Trackerless 3D Freehand Ultrasound Reconstruction Challenge 2024 - Validation Dataset

This Challenge will be an open-ended challenge, and we welcome your submission. Please register your team via this ⁠form. You can submit the algorithm via this form for TUS-REC2024 Challenge, and we will test your submitted docker on the test set. We are organising TUS-REC2025 at MICCAI2025. More information is available on the TUS-REC2025 challenge website and Baseline code repo. This is the validation dataset. The training dataset is available at Part1, Part2, and Part3. Acquisition devices and config: The 2D US images were acquired using an Ultrasonix machine (BK, Europe) with a curvilinear probe (4DC7-3/40). The associated position information of each frame was recorded by an optical tracker (NDI Polaris Vicra, Northern Digital Inc., Canada). The acquired US frames were recorded at 20 fps, with an image size of 480×640, without speckle reduction. The frequency was set at 6MHz with a dynamic range of 83 dB, an overall gain of 48% and a depth of 9 cm. Scanning protocol: Both left and right forearms of volunteers were scanned. For each forearm, the US probe moves in three different trajectories (straight line shape, "C" shape, and "S" shape), in a distal-to-proximal direction followed by a proximal-to-distal direction, with the US plane perpendicular of and parallel to the scanning direction. The validation dataset contains 72 scans in total, 24 scans associated with each subject. For detailed information please refer to the Challenge website. Baseline code is also provided, which can be found at this repo. Dataset structure: Folder frames: contains three folders (one subject per folder), each with 24 scans. Each .h5 file corresponds to one scan, storing image of each frame within this scan. Key-value pair and name of each .h5 file are explained below. “frames” - All frames in the scan; with a shape of [N,H,W], where N refers to the number of frames in the scan, H and W denote the height and width of a frame. Notations in the name of each .h5 file: “RH”: right arm; “LH”: left arm; “Per”: perpendicular; “Par”: parallel; “L”: straight line shape; “C”: C shape; “S”: S shape; “DtP”: distal-to-proximal direction; “PtD”: proximal-to-distal direction; For example, “RH_Per_L_DtP.h5” denotes a scan on the right forearm, with ultrasound probe perpendicular of the forearm sweeping along straight line, in distal-to-proximal direction. Folder transfs: contains three folders (one subject per folder), each with 24 scans. Each .h5 file corresponds to one scan, storing transformation of each frame within this scan. Key-value pair and name of each .h5 file are explained below. “tforms” - All transformations in the scan; with a shape of [N,4,4], where N is the number of frames in the scan, and the transformation matrix denotes the transformation from tracker tool space to camera space. Notations in the name of each .h5 file is the same as in folder frames. Folder landmark: contains three .h5 files. Each corresponds to one subject, storing coordinates of landmarks for 24 scans of this subject. For each scan, the coordinates are stored in numpy array with a shape of [20,3]. The first column is the index of frame; the second and third columns denote the coordinates of landmarks in the image coordinate system. calib_matrix.csv: The calibration matrix was obtained using a pinhead-based method. The "scaling_from_pixel_to_mm" and "spatial_calibration_from_image_coordinate_system_to_tracking_tool_coordinate_system" are provided in the “calib_matrix.csv”. dataset_keys.h5: stores the paths to all the scans of the data set. Keys in “dataset_keys.h5” denotes all the available scans in validation set, in a format of “sub%03d__%s” where %03d denotes folder name, and %s denotes the scan name. For example, “sub050__LH_Par_C_DtP” means the scan in folder “050”, with file name of “LH_Par_C_DtP.h5” Data Usage Policy: The training and validation data provided may be utilized within the research scope of this challenge and in subsequent research-related publications. However, commercial use of the training and validation data is prohibited. In cases where the intended use is ambiguous, participants accessing the data are requested to abstain from further distribution or use outside the scope of this challenge. Please cite our challenge paper if you use our dataset in your publication: Challenge paper: Qi Li et al. "TUS-REC2024: A Challenge to Reconstruct 3D Freehand Ultrasound Without External Tracker." arXiv preprint arXiv:2506.21765 (2025). Additional relevant publications may also be cited as appropriate (optional): Optional articles: Qi Li, Ziyi Shen, Qianye Yang, Dean C. Barratt, Matthew J. Clarkson, Tom Vercauteren, and Yipeng Hu. "Nonrigid Reconstruction of Freehand Ultrasound without a Tracker." In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 689-699. Cham: Springer Nature Switzerland, 2024. doi: 10.1007/978-3-031-72083-3_64. Qi Li, Ziyi Shen, Qian Li, Dean C. Barratt, Thomas Dowrick, Matthew J. Clarkson, Tom Vercauteren, and Yipeng Hu. "Long-term Dependency for 3D Reconstruction of Freehand Ultrasound Without External Tracker." IEEE Transactions on Biomedical Engineering, vol. 71, no. 3, pp. 1033-1042, 2024. doi: 10.1109/TBME.2023.3325551. Qi Li, Ziyi Shen, Qian Li, Dean C. Barratt, Thomas Dowrick, Matthew J. Clarkson, Tom Vercauteren, and Yipeng Hu. "Trackerless freehand ultrasound with sequence modelling and auxiliary transformation over past and future frames." In 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp. 1-5. IEEE, 2023. doi: 10.1109/ISBI53787.2023.10230773. Qi Li, Ziyi Shen, Qian Li, Dean C. Barratt, Thomas Dowrick, Matthew J. Clarkson, Tom Vercauteren, and Yipeng Hu. "Privileged Anatomical and Protocol Discrimination in Trackerless 3D Ultrasound Reconstruction." In International Workshop on Advances in Simplifying Medical Ultrasound, pp. 142-151. Cham: Springer Nature Switzerland, 2023. doi: https://doi.org/10.1007/978-3-031-44521-7_14.本次挑战赛为开放式赛事，欢迎各方提交参赛作品。请通过此表单注册参赛团队。您可通过此表单提交TUS-REC2024挑战赛的算法，我们将在测试集上对您提交的Docker（Docker）容器进行测试。 我们将于MICCAI 2025大会期间举办TUS-REC2025挑战赛，更多详情可访问TUS-REC2025挑战赛官网与基线代码仓库。 本次提供验证集。训练集可通过Part1、Part2与Part3获取。 采集设备与参数配置：二维超声（2D US）图像采用Ultrasonix设备（BK，欧洲）搭配曲线探头（curvilinear probe）采集。每帧图像的配套位置信息由光学追踪器（NDI Polaris Vicra，加拿大Northern Digital公司）记录。采集的超声帧以20 fps帧率录制，图像分辨率为480×640，未启用散斑抑制。超声频率设置为6MHz，动态范围83 dB，总增益48%，扫描深度9 cm。 扫描方案：对志愿者的左右前臂均进行扫描。对于每一侧前臂，超声探头沿三种不同轨迹（直线、‘C’形、‘S’形）扫描，先沿远心端向近心端方向，再沿近心端向远心端方向，且超声平面分别垂直于和平行于扫描方向。本次验证集共包含72组扫描数据，每位受试者对应24组扫描。 更多详细信息请参阅挑战赛官网。基线代码亦已提供，可从该代码仓库获取。 数据集结构： - 文件夹frames：包含三个子文件夹（每位受试者对应一个子文件夹），每个子文件夹内含24组扫描数据。每个.h5文件对应一组扫描，存储该扫描内所有帧的图像。每个.h5文件的键值对与文件名规则说明如下： - 键“frames”：对应该扫描内的所有帧，形状为[N, H, W]，其中N为该扫描的帧总数，H、W分别为单帧图像的高度与宽度。 每个.h5文件名的命名规则如下：“RH”代表右臂；“LH”代表左臂；“Per”代表垂直；“Par”代表平行；“L”代表直线轨迹；“C”代表C形轨迹；“S”代表S形轨迹；“DtP”代表远心端到近心端方向；“PtD”代表近心端到远心端方向。例如，“RH_Per_L_DtP.h5”表示针对右侧前臂的扫描，超声探头垂直于前臂，沿直线轨迹以远心端向近心端方向扫描。 - 文件夹transfs：包含三个子文件夹（每位受试者对应一个子文件夹），每个子文件夹内含24组扫描数据。每个.h5文件对应一组扫描，存储该扫描内每帧的变换矩阵。每个.h5文件的键值对与文件名规则说明如下： - 键“tforms”：对应该扫描内的所有变换矩阵，形状为[N,4,4]，其中N为该扫描的帧总数，变换矩阵表示从追踪工具空间到相机空间的转换关系。 文件名命名规则与frames文件夹一致。 - 文件夹landmark：包含三个.h5文件，每个文件对应一位受试者，存储该受试者24组扫描的地标坐标。对于每组扫描，坐标以形状为[20,3]的NumPy数组存储：第一列为帧索引，第二、三列为地标在图像坐标系中的坐标。 - calib_matrix.csv：通过针孔法获取的校准矩阵。该文件中包含"scaling_from_pixel_to_mm"（像素转毫米的缩放系数）与"spatial_calibration_from_image_coordinate_system_to_tracking_tool_coordinate_system"（从图像坐标系到追踪工具坐标系的空间校准矩阵）。 - dataset_keys.h5：存储该数据集所有扫描的路径。该文件内的键代表验证集所有可用的扫描，格式为"sub%03d__%s"，其中%03d代表受试者子文件夹编号，%s代表扫描文件名。例如，"sub050__LH_Par_C_DtP"表示位于"050"子文件夹下，文件名为"LH_Par_C_DtP.h5"的扫描。 数据使用政策： 本次提供的训练集与验证集仅可用于本挑战赛的研究范畴，以及后续相关研究类出版物的创作。禁止将训练集与验证集用于商业用途。若您的使用意图存在歧义，请参赛参与者停止在本挑战赛范畴外分发或使用该数据集。 若您在出版物中使用本数据集，请引用本挑战赛论文： 挑战赛论文： Qi Li 等. "TUS-REC2024: A Challenge to Reconstruct 3D Freehand Ultrasound Without External Tracker". arXiv预印本 arXiv:2506.21765 (2025). 亦可根据需要引用以下相关可选出版物： 可选论文： 1. Qi Li, Ziyi Shen, Qianye Yang, Dean C. Barratt, Matthew J. Clarkson, Tom Vercauteren, 以及 Yipeng Hu. "Nonrigid Reconstruction of Freehand Ultrasound without a Tracker". 收录于国际医学图像计算与计算机辅助干预大会（MICCAI）, 第689-699页. Cham: Springer Nature Switzerland, 2024. doi: 10.1007/978-3-031-72083-3_64. 2. Qi Li, Ziyi Shen, Qian Li, Dean C. Barratt, Thomas Dowrick, Matthew J. Clarkson, Tom Vercauteren, 以及 Yipeng Hu. "Long-term Dependency for 3D Reconstruction of Freehand Ultrasound Without External Tracker". IEEE Transactions on Biomedical Engineering, 第71卷第3期, 第1033-1042页, 2024. doi: 10.1109/TBME.2023.3325551. 3. Qi Li, Ziyi Shen, Qian Li, Dean C. Barratt, Thomas Dowrick, Matthew J. Clarkson, Tom Vercauteren, 以及 Yipeng Hu. "Trackerless freehand ultrasound with sequence modelling and auxiliary transformation over past and future frames". 收录于2023 IEEE第20届国际生物医学成像研讨会（ISBI）, 第1-5页. IEEE, 2023. doi: 10.1109/ISBI53787.2023.10230773. 4. Qi Li, Ziyi Shen, Qian Li, Dean C. Barratt, Thomas Dowrick, Matthew J. Clarkson, Tom Vercauteren, 以及 Yipeng Hu. "Privileged Anatomical and Protocol Discrimination in Trackerless 3D Ultrasound Reconstruction". 收录于简化医学超声进展国际研讨会, 第142-151页. Cham: Springer Nature Switzerland, 2023. doi: 10.1007/978-3-031-44521-7_14.