Objective: To assess the performance of a probabilistic deep learning based algorithm for predicting inter-fraction anatomical changes in head and neck patients.
Approach: A probabilistic daily anatomy model for head and neck patients $(\mathrm{DAM}_{\mathrm{HN}})$ is built on the variational autoencoder architecture. The model approximates the generative joint conditional probability distribution of the repeat computed tomography (rCT) images and their corresponding masks on the planning CT images (pCT) and their masks. The model outputs deformation vector fields, which are used to produce possible rCTs and associated masks. The dataset is composed of 93 patients (i.e., 367 pCT - rCT pairs), 9 (i.e., 37 pairs) of which were set aside for final testing. The performance of the model is assessed based on the reconstruction accuracy and the generative performance for the set aside patients.
Main results: The model achieves a DICE score of 0.92 and an image similarity score of 0.65 on the test set. The generated parotid glands volume change distributions and center of mass shift distributions were also assessed. For both, the medians of the distributions are close to the true ones, and the distributions are broad enough to encompass the real observed changes. Moreover, the generated images display anatomical changes in line with the literature reported ones, such as the medial shifts of the parotids glands.
Significance: $(\mathrm{DAM}_{\mathrm{HN}})$ is capable of generating realistic anatomies observed during the course of the treatment and has applications in anatomical robust optimization, treatment planning based on plan library approaches and robustness evaluation against inter-fractional changes.
Quantification of head and neck cancer patients' anatomical changes during radiotherapy: prediction of replanning need
McGill University(麦吉尔大学);Research Institute of the McGill University Health Centre, McGill University(麦吉尔大学健康中心研究所,麦吉尔大学);Department of Radiation Oncology, Hôpital Maisonneuve-Rosemont(Maisonneuve-Rosemont医院放射肿瘤科);Department of Radiation Oncology, McGill University(麦吉尔大学放射肿瘤科)
Predicting Lymph Node Metastasis in Head and Neck Cancer by Combining Many-objective Radiomics and 3-dimensioal Convolutional Neural Network through Evidential Reasoning
Combining Many-objective Radiomics and 3-dimensional Convolutional Neural Network through Evidential Reasoning to Predict Lymph Node Metastasis in Head and Neck Cancer
Validation of Monte Carlo Iodine-131 radiopharmaceutical dosimetry workflow using a 3D printed anthropomorphic head and neck phantom
目的:在这项研究中,我们提出了一个拟人的,头部和颈部,核医学体模的创建及其表征的蒙特卡罗,SPECT图像为基础的,碘-131 RPT剂量测定工作流程的验证。方法:使用3D打印技术从患者CT数据集创建拟人化体模。使用均质、Jaszczak和拟人化体模进行三次碘-131 SPECT/CT成像研究,以量化SPECT图像。使用基于图像的Geant 4 Monte Carlo RPT剂量测定工作流程计算准直器探测器响应(CDR)建模和基于体积的部分体积校正(PVC)对吸收剂量的影响,并与真实场景进行比较。最后,根据最近的EANM指南量化了不确定性。结果:3D打印的拟人化体模是对患者解剖结构(包括骨骼)的准确再现。对于CDR和非CDR情况,外推的Jaszczak回收系数大于3D打印插入物的回收系数(约22.8 ml)。利用Jaszczak体模PVC,在无CDR和有CDR的情况下,吸收剂量分别被低估0.7%和4.9%。使用拟人体模RC,在有和没有CDR的情况下,对吸收剂量的预测均超出3%。包含PVC的所有剂量测定方案均在计算的放射性不确定度范围内。对于体积为0.5 ml至16 ml的Jaszczak球,累积活性的不确定度范围为25.6%至113%。结论:使用拟人体模验证了基于蒙特卡罗的头颈部癌131碘RPT剂量学的准确性。体模的未来应用可能涉及3D打印和表征患者特定体积,以进行更个性化的RPT剂…
Fully Automated Treatment Planning for Head and Neck Radiotherapy using a Voxel-Based Dose Prediction and Dose Mimicking Method
最近在自动放射治疗计划中的工作已经使用基于历史治疗计划的机器学习来直接从计划图像推断新患者的空间剂量分布。我们提出了一种基于图谱的方法,该方法在训练数据库中学习每个患者的剂量预测模型(图谱),然后学习将新患者与最相关的图谱相匹配。该方法创建空间剂量目标,其指定期望的每体素剂量,并且因此取代指定剂量体积目标的任何要求,以传达治疗计划的目标。概率剂量分布从最相关的图谱中推断,并使用条件随机场进行定标,以确定最可能的剂量空间分布,从而为相关的感兴趣区域产生特定的剂量先验(直方图)。然后,基于体素的剂量模拟将预测的剂量分布转换为可递送的治疗计划剂量分布。在这项研究中,我们研究了接受IMRT和VMAT治疗的右侧orbiliaynx头颈部患者的自动计划。我们使用54个训练和12个独立测试患者的数据库比较了我们的剂量预测管道的四个版本。我们的初步结果是有希望的;与临床相比,自动计划在7例患者中实现了更多的剂量评价标准,在4例患者中实现了相同数量的剂量评价标准。总体而言,自动化计划达到的标准相对数量高于临床(17 vs 8),自动化计划显示出对风险器官的保留增加(52 vs 44)和更好的靶覆盖/均匀性(41 vs 31)。
Divergent Clinical Equivalence Findings from DVH and NTCP Metrics for Alternative OAR Delineations with Increasing Setup Variability in Head-and-Neck Radiotherapy
Diffusion Schrödinger Bridge Models for High-Quality MR-to-CT Synthesis for Head and Neck Proton Treatment Planning
Paul Scherrer Institut(保罗·谢勒研究所);ETH Zurich(苏黎世联邦理工学院);University Hospital of Zurich(苏黎世大学医院);Inselspital, Bern University Hospital, University of Bern(伯尔尼大学医院(因塞尔医院),伯尔尼大学)
Navigated interventions in the head and neck area: standardized assessment of a new handy field generator
电磁(EM)跟踪使得能够在由EM场发生器(FG)发射的磁场内定位手术器械。通常,FG越大,其跟踪体积越大。NDI(Northern Digital Inc.,Waterloo,ON,Canada)最近推出了Planar 10-11 FG,它结合了紧凑的结构(97 mm x 112 mm x 31 mm)和相对较大的圆柱形跟踪体积(直径:340 mm,高度:340 mm)。使用Hummel等人的标准化评估方案,测试了FG的跟踪精度和对外部干扰源的鲁棒性。平均位置误差(根据Hummel方案的5cm距离度量)为0.59 mm,标准设置中的平均抖动为0.26 mm。平均定向误差为0.10°。金属干扰源引起的最大位置误差(4.82 mm)是由SST 303钢引起的。相比之下,不锈钢416引起的位置误差最小(0.10 mm)。总体而言,与其他NDI FG相比,Planar 10-11 FG往往能实现更好的跟踪精度结果。由于其紧凑的结构和便携性,FG可能有助于增加EM跟踪系统的临床使用。
Development of a defacing algorithm to protect the privacy of head and neck cancer patients in publicly-accessible radiotherapy datasets
McGill University(麦吉尔大学);Research Institute of the McGill University Health Centre(麦吉尔大学健康中心研究所);Gerald Bronfman Department of Oncology, McGill University(麦吉尔大学杰拉尔德·布朗夫曼肿瘤学系)
Modeling Bilateral Lymphatic Head and Neck Tumour Progression for Personalized Elective Target Volume Definition
Aarhus University(奥胡斯大学);Danish Centre for Particle Therapy, Aarhus University Hospital(奥胡斯大学医院丹麦粒子治疗中心);Department of Experimental Clinical Oncology, Aarhus University Hospital(奥胡斯大学医院实验临床肿瘤学系);Department of Radiation Oncology, University Hospital of Zurich(苏黎世大学医院放射肿瘤学系)
Segmentation-Free Outcome Prediction from Head and Neck Cancer PET/CT Images: Deep Learning-Based Feature Extraction from Multi-Angle Maximum Intensity Projections (MA-MIPs)
University of British Columbia(不列颠哥伦比亚大学);BC Cancer Research Institute(不列颠哥伦比亚癌症研究所);Geneva University Hospital(日内瓦大学医院);University Hospital Bern(伯尔尼大学医院)
Contour-informed inter-patient deformable registration of Head-and-Neck patients
Center for Proton Therapy, Paul Scherrer Institut(质子治疗中心,保罗谢尔研究所);Shanghai Institute of Applied Physics, Chinese Academy of Sciences(中国科学院上海应用物理研究所);Department of Computer Science, ETH Zurich(苏黎世联邦理工学院计算机系);Department of Physics, ETH Zurich(苏黎世联邦理工学院物理系);Shanghai Advanced Research Institute, Chinese Academy of Sciences(中国科学院上海高级研究院)
Causal Machine Learning Analysis of Empirical Relative Biological Effectiveness (RBE) for Mandible Osteoradionecrosis in Head and Neck Cancer Radiotherapy
Mayo Clinic(梅奥诊所);Southwestern University of Finance and Economics(西南财经大学);the University of Miami(迈阿密大学);University of Georgia(佐治亚大学);Nanchang University(南昌大学);Mayo Clinic Arizona(梅奥诊所亚利桑那分院)
Patient-Specific Deep Reinforcement Learning for Automatic Replanning in Head-and-Neck Cancer Proton Therapy
Department of Radiation and Cellular Oncology University of Chicago(辐射与细胞肿瘤学系,芝加哥大学);Division of Environmental and Occupational Health Sciences University of Illinois at Chicago(环境与职业卫生科学系,伊利诺伊大学芝加哥分校);Department of Radiation Oncology and Winship Cancer Institute Emory University(放射肿瘤学系和Winship癌症研究所,埃默里大学)
A Dual Path Framework with Hotspot Guided Fusion for Three Dimensional CT to PET Synthesis in Head and Neck Cancer
Advanced Molecular Imaging in Radiotherapy (AdMIRe) Research Laboratory, School of Health Sciences, Purdue University, West Lafayette, IN, 47907, USA(高级分子影像在放射治疗(AdMIRe)研究实验室,健康科学学院,普渡大学,西拉法叶,IN,47907,美国);Department of Radiation Oncology, Indiana University School of Medicine, Indianapolis, IN 46202, USA(放射肿瘤学部,印第安纳大学医学院,印第安纳波利斯,IN,46202,美国)
Three-Dimensional Radiotherapy Dose Prediction on Head and Neck Cancer Patients with a Hierarchically Densely Connected U-net Deep Learning Architecture
University of Texas Southwestern Medical Center(德克萨斯大学西南医学中心)
Enabling Clinical Use of Linear Energy Transfer in Proton Therapy for Head and Neck Cancer -- A Review of Implications for Treatment Planning and Adverse Events Study
TransAnaNet: Transformer-based Anatomy Change Prediction Network for Head and Neck Cancer Patient Radiotherapy
UT Southwestern Medical Center(德克萨斯大学西南医学中心);University of Maryland Medical Center(马里兰大学医学中心);Central Arkansas Radiation Therapy Institute(中央阿肯色放射治疗研究所)
Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy
University College London Hospitals NHS Foundation Trust(伦敦大学学院医院国民保健服务基金会信托);Google Health(谷歌健康);DeepMind(深度思维);Clatterbridge Cancer Centre NHS Foundation Trust(克拉特布里奇癌症中心国民保健服务基金会信托);University College London(伦敦大学学院)
Large-scale automatic carbon ion treatment planning for head and neck cancers via parallel multi-agent reinforcement learning
1 State Key Laboratory of Nuclear Physics;Technology, Institute of Heavy Ion Physics, Peking University School of Physics, Beijing 100871, China.;2 Key Laboratory of Carcinogenesis;Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital \& Institute, Beijing 100142, China.;3 Department of Technology, CAS Ion Medical Technology Co., Ltd., Beijing 100190, China.;4 Department of Health Technology;Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, 999077, China.