To evaluate the presented approaches, we created the Physical Anomalous Trajectory or Motion (PHANTOM) dataset consisting of six classes featuring everyday objects or physical setups, and showing nine different kinds of anomalies. We designed our classes to evaluate detection of various modes of video abnormalities that are generally excluded in video AD settings.

The train and test sets of each class contain approximately 30 videos of varying lengths. The train set contains only normal videos, while the test set is evenly balanced between normal and anomalous videos. The classes were designed to be of varying difficulties and to feature different types of anomalies. For example, the window class was filmed in multiple lighting scenarios to increase variance. The normal videos include motion that follows an expected trajectory (pendulum, keyboard) or an expected movement (window). The sushi class features procedural motion, while candle and magnets feature more subtle motion that only appears locally. The anomalous videos can feature an interference of the regular motion (window, candle, magnets), an added or removed step in the usual procedure (sushi), motion that follows a different trajectory (pendulum, keyboard), or contains a different object (pendulum).

The RIDER PHANTOM PET-CT collection consists of repeat measurement PET/CT phantom scan collections carried out under the aegis of the Society of Nuclear Medicine (SNM) to discern the uniformity of clinical imaging instrumentation at various sites. They were obtained in cooperation with SNM as a resource for increased quantitative understanding of machine acquisition, analytic reproducibility and image processing.

The phantom was manufactured by Sanders Medical (www.sandersmedical.com) in December of 2006. The phantom was based on a NEMA NU-2 IQ phantom (manufactured by Data Spectrum, Durham NC), but with the central 5 cm diameter 'lung' cylinder of the IQ phantom removed. In addition the two larger fillable spheres were changed to hot spheres, as opposed to cold spheres as in the NEMA NU-2 specifications. Nominal target/background ratio was 4:1 with the initial background activity level set to be equivalent to 15 mCi in a 70 Kg patient, With the 271 day half-life of Ge-68 after 6 months the activity will be about 9.5 mCi. After a year it was 6 mCi.

About the RIDER project

The Reference Image Database to Evaluate Therapy Response (RIDER) is a targeted data collection used to generate an initial consensus on how to harmonize data collection and analysis for quantitative imaging methods applied to measure the response to drug or radiation therapy. The National Cancer Institute (NCI) has exercised a series of contracts with specific academic sites for collection of repeat "coffee break," longitudinal phantom, and patient data for a range of imaging modalities (currently computed tomography [CT] positron emission tomography [PET] CT, dynamic contrast-enhanced magnetic resonance imaging [DCE MRI], diffusion-weighted [DW] MRI) and organ sites (currently lung, breast, and neuro). The methods for data collection, analysis, and results are described in the new Combined RIDER White Paper Report (Sept 2008):

• RIDER White Paper: Combined contracts report ( Sept 2008) PDF

The long term goal is to provide a resource to permit harmonized methods for data collection and analysis across different commercial imaging platforms to support multi-site clinical trials, using imaging as a biomarker for therapy response. Thus, the database should permit an objective comparison of methods for data collection and analysis as a national and international resource as described in the first RIDER white paper report (2006):

• RIDER White Paper: Executive Summary PDF
• RIDER White Paper: Editorial in Nature.com

As part of a more general effort to probe the interrelated factors impacting the accuracy and precision of lung nodule size estimation, we have been conducting phantom CT studies with an anthropomorphic thoracic phantom containing a vasculature insert on which synthetic nodules were inserted or attached.

The utilization of synthetic nodules with known truth regarding size and location allows for bias and variance analysis, enabled by the acquisition of repeat CT scans. Using a factorial approach to probe imaging parameters (acquisition and reconstruction) and nodule characteristics (size, density, shape, location), ten repeat scans have been collected for each protocol and nodule layout. The resulting database of CT scans is incrementally becoming available to the public via The Cancer Imaging Archive (TCIA) to facilitate the assessment of lung nodule size estimation methodologies and the development of image analysis software among other possible applications.

The XCAT phantom dataset used in our paper "Resolving Variable Respiratory Motion From Unsorted 4D Computed Tomography", MICCAI 2024. For details on how to use the dataset, please visit https://github.com/Yuliang-Huang/4DCT-irregular-motion. If you find this dataset useful for your research, please cite our MICCAI paper.Note: We thank Prof Paul Segars from Duke University for the permission of releasing this single simulation example. If you want to use the XCAT software, please contact him.Introduction to the dataset:A digital phantom of thoracic region with motion was generated by the 4DXCAT software [1] and post-processed by the cid-X software [2]. The simulation was controlled by two respiration traces, i.e. the motion of the chest and the diaphragm, which were measured from 2D Cine MRI from a real patient. The diaphragm trace was deliberately delayed by 1 second to add hysteresis, i.e. the breathing would follow different paths during inhalation and exhalation. The chest trace could simulate the skin marker or belt signals normally used to sort 4DCT data in clinical practice and was stored in the rpm_signal.txt file.The phantom dataset consisted of images of thoracic regions at 182 timepoints in NIFTI format, each with size 355x280x115 voxels and resolution of 1x1x3 mm. Binary masks of the tumour were also provided for each timepoint. The dynamic volumes and tumor masks can be found in the compressed ground_truth.zip folder.The ref_empty_image.nii.gz file is an image with zero voxel values that define the reference image space. The ref_tumor_mask.nii.gz is the ground-truth tumor mask at the time average position.References:[1]Segars, W.P., Sturgeon, G., Mendonca, S., Grimes, J., Tsui, B.M.: 4d xcat phantomfor multimodality imaging research. Medical physics 37(9), 4902–4915 (2010)[2]Eiben, B., Bertholet, J., Menten, M.J., Nill, S., Oelfke, U., McClelland, J.R.: Con-sistent and invertible deformation vector fields for a breathing anthropomorphicphantom: a post-processing framework for the xcat phantom. Physics in Medicine& Biology 65(16), 165005 (2020)

This database contains imaging and calibration data for phantoms contained in the NIST/NIBIB Phantom Lending Library (PLL). Description and access to the PLL can be found at https://www.nist.gov/programs-projects/nistnibib-medical-imaging-phantom-lending-library . Public analysis software written in Python can be found at https://github.com/MRIStandards/PhantomViewer . This database contains image sets from different scanners and different sites to be used for comparison and reference purposes. It is not meant to endorse any specific scanner or scan protocol.

DICOM images of CEORA and SATI phantom for calcium volume scores acquired using clinical calcium score and partial volume corrected scores used in manuscript "Coronary calcium scoring with partial volume correction in anthropomorphic thorax phantom and screening chest CT images" submitted at PLOS ONE.

43 measurements acquired in eight different sites within the IMAGEN-project, comprising the following 3 T scanner types: Siemens Verio and TimTrio; General Electric Signa Excite, and Signa HDx; Philips Achieva. Additionally one phantom data set was aquired on a 3 T Siemens Skyra resulting in 44 measurements.

The FDA anthropomorphic thorax phantom with 12 phantom lesions of different sizes (10 and 20 mm in effective diameter), shapes (spherical, elliptical, lobulated, and spiculated), and densities (−630,−10, and +100 HU) was scanned at Columbia University Medical Center on a 64-detector row scanner (LightSpeed VCT, GE Healthcare, Milwaukee, WI). The CT scanning parameters were 120 kVp, 100 mAs, 64x0.625 collimation, and pitch of 1.375. The images were reconstructed with the lung kernel using 1.25 mm slice thickness.

This data set was provided to TCIA for use in the National Cancer Institute's Quantiatitive Imaging Network (QIN) Lung CT Segmentation Challenge. A TCIA Analysis Result dataset was created to enable easy re-use of the complete multi-site challenge data set.

About the NCI QIN

The mission of the QIN is to improve the role of quantitative imaging for clinical decision making in oncology by developing and validating data acquisition, analysis methods, and tools to tailor treatment for individual patients and predict or monitor the response to drug or radiation therapy. More information is available on the Quantitative Imaging Network Collections page. Interested investigators can apply to the QIN at: Quantitative Imaging for Evaluation of Responses to Cancer Therapies (U01).

An open-data initiative for the distributation of common datasets for the evaluation and validation of diffusion MRI processing methods. http://www.dkfz.de/en/medphysrad/projectgroups/dwi/DTI_projects.html#inhalt3

Images trained for my phantom diffusion series. Since they are all AI generated images that are public domain under the US law, I claim it is legal to redistribute them as public domain. However, they might have copyright in your/their original country. Still, many countries including Japan allow us to use them for training an AI under their copyrights law, and because all the artists here are from Japan, I assume it should be allowed to reuse it for training globally.

Imaging data sets for printed contrast phantoms across 4 timepoints and 3 frequencies. Printed contrast regions were analyzed for Backscatter signal within the region and CNR within the region compared to a background ROI.

Manusia & Phantom

## Overview

Manusia & Phantom is a dataset for object detection tasks - it contains Peak annotations for 1,010 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Snapshot img

Medical Imaging Phantom Market Size 2024-2028

The medical imaging phantom market size is forecast to increase by USD 47.7 million, at a CAGR of 5.2% between 2023 and 2028.

The market is experiencing significant growth, driven by the increasing prevalence of chronic conditions that necessitate frequent imaging examinations. This trend is fueled by an aging population and rising incidences of diseases such as cancer and cardiovascular disorders. Furthermore, technological advancements in imaging phantoms are enhancing diagnostic accuracy and enabling more efficient and cost-effective imaging procedures. These innovations include the development of advanced materials and designs that mimic human tissue more accurately, as well as the integration of automation and connectivity features. However, the market also faces challenges, including stringent regulatory frameworks that require phantoms to meet rigorous safety and performance standards.
Additionally, the high cost of developing and manufacturing advanced imaging phantoms can limit market penetration, particularly in developing countries. To navigate these challenges, companies must focus on innovation, regulatory compliance, and cost-effective manufacturing strategies. By addressing these issues, they can capitalize on the market's growth potential and meet the evolving needs of healthcare providers and patients.

What will be the Size of the Medical Imaging Phantom Market during the forecast period?

Explore in-depth regional segment analysis with market size data - historical 2018-2022 and forecasts 2024-2028 - in the full report.
Request Free Sample

The market continues to evolve, driven by the constant demand for advanced imaging technologies and the need for accurate and reliable results. Phantoms, which are essential tools for image acquisition, calibration, and quality control, play a crucial role in this dynamic industry. Phantom image segmentation and tissue mimicking materials are at the forefront of this evolution. These advanced phantom designs enable more precise image analysis, improving diagnostic accuracy and enhancing research capabilities. The construction of MRI phantoms, for instance, incorporates intricate tissue mimicking materials to replicate human anatomy, allowing for more realistic and accurate imaging.

The modulation transfer function and phantom manufacturing process are other critical aspects of this market. These elements ensure that phantoms maintain consistent image quality and provide accurate results, even as imaging technologies continue to advance. Scatter correction evaluation and lesion detectability analysis are also essential, as they help mitigate image distortions and improve diagnostic confidence. Signal-to-noise ratio, material composition effects, and contrast resolution measurement are just a few of the many factors that influence phantom performance. Phantom geometry variations, artifact detection methods, and phantom image processing are also crucial considerations. Quality control procedures and phantom lifespan testing ensure that these tools maintain their accuracy and reliability over time.

Computer-aided design, ultrasound phantom features, image quality assessment, SPET phantom validation, and PET phantom calibration are just a few of the ongoing initiatives in this market. The continuous unfolding of market activities and evolving patterns underscore the importance of phantoms in medical imaging and their role in advancing diagnostic capabilities and driving research forward.

How is this Medical Imaging Phantom Industry segmented?

The medical imaging phantom industry research report provides comprehensive data (region-wise segment analysis), with forecasts and estimates in 'USD million' for the period 2024-2028, as well as historical data from 2018-2022 for the following segments.

End-user

  Hospitals
  Diagnostic laboratories
  Academic and research


Geography

  North America

    US
    Canada


  Europe

    Germany
    UK


  APAC

    China


  Rest of World (ROW)

By End-user Insights

The hospitals segment is estimated to witness significant growth during the forecast period.

The market is experiencing significant growth due to the increasing demand for accurate and efficient imaging solutions in healthcare settings. Hospitals, as the primary end-users, are driving market expansion as they seek cost-effective medical imaging phantoms to facilitate better diagnosis and treatment planning. These phantoms play a crucial role in various medical imaging modalities, including CT, MRI, ultrasound, and PET, enabling image registration accuracy, energy resolution testing, attenuation coefficient accuracy, radiation dose optimization, and quantitative image analysis. Phantom design and manufacturing processes are continually evolving to address the need for system performance verification, phantom im

The RIDER Phantom MRI data set contains repeat phantom studies. The phantom used for all data acquisitions was a version of the EuroSpin II Test Object 5 as distributed by Diagnostic Sonar, Ltd (Livingston, West Lothian, Scotland). The phantom was comprised of 18 25-mm doped gel filled tubes and 1 20-mm tube containing 0.25 mM GdDTPA.

Scanners evaluated:

• Scanner A – 1.5T GE 8-channel HD with BRM gradient subsystem (33 mT/m amplitude; 120 T/m-s)
• Scanner B – 1.5T GE 8-channel HD with CRM gradient subsystem (50 mT/m amplitude; 150 T/m-s)
• Scanner C – 1.5T Siemens Espree (VB13) with 33 mT/m amplitude, 100 T/m-s gradient subsystem
• Scanner D – 3.0T GE 8-channel HD with TwinSpeed gradients (40 mT/m; 150 T/m-s in zoom mode) For all measurements, an 8-channel phased array head coil was used.

About the RIDER project

The Reference Image Database to Evaluate Therapy Response (RIDER) is a targeted data collection used to generate an initial consensus on how to harmonize data collection and analysis for quantitative imaging methods applied to measure the response to drug or radiation therapy. The National Cancer Institute (NCI) has exercised a series of contracts with specific academic sites for collection of repeat "coffee break," longitudinal phantom, and patient data for a range of imaging modalities (currently computed tomography [CT] positron emission tomography [PET] CT, dynamic contrast-enhanced magnetic resonance imaging [DCE MRI], diffusion-weighted [DW] MRI) and organ sites (currently lung, breast, and neuro). The methods for data collection, analysis, and results are described in the new Combined RIDER White Paper Report (Sept 2008):

• RIDER White Paper: Combined contracts report ( Sept 2008) PDF

The long term goal is to provide a resource to permit harmonized methods for data collection and analysis across different commercial imaging platforms to support multi-site clinical trials, using imaging as a biomarker for therapy response. Thus, the database should permit an objective comparison of methods for data collection and analysis as a national and international resource as described in the first RIDER white paper report (2006):

• RIDER White Paper: Executive Summary PDF
• RIDER White Paper: Editorial in Nature.com

Summary

This dataset is a collection of raw ultrasound plane wave data from a breast mimicking phantom and a calibration phantom. The breast phantom data contains samples of hyperechoic lesions, hypoechoic lesions and no lesions. Whereas the calibration phantom contains samples to experimentally validate resolution and contrast. This dataset was acquired to do experimental validation of physics based deep learning for image registration, about which a paper is a current work in progress.

Description

Sample information

One the one hand this dataset contain 220 samples of in-vitro breast phantom ultrasound plane wave data (identified by CIRS073_RUMC). This data consists of three lesion types: hyperechoic lesions, hypoechoic lesions, and no lesions. On the other hand this dataset contains data from a calibration phantom (identified by CIRS040GSE). This data consists of: 5 samples of hypoechoic cysts, 5 samples from wire targets of 100 micrometer, 5 samples with -6dB and -3dB lesions in the field of view, and 5 samples with +3dB and +6dB in the field of view. All recordings were obtained twice: once in a low attenuating area 0.7 dB/cm/mHz, and once in a high attenuating area 0.95 dB/cm/mHz . The calibration phantom used is: Multi-Purpose Multi-Tissue Ultrasound Phantom Model 040GSE (CIRS, Norfolk, USA).

Acquisition Information

Data was acquired using a Verasonics Vantage T256 R256 system with an L12-5 50 mm linear array ultrasound transducer operating at a center frequency of 7.8 MHz. Plane wave data has been acquired consisting of 75 steering angles with an angle range of -16 degrees to +16 degrees. Verasonics scripts used for the acquisition are provided along with the data.

Image Reconstruction

The GitHub repository contains code to subsample any amount of angles from the 75 acquired angles and to do image reconstruction with the f-k migration algorithm on this dataset. This processing code is available in Python.

Involved Parties

This dataset was produced by the Computational Imaging group at Centrum Wiskunde & Informatica (CI-CWI) in Amsterdam, The Netherlands in collaboration with the Medical Ultrasound Imaging Center in Radboud UMC Nijmegen, The Netherlands.

Contact Details

r [dot] schoop [at] nki [dot] nl

Analyzed data from the serpentine Doppler phantom. The variable Acq consists of structures of the image data as they were originally acquired, and Registered moves each dataset from Acq to their respective location within the co-registered volume. Each structure contains relevant metadata for reconstruction of the 3D volume.

This Datasets is from a Traveling Human Phantom (THP) dataset that was collected for a multi-site neuroimaging reliability study. The THP dataset includes repeated multi-modal magnetic resonance (MR) images obtained for five healthy controls performed at eight imaging centers. The modalities include diffusion weighted images (DWI) and three-dimensional T1 weighted MP-RAGE and T2 SPACE sequences. Intra-subject and inter-site variability for MRI scans was and can be assessed as repeated images were taken across multiple imaging protocols.

Another use for the THP dataset could be to evaluate and improve one's tool against multi-modal and multi-site data. In addition to the THP dataset, which is useful as it is, we share our processed results. DWI datasets were processed to produce common rotationally invariant scalar images and diffusion tensor images. Anatomical images, T1 and T2, were processed with the BRAINSTools suite to produce anatomical segmentations.

@article{magnotta2012multicenter, abstract = {A number of studies are now collecting diffusion tensor imaging (DTI) data across sites. While the reliability of anatomical images has been established by a number of groups, the reliability of DTI data has not been studied as extensively. In this study, five healthy controls were recruited and imaged at eight imaging centers. Repeated measures were obtained across two imaging protocols allowing intra-subject and inter-site variability to be assessed. Regional measures within white matter were obtained for standard rotationally invariant measures: fractional anisotropy, mean diffusivity, radial diffusivity, and axial diffusivity. Intra-subject coefficient of variation (CV) was typically {\textless}1{\%} for all scalars and regions. Inter-site CV increased to {~{}}1{\%}-3{\%}. Inter-vendor variation was similar to inter-site variability. This variability includes differences in the actual implementation of the sequence.}, author = {Magnotta, Vincent a. and Matsui, Joy T. and Liu, Dawei and Johnson, Hans J. and Long, Jeffrey D. and Bolster, Bradley D. and Mueller, Bryon a. and Lim, Kelvin O. and Mori, Susumu and Helmer, Karl and Turner, Jessica a. and Lowe, Mark J. and Aylward, Elizabeth and Flashman, Laura a. and Bonett, Greg and Paulsen, Jane S.}, doi = {10.1089/brain.2012.0112}, isbn = {8605457767}, issn = {2158-0014}, journal = {Brain Connectivity}, keywords = {diffusion tensor,fractional anisotropy,magnetic resonance,mean diffusivity,reliability,white matter}, mendeley-groups = {ReginaThesis,BiosketchReferences,JoysThesis,JoyCrossSectionalDWI,TEMP{_}HOWES{_}RE}, month = {jan}, number = {6}, pages = {121018043201009}, pmid = {23075313}, publisher = {Mary Ann Liebert, Inc. 140 Huguenot Street, 3rd Floor New Rochelle, NY 10801 USA}, title = {{Multi-Center Reliability of Diffusion Tensor Imaging}}, url = {http://www.ncbi.nlm.nih.gov/pubmed/23075313 http://online.liebertpub.com/doi/abs/10.1089/brain.2012.0112 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3623569}, volume = {2}, year = {2012} }

Longitudinal brain scans of a single human phantom acquired on multiple MRI devices across North America over a period of 11 years. In addition to the human brain images, lego phantom scans have been acquired in parallel for quality assessments over time across sites.

Background

Radiomics, the process of extracting high-dimensional quantitative features from medical images, has demonstrated significant promise in enhancing precision diagnosis, prognosis, and personalized treatment planning. Despite its potential, one of the most critical challenges facing the field is the limited reproducibility of radiomics features. This variability is largely attributed to inconsistencies in imaging devices, acquisition protocols, and image reconstruction techniques.

Methods

This study presents the first open-access CBCT phantom dataset specifically curated to address reproducibility challenges in on-board imaging systems integrated with C-arm linear accelerators. CBCT images were acquired using a widely adopted Catphan phantom across multiple clinical devices from different vendors. Imaging parameters were systematically varied, including tube current (mAs), slice thickness, and reconstruction filters, to simulate realistic variability encountered in clinical workflows. The dataset is structured to allow researchers to evaluate and compare the impact of these variations on radiomics feature robustness.

Findings

The dataset comprises 120 CBCT image volumes collected from diverse imaging platforms, accompanied by corresponding region of interest (ROI) segmentations and radiomics features. This allows for extensive intra- and inter-vendor assessments of radiomics feature stability. The controlled setup and standardized segmentation provide a unique opportunity to benchmark radiomics workflows and test harmonization strategies.

Interpretation

By making this dataset publicly available, the study aims to support the radiomics research community in developing more reliable and reproducible analysis pipelines. It contributes to the ongoing efforts to standardize CBCT-based radiomics, enabling the generation of robust and generalizable models for clinical decision support in radiotherapy and beyond.

The Medical Imaging Phantoms Market Report is Segmented by Product Type (X-Ray Phantoms, CT Phantoms, Ultrasound Phantoms, MRI Phantoms, Nuclear Imaging Phantoms, and Others), Material (Stimulating Devices, False Organs (Anthropomorphic) and Other Materials), End User (Hospitals, Diagnostic Imaging Centers, and More), and Geography (North America, Europe, and More). The Market Forecasts are Provided in Terms of Value (USD).