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

low quality

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

a partial scan as accessable by ultrasound imaging as well as full bone model computed by a statistical shape model is provided.

Confusion matrix and performance statistics of BUSClean performance on the case study dataset/BUSI dataset [22].

Snapshot img

Ultrasound Equipment Market Size 2025-2029

The ultrasound equipment market size is forecast to increase by USD 3.27 billion, at a CAGR of 6.5% between 2024 and 2029.

The market is driven by the expanding applications of ultrasound technology beyond traditional diagnostic uses. This includes areas such as therapeutic interventions, image-guided procedures, and non-invasive surgeries. Another significant trend shaping the market is the integration of Artificial Intelligence (AI) into ultrasound systems, enabling advanced image analysis and diagnosis. However, the market faces challenges due to the saturation in developed markets, where the majority of the population already has access to ultrasound technology. To capitalize on opportunities and navigate these challenges, companies must focus on innovation, expanding their customer base in emerging markets, and collaborating with healthcare providers to offer comprehensive solutions.
By addressing these trends and challenges, players in the market can effectively contribute to the advancement of healthcare and improve patient outcomes.

What will be the Size of the Ultrasound Equipment Market during the forecast period?

Explore in-depth regional segment analysis with market size data - historical 2019-2023 and forecasts 2025-2029 - in the full report.
Request Free Sample

The market continues to evolve, driven by advancements in technology and expanding applications across various sectors. Ultrasound guided biopsy, a minimally invasive diagnostic procedure, is increasingly being adopted in healthcare settings. Ultrasound systems are being integrated with high-frequency ultrasound for improved imaging in various fields, including vascular and obstetric applications. Ultrasound guided surgery and telehealth are revolutionizing the way medical procedures are performed and delivered. Real-time imaging and signal processing are key features enhancing the diagnostic accuracy of ultrasound imaging.

Ultrasound biopsy and guided drainage are essential interventions in the management of various conditions. The integration of ultrasound technology with robotics, telemedicine, injections, therapy, cryosurgery, biometrics, and contrast agents is expanding its reach and potential. The dynamic nature of this market ensures continuous innovation and growth.

How is this Ultrasound Equipment Industry segmented?

The ultrasound equipment industry research report provides comprehensive data (region-wise segment analysis), with forecasts and estimates in 'USD million' for the period 2025-2029, as well as historical data from 2019-2023 for the following segments.

End-user

  Hospitals
  Imaging centers
  Research centers
  Others


Product Type

  Stationary ultrasound equipment
  Portable ultrasound equipment


Application

  Diagnostic
  Therapeutic


Technology

  2D Ultrasound
  3D Ultrasound
  4D Ultrasound
  Doppler Ultrasound


Component

  Transducers/Probes
  Workstations
  Software
  Accessories


Geography

  North America

    US
    Canada


  Europe

    France
    Germany
    Italy
    UK


  Middle East and Africa

    UAE


  APAC

    China
    India
    Japan
    South Korea


  South America

    Brazil


  Rest of World (ROW)

.

By End-user Insights

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

The market encompasses various applications, including abdominal ultrasound, vascular ultrasound, obstetric ultrasound, and ultrasound guided procedures such as biopsy, drainage, and surgery. Ultrasound scanners utilize high-frequency and low-frequency ultrasound waves to produce real-time imaging, enabling early and accurate diagnosis. Ultrasound imaging is essential in guiding minimally invasive procedures, such as ultrasound-guided injections, osteotomy, and cryosurgery. Advancements in technology have led to the development of innovative ultrasound equipment, including 4D ultrasound, ultrasound transducers, and robotic systems. Ultrasound guided telehealth and telemedicine have gained popularity, expanding access to diagnostic services in remote areas. Image processing and signal processing technologies enhance the accuracy and quality of ultrasound images.

Ultrasound contrast agents improve the visualization of internal structures, particularly in complex cases. High-end private hospitals invest in the latest ultrasound equipment due to their focus on providing advanced diagnostic and therapeutic services to high-income patients. In contrast, government general hospitals face budget constraints and rely on diagnostic centers for sophisticated equipment. Ultrasound guided biofeedback and biometrics applications offer potential for improved patient care and outcomes. Doppler ultrasound and ultrasound software are essential tools for diagnosing vascular diseases and processing ultrasound data, resp

DukeUltrasound is an ultrasound dataset collected at Duke University with a Verasonics c52v probe. It contains delay-and-sum (DAS) beamformed data as well as data post-processed with Siemens Dynamic TCE for speckle reduction, contrast enhancement and improvement in conspicuity of anatomical structures. These data were collected with support from the National Institute of Biomedical Imaging and Bioengineering under Grant R01-EB026574 and National Institutes of Health under Grant 5T32GM007171-44. A usage example is available here.

To use this dataset:

import tensorflow_datasets as tfds

ds = tfds.load('duke_ultrasound', split='train')
for ex in ds.take(4):
 print(ex)

See the guide for more informations on tensorflow_datasets.

Confusion matrix and performance statistics of BUSClean performance on the internal test dataset.

Snapshot img

3D Vascular Ultrasound Imaging Market Size 2024-2028

The 3d vascular ultrasound imaging market size is forecast to increase by USD 383.8 million, at a CAGR of 4.5% between 2023 and 2028.

The market is experiencing significant growth, driven by the increasing adoption of virtual reality (VR) devices in the healthcare industry. The integration of VR technology in ultrasound imaging enhances the diagnostic accuracy and enables a more immersive experience for medical professionals. This trend is expected to continue as VR technology advances and becomes more accessible. However, the market faces challenges from the stringent regulatory process. Regulatory bodies require extensive testing and approval processes for new imaging technologies, which can delay market entry and increase costs for manufacturers.
Additionally, ensuring compliance with these regulations can be a complex and time-consuming process. Companies seeking to capitalize on market opportunities must navigate these challenges effectively, investing in robust regulatory strategies and staying informed of evolving regulatory requirements.

What will be the Size of the 3D Vascular Ultrasound Imaging 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 advancements in technologies such as temporal resolution enhancement, power doppler imaging, plaque characterization, intravascular ultrasound, plaque volume measurement, and image segmentation methods. These innovations enable more precise and detailed visualization of blood vessels, enhancing procedural guidance and clinical decision support. Blood flow velocity assessment through 3D vessel reconstruction and contrast-enhanced ultrasound is increasingly utilized in various sectors, including cardiology and radiology. Ultrasound transducer array technology and motion artifact reduction techniques contribute to improved image quality, while quantitative parameters and diagnostic accuracy are enhanced through the application of artificial intelligence algorithms. Strain imaging and deep learning applications are emerging trends in the market, offering potential for enhanced angiogenesis assessment, stenosis quantification, and shear wave elastography.

Vessel wall analysis and 3D visualization software enable more comprehensive vascular assessments, while 3D volume rendering and spatial resolution enhancement contribute to a more comprehensive understanding of complex vascular structures. The ongoing development of noise reduction algorithms, image registration techniques, tissue harmonic imaging, and adaptive filtering continues to refine the capabilities of 3D vascular ultrasound imaging, enabling more accurate and reliable assessments of microvascular flow and vessel lumen diameter. Continuous innovation in this field is expected to drive market growth and expand its applications across various sectors.

How is this 3D Vascular Ultrasound Imaging Industry segmented?

The 3d vascular ultrasound imaging 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.

Application

  Vascular imaging
  Fetal cardiac
  Gynecology
  Opthalmology
  Others


Geography

  North America

    US
    Canada


  Europe

    Germany
    UK


  APAC

    China


  Rest of World (ROW)

By Application Insights

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

The market is experiencing notable advancements, driven by the integration of several innovative technologies. Temporal resolution enhancement enables more accurate and precise imaging, while power doppler imaging improves the detection of low-velocity blood flow. Plaque characterization and intravascular ultrasound offer enhanced insights into plaque morphology and volume measurement. Image segmentation methods facilitate automated analysis, and blood flow velocity assessment is crucial for diagnosing various vascular conditions. Three-dimensional vessel reconstruction provides a more comprehensive understanding of complex vascular structures, and contrast-enhanced ultrasound enhances image contrast for better visualization. Ultrasound transducer arrays offer higher resolution, and motion artifact reduction techniques ensure image clarity.

Quantitative parameters, clinical decision support, and procedural guidance enable more accurate diagnoses and treatment planning. Advanced imaging fusion techniques, artificial intelligence algorithms, strain imaging, deep learning applications, and contrast agent kinetics contribute to improved diagnostic accuracy. Shear wave elastography, v

Abstract Background Lower limb edema has both systemic and local causes. Using software to differentiate the origin of edema in ultrasound images is an innovation. Objective To determine the parameters for using software to differentiate edema of venous and/or lymphatic origin in ultrasound images of the lower limbs. Method This is a cross-sectional, quantitative, analytical study with non-probabilistic sampling by convenience. Data were collected by patient interview, physical examination, ultrasound examination, and analysis of software for tissue characterization in ultrasound image by means of quantification of echogenicity and Gray Scale Median (GSM). Results The sample comprised 42 lower limbs with venous edema, 35 with lymphatic edema, 14 with mixed edema, and 11 control limbs. The distributions of pixels in echogenicity intervals by group was as follows. In the venous edema group, 88.31% were distributed from hypoechogenic interval IV to echogenic interval III; in the lymphatic edema group 71.73% were from hypoechogenic interval II to echogenic interval I; in the mixed edema group 76.17% were from hypoechogenic interval III to echogenic interval II; and in the control group 84.87% were distributed from echogenic interval II to hyperechogenic interval I. Mean and standard deviation of GSM values showed statistical differences between groups. Conclusion The CATUS software enabled differentiation of the type of lower limb edema, facilitating diagnosis of edema type and, consequently, choice of the best therapeutic option.

References - Li, Fu, Umberto Villa, Seonyeong Park, and Mark A. Anastasio. "3-D stochastic numerical breast phantoms for enabling virtual imaging trials of ultrasound computed tomography." IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control 69, no. 1 (2021): 135-146. DOI: 10.1109/TUFFC.2021.3112544 - Li, Fu; Villa, Umberto; Park, Seonyeong; Anastasio, Mark, 2021, "2D Acoustic Numerical Breast Phantoms and USCT Measurement Data", https://doi.org/10.7910/DVN/CUFVKE, Harvard Dataverse, V1 Overview - This dataset includes 1,089 two-dimensional slices extracted from 3D numerical breast phantoms (NBPs) for ultrasound computed tomography (USCT) studies. The anatomical structures of these NBPs were obtained using tools from the Virtual Imaging Clinical Trial for Regulatory Evaluation (VICTRE) project. The methods used to modify and extend the VICTRE NBPs for use in USCT studies are described in the publication cited above. - The NBPs in this dataset represent the following four ACR BI-RADS breast composition categories: > Type A - The breast is almost entirely fatty > Type B - There are scattered areas of fibroglandular density in the breast > Type C - The breast is heterogeneously dense > Type D - The breast is extremely dense - Each 2D slice is taken from a different 3D NBP, ensuring that no more than one slice comes from any single phantom. File Name Format - Each data file is stored as an HDF5 .mat file. The filenames follow this format: {type}{subject_id}.mat where{type} indicates the breast type (A, B, C, or D), and {subject_id} is a unique identifier assigned to each sample. For example, in the filename D510022534.mat, "D" represents the breast type, and "510022534" is the sample ID. File Contents - Each file contains the following variables: > "type": Breast type > "sos": Speed-of-sound map [mm/μs] > "den": Ambient density map [kg/mm³] > "att": Acoustic attenuation (power-law prefactor) map [dB/ MHzʸ mm] > "y": power-law exponent > "label": Tissue label map. Tissue types are denoted using the following labels: water (0), fat (1), skin (2), glandular tissue (29), ligament (88), lesion (200). - All spatial maps ("sos", "den", "att", and "label") have the same spatial dimensions of 2560 x 2560 pixels, with a pixel size of 0.1 mm x 0.1 mm. - "sos", "den", and "att" are float32 arrays, and "label" is an 8-bit unsigned integer array.

This dataset contains supplemental material to the research article: "Colour Doppler study of blood flow in the portal vein in relation to blood flow in the milk vein, milk yield and body condition of dairy cows during dry period and lactation".

Dataset contents explained:

1. Portal Vein Blood FLow (.avi) - video of color Doppler examination of blood flow in the portal vein of dairy cows

2. Table 3 (.pdf) - Descriptive statistics of milk vein blood flow volume (MV_BFVol), body condition score (BCS), backfat thickness (BFT) and heart girth (HG) circumference of the dairy cows included in the study, stratified by production stage (late lactation, dry period, early lactation).

3. Tables 4, 5, 6 (.pdf): Ingredients, chemical composition and nutritive value of the total mixed rations provided for the: High Lactation, Low Lactation, and Close-Up (dry period) groups.

4. Fig. 6 (.tiff) - Cross Sectional Area (CSA) of the portal vein: Changes throughout the study period: starting from 7 days before the dry period (“DP”), throughout the DP, 7 and 3 days prior to calving, at calving (“C”) and from the 3rd to the 90th day in the new lactation (“DIM”: days in milk).

5. Fig. 7 (.tiff) - Diameter of the Portal Vein: Changes throughout the study period: starting from 7 days before the dry period (“DP”), throughout the DP, 7 and 3 days prior to calving, at calving (“C”) and from the 3rd to the 90th day in the new lactation (“DIM”: days in milk).

6. Fig. 8 (.tiff) - Distance of the Portal Vein from skin surface: Changes throughout the study period: starting from 7 days before the dry period (“DP”), throughout the DP, 7 and 3 days prior to calving, at calving (“C”) and from the 3rd to the 90th day in the new lactation (“DIM”: days in milk).

7. BFT example (.bmp) - B-mode ultrasound measurement of backfat thickness of a dairy cow (according to Schroeder and Staufenbiel, 2006)

8. Power Analyses (a-priori and post-hoc) (.pdf)

This is the second part of the Challenge dataset. Link to first part; Link to third part. Link to validation dataset.

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 train dataset contains 1200 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:

The dataset contains 50 folders (one subject per folder), each with 24 scans. Each .h5 file corresponds to one scan, storing image and transformation of each frame within this scan. Key-value pairs in 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.

“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: “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.

Calibration matrix: 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”.

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 note the following publication policy mentioned in the Challenge proposal:

We are planning to submit a paper including challenge dataset summary and results analysis. Members of the top five participating teams will be invited as co-authors.

The participating teams can only publish their novel methodology without discussion of data and obtained results if the above mentioned paper is not published (submission to arXiv is considered as a sufficient waiting period). Once the challenge paper from the organising team is published, the participants should cite this challenge paper if their work has not been published.

After we publish the summary paper of the challenge, if you use our dataset in your publication, please cite the summary paper (reference will be provided once published) and some of the following 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.

Sample characteristics for the internal test and case study (BUSI) [22] datasets.

According to Cognitive Market Research, The Global Ultrasound Machines Market size is USD 9.3 billion in 2023 and will grow at a compound annual growth rate (CAGR) of 5.9% from 2023 to 2030.

Technological advancements boost ultrasound market growth by improving image quality, portability, and diagnostic accuracy, increasing adoption and reducing healthcare costs.
The growing global aging population requires more ultrasound imaging for age-related health issues, fueling the demand for ultrasound machines, which play a crucial role in diagnosing and monitoring conditions like cardiovascular diseases, arthritis, and cancer, making them an integral part of modern healthcare.
ASCs and others (Ambulatory Surgical Centers and similar facilities) are rapidly growing due to the increasing demand for outpatient care and cost-effective specialized medical services, driving the essential role of ultrasound machines in diagnostics and minimally invasive procedures.
North America will continue to lead, whereas the Asia Pacific Ultrasound Machines Market will experience the strongest growth until 2030.

Technological Advancements Fueling Ultrasound Machines Market Growth

Continuous technological advancements drive the ultrasound machines market. Innovations in transducer technology, image processing algorithms, and miniaturization have led to more portable, affordable, and versatile ultrasound devices. Advanced transducers employ materials like piezoelectric crystals, enhancing image quality and sensitivity. Sophisticated image processing algorithms provide sharper images and real-time data analysis, aiding in precise diagnoses. Miniaturization allows for handheld and point-of-care ultrasound devices, increasing accessibility and affordability. These advancements enable healthcare providers to offer better diagnostic capabilities and expand ultrasound applications, resulting in increased adoption and market growth. Enhanced image quality improves diagnostic accuracy, leading to better patient outcomes and reduced healthcare costs. Portable devices empower healthcare professionals to perform ultrasounds in diverse settings, from rural clinics to emergency rooms, increasing the overall demand for ultrasound equipment. As technology continues to evolve, the ultrasound machine market is poised for sustained expansion and innovation.

Aging Population Drives Ultrasound Market Growth

The global aging population is expanding, leading to a greater need for medical imaging, including ultrasound, for age-related health issues and conditions. This demographic shift is driven by increased life expectancy, reduced birth rates, and improvements in healthcare. As the elderly population increases, healthcare facilities require more ultrasound machines to address senior healthcare needs. Ultrasound plays a crucial role in diagnosing and monitoring age-related conditions like cardiovascular diseases, arthritis, and cancer. Moreover, it is a preferred imaging modality for its non-invasive nature, making it ideal for elderly patients. This rising demand for senior care fuels the growth of the ultrasound machines market, making it an integral component of modern healthcare systems worldwide.

Market Dynamics of Ultrasound Machines

High Equipment Costs will Limit Market Expansion

Ultrasound machines' advanced technology results in substantial production expenses, driving up equipment costs. This financial barrier restricts healthcare facilities' ability to invest in advanced ultrasound technology, particularly affecting smaller clinics and resource-limited regions, ultimately limiting patient access to high-quality diagnostics and hindering market growth.

Impact of COVID–19 on the Ultrasound Machines Market

The surge in infectious diseases, primarily COVID-19 cases, during the pandemic caused hospitals to prioritize emergency protocols over elective procedures. While elective ultrasound procedures decreased, the adoption of emergency imaging services like X-rays, CT scans, and ultrasounds increased significantly, especially for lung assessments. This trend is expected to persist, with ultrasound systems playing a crucial role in specialized diagnoses, particularly for kidney and lung-related conditions, due to the lasting impact of COVID-19. Introduction of Ultrasound Machines

Continuous technological advancements, including enhanced transducers, advanced image processing algo...

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.

After we publish the summary paper of the challenge, if you use our dataset in your publication, please cite the summary paper (reference will be provided once published) and the following article:

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.

Example axial and coronal phase maps and post-treatment MRI from 68 thalamotomies in essential tremor patients and four pallidotomies in Parkinson's disease patients. From the manuscript "Using phase data from MR temperature imaging to visualize anatomy during MRI-guided focused ultrasound neurosurgery" published in 2020 in IEEE Trans. Med. Imaging.

Snapshot img

Ultrasound Transducer Market Size 2024-2028

The ultrasound transducer market size is forecast to increase by USD 838.3 million, at a CAGR of 4.5% between 2023 and 2028.

The market is experiencing significant growth, driven by the increasing prevalence of chronic diseases and the growing focus on developing pocket-sized ultrasound devices. The rising incidence of chronic conditions necessitates frequent diagnostic imaging, leading to a surge in demand for ultrasound transducers. Furthermore, advancements in technology have enabled the production of compact, portable ultrasound devices, making diagnostic imaging more accessible and convenient for healthcare professionals. However, the market faces challenges, primarily due to the high costs associated with ultrasound systems. The expensive nature of these systems may hinder their widespread adoption, particularly in developing countries and low-income communities.
Additionally, the intense competition among market players may put pressure on prices, further limiting profitability. To capitalize on market opportunities and navigate these challenges effectively, companies must focus on offering cost-effective solutions while maintaining high-quality standards. By doing so, they can cater to the evolving needs of healthcare providers and patients alike, ensuring long-term growth and success in the market.

What will be the Size of the Ultrasound Transducer 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 is characterized by its continuous evolution and dynamic nature, driven by advancements in technology and expanding applications across various sectors. Ultrasound equipment utilizes transducers to convert electrical energy into mechanical waves, enabling real-time imaging and diagnostic capabilities. These transducers are integral to various ultrasound applications, including harmonic imaging, transcranial ultrasound, and 3D ultrasound imaging. Ultrasound contrast agents, such as micro-bubble contrast agents, enhance image resolution and provide better tissue characterization in diagnostic imaging. Ultrasound biopsy, a minimally invasive procedure, relies on high-intensity focused ultrasound and shear wave elastography for accurate tissue diagnosis. Regulatory approvals, including CE marking and FDA approval, play a crucial role in market growth, ensuring safety and efficacy of ultrasound systems and transducers.

Ultrasound data processing, image analysis, and ultrasound software are essential components that enable real-time interpretation and analysis of ultrasound data. In interventional radiology and vascular medicine, ultrasound guidance is increasingly used for surgical navigation and therapeutic applications. Ultrasound therapy, including ultrasound tomography and ultrasound elastography, offers new treatment modalities for various conditions. The market for ultrasound transducers is further propelled by ongoing research and development in areas such as ultrasound spectroscopy, ultrasound data acquisition, and clinical trials. Piezoelectric crystals, acoustic impedance, and dynamic range are critical factors influencing transducer design and performance. Ultrasound imaging applications span numerous sectors, including musculoskeletal imaging, obstetrics and gynecology, and diagnostic imaging. The integration of advanced technologies, such as Doppler ultrasound and color doppler imaging, further expands the potential of ultrasound transducers in clinical practice.

How is this Ultrasound Transducer Industry segmented?

The ultrasound transducer 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.

Type

  Convex
  Linear
  Endocavitary
  Phased array
  CW doppler


Geography

  North America

    US
    Canada


  Europe

    Germany
    UK


  APAC

    China


  Rest of World (ROW)

.

By Type Insights

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

The market encompasses various technologies, including ultrasound microscopy, tissue characterization, harmonic imaging, and transducer arrays. Piezoelectric crystals are a fundamental component of ultrasound probes, converting electrical energy into mechanical waves that penetrate tissue. Ultrasound data processing and software enable dynamic range and image resolution enhancements, while ultrasound guidance and data acquisition are essential for clinical trials and interventional radiology procedures. Focused ultrasound, contrast-enhanced ultrasound, and strain imaging are advanced applications driving market growth. Convex transducers, which ma

This study investigates the feasibility of reducing manual image annotation costs in medical image database construction by utilizing a step by step approach where the Artificial Intelligence model (AI model) trained on a previous batch of data automatically pre-annotates the next batch of image data, taking ultrasound image of thyroid nodule annotation as an example. The study used YOLOv8 as the AI model. During the AI model training, in addition to conventional image augmentation techniques, augmentation methods specifically tailored for ultrasound images were employed to balance the quantity differences between thyroid nodule classes and enhance model training effectiveness. The study found that training the model with augmented data significantly outperformed training with raw images data. When the number of original images number was only 1,360, with 7 thyroid nodule classifications, pre-annotation using the AI model trained on augmented data could save at least 30% of the manual annotation workload for junior physicians. When the scale of original images number reached 6,800, the classification accuracy of the AI model trained on augmented data was very close with that of junior physicians, eliminating the need for manual preliminary annotation.

Transmission ultrasound data simulated using the k-Wave toolbox as a benchmark for biomedical quantitative ultrasound tomography using a ray approximation to Green's function

The folder ‘’simulation’’ includes the transmission ultrasound data sets used in the project:https://github.com/Ash1362/ray-based-quantitative-ultrasound-tomography. In the Github link, the associated project can be found in the branch master in the folder r-Wave #V1.1. (The folder ‘’data_ust_kWave_transmission.zip’’ is deprecated.)

...........................................................................................

The ultrasound data were simulated using the k-Wave toolbox (version 1.3.) [5] and using a digital breast phantom [4]. In k-Wave version 1.4., no changes have been reported that affects the simulations. The simulations were done assuming isotropic point sources.

The folder ‘’simulation’’ must be added to the path:

''…r-Wave/data/simulation/…''

For running the Matlab example scripts in the project in the github, the user has two choices:

Simulate the k-Wave ultrasound data by setting data_sim=true; in the examples in the project.

Upload the already simulated k-Wave ultrasound data according to the description below and load them by setting data_sim=false; in the examples in the project.

Please read the description in the example scripts!

…………………………………………………………………………………

The folder simulation includes 2 subfolders, ‘’phantom’’ and ‘’data_ust_kWave_transmission’’.

1) The subfolder ‘’simulation/phantom’’ includes ‘’OA-BREAST’’.

In the project: https://anastasio.bioengineering.illinois.edu/downloadable-content/oa-breast-database/,

the user must upload the folder ‘’Neg_47_Left’’ , and add it as ‘’r-wave/data/simulation/phantom/OA-BREAST/Neg_47_Left/’’.

.......................................................................................................................................................................

2) The subfolder ‘’simulation/data_ust_kWave_transmission’’ includes 2 subfolders, ‘’2D’’ and ‘’3D’’ .

The subfolder ‘’2D’’ includes:

data_ust_kWave_transmission/2D/PulsePammoth_1_dx4_cfl1_Nr256_Ne64_Interpoffgrid_Transgeompoint_Absorption1_CodeMatlab/data4_sphere_nonsmooth.mat

Two transmission ultrasound data sets were simulated using the k-wave for only water and breast in water according to section ‘’6.1. data simulation’’ in [1]. 64 emitters and 256 receivers are simulated as off-grid points which are placed on a 2D circular ring. (The characters ‘’_sphere_’’ are added to indicate that the transducers are placed on a ring.) To simulate the data, each emitter was individually driven by an excitation pulse, and the induced acoustic pressure time series were recorded on all the receivers. The k-Wave simulation was performed on a grid with grid spacing 0.4 mm, and the time spacing was set using a CFL number 0.1. The acoustic absorption and dispersion were accounted for based on the frequency power law. This data set is used for the purpose of image reconstruction, and therefore, the sound speed and absorption coefficients maps are not smoothed, i.e., the original maps are used for simulations. This data set can be used for image reconstruction using the time-of-flight-based approach and then the Green's approach.

data_ust_kWave_transmission/2D/PulsePammoth_1_dx4_cfl1_Nr256_Ne64_Interpoffgrid_Transgeompoint_Absorption1_CodeMatlab/data4_plane_nonsmooth.mat

Two transmission ultrasound data sets were simulated using the k-wave for only water and breast in water. 64 emitters and 256 receivers are simulated as off-grid points which are placed on 16 planar arrays which are all aligned with a circle. Each planar array includes 4 emitters and 16 receivers. Therefore, in contrast with the data mentioned above, the ray linking is performed using the line equations defining the 2D geometry of the linear arrays. (The characters ‘’_plane_’’ are added to indicate that the transducers are placed on line.) To simulate the data, each emitter was individually driven by an excitation pulse, and the induced acoustic pressure time series were recorded on all the receivers. The k-Wave simulation was performed on a grid with grid spacing 0.4 mm, and the time spacing was set using a CFL number 0.1. The acoustic absorption and dispersion were accounted for based on the frequency power law. This data set is used for the purpose of image reconstruction, and therefore, the sound speed and absorption coefficients maps are not smoothed, i.e., the original maps are used for simulations. This data set can be used for image reconstruction using the time-of-flight-based approach, but ahs not been extended to the Green's approach yet. The image reconstruction should be slower than the circular array. the reason is for circular array, for each emitter, the raylinking problem is solved for all receivers once using the equation of circle. However, for this data set, for each emitter, the ray linking problem is solved for each receiver array separately, because receiver arrays are defined with different line equations.

data_ust_kWave_transmission/2D/PulsePammoth_1_dx4_cfl1_Nr256_Ne64_Interpoffgrid_Transgeompoint_Absorption1_CodeMatlab/data4_sphere_smooth_17_1.mat

Two transmission ultrasound data sets were simulated using the k-Wave for only water and breast in water as the benchmark for validation of ray approximation to Green’s function in homogeneous and heterogenous media, respectively. The simulation was performed according to section ‘’6.2. Numerical validation of the ray approximation to the Green’s function’’ in [1].

64 emitters and 256 receivers are simulated as off-grid points which are placed on a 2D circular ring. (The characters ‘’_sphere_’’ are added to indicate that the transducers are placed on a ring.) The pressure field was produced by emitter 1 (of the 64 emitters) and was recorded in time on all 256 receivers. The k-Wave simulation was performed on a grid with grid spacing 0.4 mm, and the time spacing was set using a CFL number 0.1. The acoustic absorption and dispersion were accounted for based on the frequency power law. The sound speed and absorption coefficient maps were smoothed by an averaging window of size 17 grid points. This data set is used as the benchmark for measuring accuracy of ray approximation to Green’s function for computing phase and amplitude of the pressure field on the receivers.

data_ust_kWave_transmission/2D/PulsePammoth_1_dx4_cfl1_Nr256_Ne64_Interpoffgrid_Transgeompoint_Absorption1_CodeMatlab/data4_sphere_smooth_17_20.mat

This data set is the same as data4_smooth_17_1 except the pressure field is produced by emitter 20.

………………………………………………………………………………………………………………….

The subfolder ‘’3D’’ includes:

data_ust_kWave_transmission/3D/PulsePammoth_1_dx5_cfl1_Nr4096_Ne1024_Interpnearest_Transgeompoint_Absorption0_CodeCUDA/data5_sphere_nonsmooth_tof_singram.mat

The discrepancy of time-of-flight data for two transmission ultrasound data sets simulated by the k-wave for breast in water and only water according to section 5.2 in [3]. The pressure fields were produced by 1024 emitters separately and were recorded on 4096 receivers. The emitters and receivers were simulated as points which are placed on a 3D hemispherical surface, and are interpolated onto the grid using a neighboring interpolation. The k-Wave simulations were performed on a grid with grid spacing 0.5 mm, and the time spacing was set using a CFL number 0.1. The time-of-flight data were computed and will be used for a refraction-corrected image reconstruction of the sound speed based on the inversion approach proposed in [3].

References

1 - A. Javaherian, ❝Hessian-inversion-free ray-born inversion for high-resolution quantitative ultrasound tomography❞, 2022, https://arxiv.org/abs/2211.00316/ .

2 - A. Javaherian and B. Cox, ❝Ray-based inversion accounting for scattering for biomedical ultrasound tomography❞, Inverse Problems vol. 37, no.11, 115003, 2021. https://iopscience.iop.org/article/10.1088/1361-6420/ac28ed/

3- A. Javaherian, F. Lucka and B. T. Cox, ❝Refraction-corrected ray-based inversion for three-dimensional ultrasound tomography of the breast❞, Inverse Problems, 36 125010. https://iopscience.iop.org/article/10.1088/1361-6420/abc0fc/

4- Y. Lou, W. Zhou, T. P. Matthews, C. M. Appleton and M. A. Anastasio, ❝Generation of anatomically realistic numerical phantoms for photoacoustic and ultrasonic breast imaging❞, J. Biomed. Opt., vol. 22, no. 4, pp. 041015, 2017. https://anastasio.bioengineering.illinois.edu/downloadable-content/oa-breast-database/

5 - B. E. Treeby and B. T. Cox, ❝k-Wave: MATLAB toolbox for the simulation and reconstruction of photoacoustic wave fields❞, J. Biomed. Opt. vol. 15, no. 2, 021314, 2010. http://www.k-wave.org/