): 101-111.

[4] Kadoya N, Fujita Y, Katsuta Y, et al. Evaluation of various deformable image registration algorithms for thoracic images[J]. J Radiat Res, 2014, 55(1): 175-182.

[5] Kadoya N, Nakajima Y, Saito M, et al. Multi—institutional validation study of commercially available deformable image registration software for thoracic images[J]. Int J Radiat Oncol Biol Phys, 2016, 96(2): 422-431.

[6] Czajkowski P, Piotrowski T . Registration methods in radiotherapy[J]. Rep Pract Oncol Radiother, 2019, 24(1): 28-34.

[7] Castillo R, Castillo E, Guerra R, et al. A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets[J]. Phys Med Biol, 2009, 54(7): 1849-1870.

[8] Weistrand O, Svensson S . The ANACONDA algorithm for deformable image registration in radiotherapy[J]. Med Phys, 2015, 42(1): 40-53.

[9] Brock KK, Sharpe MB, Dawson LA, et al. Accuracy of finite element model—based multi—organ deformable image registration[J]. Med Phys, 2005, 32(6): 1647-1659.

[10] Velea M, Moseley JL, Svensson S, et al. Validation of biomechanical deformable image registration in the abdomen, thorax, and pelvis in a commercial radiotherapy treatment planning system[J]. Med Phys, 2017, 44(7): 3407-3417.

[11] Kumar MA, Hajare R, Nath BD, et al. Performance evaluation of deformable image registration systems — SmartAdapt® and VelocityTM[J]. J Med Phys, 2024, 49(2): 240-249.

[12] Motegi K, Tachibana H, Motegi A, et al. Usefulness of hybrid deformable image registration algorithms in prostate radiation therapy[J]. J Appl Clin Med Phys, 2019, 20(1): 229-236.

[13] Latifi K, Caudell J, Zhang G, et al. Practical quantification of image registration accuracy following the AAPM TG—132 report framework[J]. J Appl Clin Med Phys, 2018, 19(4): 125-133.

[14] Nenoff L, Amstutz F, Murr M, et al. Review and recommendations on deformable image registration uncertainties for radiotherapy applications[J]. Phys Med Biol, 2023, 68(24): 24TR01.

[15] Mee M, Stewart K, Lathouras M, et al. Evaluation of a deformable image registration quality assurance tool for head and neck cancer patients[J]. J Med Radiat Sci, 2020, 67(4): 284-293.

[16] Rong Y, Rosu—Bubulac M, Benedict SH, et al. Rigid and deformable image registration for radiation therapy: a self—study evaluation guide for NRG oncology clinical trial participation[J]. Pract Radiat Oncol, 2021, 11(4): 282-298.

[17] Wu RY, Liu AY, Williamson TD, et al. Quantifying the accuracy of deformable image registration for cone—beam computed tomography with a physical phantom[J]. J Appl Clin Med Phys, 2019, 20(10): 92-100.

[18] Kubli A, Pukala J, Shah AP, et al. Variability in commercially available deformable image registration: a multi—institution analysis using virtual head and neck phantoms[J]. J Appl Clin Med Phys, 2021, 22(5): 89-96.

[19] Paganelli C, Meschini G, Molinelli S, et al. Patient—specific validation of deformable image registration in radiation therapy: overview and caveats[J]. Med Phys, 2018, 45(10): e908-e922.

[20] Murr M, Brock KK, Fusella M, et al. Applicability and usage of dose mapping/accumulation in radiotherapy[J]. Radiother Oncol, 2023, 182: 109527.

[21] Barber J, Yuen J, Jameson M, et al. Deforming to best practice: key considerations for deformable image registration in radiotherapy[J]. J Med Radiat Sci, 2020, 67(4): 318-332.

[22] Glide—Hurst CK, Lee P, Yock AD, et al. Adaptive radiation therapy (ART) strategies and technical considerations: a state of the ART review from NRG oncology[J]. Int J Radiat Oncol Biol Phys, 2021, 109(4): 1054-1075.

[23] Torchia J, Velec M . Deformable image registration for composite planned doses during adaptive radiation therapy[J]. J Med Imaging Radiat Sci, 2024, 55(1): 82-90.

基金资助

国家自然科学基金(12405391)