MétaCan
Menu
Back to cohort
Record W4393495729 · doi:10.5281/zenodo.7740734

Freehand ultrasound without external trackers

2022· dataset· en· W4393495729 on OpenAlexaboutno aff
Ziyi Shen, Qian Li, Dean C. Barratt, Thomas Dowrick, Matthew J. Clarkson, Tom Vercauteren, Yipeng Hu

Bibliographic record

VenueZenodo (CERN European Organization for Nuclear Research) · 2022
Typedataset
Languageen
FieldEngineering
TopicEngineering Technology and Methodologies
Canadian institutionsnot available
Fundersnot available
KeywordsBitTorrent trackerUltrasoundComputer scienceComputer visionComputer graphics (images)Artificial intelligenceMedicineRadiologyEye tracking

Abstract

fetched live from OpenAlex

We have collected a new large freehand ultrasound dataset and are organising a MICCAI2024&2025 Challenges (TUS-REC Challenge). Check Part 1 and Part 2 of the training dataset for TUS-REC2024, and Train Data for TUS-REC2025. Freehand US scans were acquired on both left and right forearms from 19 volunteers, using Ultrasonix machine (BK, Europe) with a curvilinear probe (4DC7-3/40), tracked by an NDI Polaris Vicra (Northern Digital Inc., Canada). On each forearm, the US probe was moved, for the study purpose, in a straight line, a ‘C’ shape and a ‘S’ shape, in a distal-to-proximal direction. These three scans were repeated, with the curvilinear transducer held (thus the US planes) perpendicular of and parallel to the forearm. B-mode images with median level of speckle reduction were recorded at ~20 fps. Each scan included frames between 36 and 430 with a size of 480×640 pixels, equivalent to a probe travel distance approximately between 100 and 200 mm. A total of 12 scans were acquired from each volunteer, recorded in a single ‘*.mha’ file, with the filename indicating the acquisition time. For example, “LH_Ver_S_20220425_141454.mha” means a scan acquired on 14:14:54 April 25th, 2022. The ‘valid_frames.csv’ file contains the 6 “protocols” with each arm from each volunteer: 1) RH_Par_L (right arm, straight line shape with the probe parallel to the forearm); 2) RH_Par_C (right arm, ‘C’ shape with the probe parallel to the forearm); 3) RH_Par_S (right arm, ‘S’ shape with the probe parallel to the forearm); 4) RH_Ver_L (right arm, straight line shape with the probe perpendicular of the forearm); 5) RH_Ver_C (right arm, ‘C’ shape with the probe perpendicular of the forearm); 6) RH_Ver_S (right arm, ‘S’ shape with the probe perpendicular of the forearm); 7) LH_Par_L (left arm, straight line shape with the probe parallel to the forearm); 8) LH_Par_C (left arm, ‘C’ shape with the probe parallel to the forearm); 9) LH_Par_S (left arm, ‘S’ shape with the probe parallel to the forearm); 10) LH_Ver_L (left arm, straight line shape with the probe perpendicular of the forearm); 11) LH_Ver_C (left arm, ‘C’ shape with the probe perpendicular of the forearm); 12) LH_Ver_S (left arm, ‘S’ shape with the probe perpendicular of the forearm). The ‘start’ and ‘end’ denote the start and end frame indices of a scan, respectively, in each ‘*.mha’ file. US images, transformation matrix obtained from the tracker, and corresponding csv file, for each scan can be found in Freehand_US_data.zip. In the “calib_matrix.csv” file, we provide a calibration matrix and a time difference in sec, obtained from our calibration experiments. A baseline code is provided in this repo. If you find this data set useful for your research, please consider citing some of the following works: 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, 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. "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

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Dataset · Consensus signal: Dataset
Teacher disagreement score0.030
Threshold uncertainty score0.099

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.004
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0020.001
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0020.002
Research integrity0.0020.001
Insufficient payload (model declined to judge)0.0300.033

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.038
GPT teacher head0.255
Teacher spread0.217 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreDataset

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueZenodo (CERN European Organization for Nuclear Research)Same topicEngineering Technology and MethodologiesFrench-language works237,207