Breast Cancer Ultrasound Images

This dataset has been created by hand for scientific and learning purposes. It is used in "Fine-tuning a Vision Transformer Model With a Custom Biomedical Dataset" in Hugging Face Cookbook.

  Dataset Details

The dataset contains total of 780 images from the following 3 classes: benign, malignant and normal. You can use this dataset for your computer vision tasks.

  Used model

You can use this fine-tuned Vision Transformer Model with… See the full description on the dataset page: https://huggingface.co/datasets/emre570/breastcancer-ultrasound-images.

The data collected at baseline include breast ultrasound images among women in ages between 25 and 75 years old. This data was collected in 2018. The number of patients is 600 female patients. The dataset consists of 780 images with an average image size of 500*500 pixels. The images are in PNG format. The ground truth images are presented with original images. The images are categorized into three classes, which are normal, benign, and malignant.

Research Curtesy: Al-Dhabyani W, Gomaa M, Khaled H, Fahmy A. Dataset of breast ultrasound images. Data in Brief. 2020 Feb;28:104863. DOI: 10.1016/j.dib.2019.104863.

https://www.kaggle.com/mohammedtgadallah/mt-small-dataset. (RAR)

We collected breast cancer ultrasound images diagnosed breast cancer in radiology of Renmin Hospital of Wuhan University from December 2020 to December 2022. The dataset contains 927 images including benign and malignant cancer from patients with the range of age 17 to 79. Meanwhile, the ethical approval of this study was approved by the ethics committee of Renmin Hospital of Wuhan University (WDRY2022-K217). Each image contains tumor regions. At the same time, the dataset has different tumor area and morphology features, including contrast, brightness, and fuzzy. In summary, we collected a breast ultrasound image for the segmentation task.

Dataset Card for Breast Ultrasound Images Dataset

  Dataset Summary

Breast cancer is one of the most common causes of death among women worldwide. Early detection helps in reducing the number of early deaths. The data reviews the medical images of breast cancer using ultrasound scan. Breast Ultrasound Dataset is categorized into three classes: normal, benign, and malignant images. Breast ultrasound images can produce great results in classification, detection, and… See the full description on the dataset page: https://huggingface.co/datasets/ShivamRaisharma/breastcancer.

Dataset

This dataset was created by Ly Tran Hoang Hieu

Released under Attribution 3.0 Unported (CC BY 3.0)

Contents

The global breast imaging market, valued at $5.79 billion in 2025, is projected to experience robust growth, driven by a rising prevalence of breast cancer, technological advancements in imaging techniques, and increasing awareness about early detection. The market's Compound Annual Growth Rate (CAGR) of 7.35% from 2025 to 2033 indicates significant expansion. Key drivers include the rising adoption of advanced imaging modalities like digital mammography, breast MRI, and ultrasound, offering improved diagnostic accuracy and reduced invasiveness. Furthermore, the increasing number of diagnostic centers and hospitals globally contributes to market growth. The market is segmented by imaging technique (mammography, ultrasound, MRI, image-guided biopsy, others) and end-users (hospitals, diagnostic centers, others). Mammography currently holds the largest market share due to its widespread use as a primary screening tool. However, the adoption of breast MRI and ultrasound is expected to increase significantly due to their superior capabilities in detecting certain types of breast lesions. Geographic segmentation reveals North America as the largest market, attributed to high healthcare expenditure and advanced healthcare infrastructure. However, Asia-Pacific is anticipated to witness the fastest growth rate due to rising healthcare awareness, increasing disposable incomes, and a burgeoning population. Growth will be further fueled by government initiatives promoting early breast cancer detection programs in developing economies. The competitive landscape is characterized by the presence of established players such as Fujifilm, GE Healthcare, Hologic, Philips, and Siemens Healthineers. These companies continuously invest in research and development to enhance existing technologies and introduce innovative solutions, thereby further driving market growth. However, factors such as high costs associated with advanced imaging techniques and the potential for false positives may restrain market expansion to some degree. Nevertheless, the overall outlook for the breast imaging market remains positive, with consistent growth anticipated throughout the forecast period driven primarily by the growing need for accurate and timely breast cancer diagnosis. The market will likely see increased focus on personalized medicine approaches integrating image analysis with genomics and proteomics to improve diagnostic and treatment outcomes. Recent developments include: In May 2022, the Barcelona Supercomputing Center (BSC) coordinated QUSTom (Quantitative Ultrasound Stochastic Tomography), a new European project that aims to introduce a new medical imaging modality based on ultrasound and supercomputing, which will complement or even replace current techniques that use X-rays such as mammograms, In March 2022, researchers at the University of Notre Dame designed a new imaging device, NearWave Imager, for non-invasive breast cancer detection.. Key drivers for this market are: Growing Prevalence of Breast Cancer, Technological Advancements in the Field of Breast Imaging; Investments and Initiatives from Various Organizations in Breast Cancer Screening Campaigns. Potential restraints include: Growing Prevalence of Breast Cancer, Technological Advancements in the Field of Breast Imaging; Investments and Initiatives from Various Organizations in Breast Cancer Screening Campaigns. Notable trends are: Mammography Segment is Expected to Hold a Major Market Share in the Breast Imaging Market Over the Forecast Period.

The AISSLab Breast Cancer Dataset is a collection of mammogram images by experts from the Ma'amon's Diagnostic Centre Mammogram Images for Breast Cancer (MDCMI-BC) in Yemen. It is designed to support advancements in breast cancer research and computer-aided diagnosis (CAD) systems. To facilitate research in breast cancer detection, focusing on harmonizing AI with diverse imaging data. This dataset emphasizes improving diagnostic accuracy and is available for academic and clinical research applications.

If you are using this dataset for research purpose kindly cite the following papers:

[1] A. M. Al-Hejri, R. M. Al-Tam, M. Fazea, A. H. Sable, S. Lee, and M. A. Al-antari, “ETECADx: Ensemble Self-Attention Transformer Encoder for Breast Cancer Diagnosis Using Full-Field Digital X-ray Breast Images,” Diagnostics, vol. 13, no. 1, p. 89, Dec. 2022, doi: 10.3390/diagnostics13010089.

[2] R. M. Al-Tam, A. M. Al-Hejri, S. S. Alshamrani, M. A. Al-antari, and S. M. Narangale, “Multimodal breast cancer hybrid explainable computer-aided diagnosis using medical mammograms and ultrasound Images,” Biocybern. Biomed. Eng., vol. 44, no. 3, pp. 731–758, Jul. 2024, doi: 10.1016/j.bbe.2024.08.007.

Quantitative evaluation of BUS images of different input sizes.

Results of the Mann-Whitney U test of the proposed DAU-Net model used for segmenting tumor regions in breast images of the BUSI dataset.

Automated Breast Ultrasound Systems Market Outlook

The global market size for Automated Breast Ultrasound Systems (ABUS) was valued at approximately USD 945 million in 2023 and is projected to reach around USD 2.3 billion by 2032, growing at a robust CAGR of 10.3% during the forecast period. This significant growth can be attributed to the rising prevalence of breast cancer, increased awareness regarding early detection, and technological advancements in breast imaging techniques.

One of the primary growth factors driving the market is the increasing incidence of breast cancer worldwide. According to the World Health Organization (WHO), breast cancer is the most common cancer among women globally, which underscores the urgent need for early detection and effective treatment. Automated Breast Ultrasound Systems provide a non-invasive and highly reliable method for early diagnosis, significantly reducing mortality rates associated with late-stage breast cancer detection.

Technological advancements in the field of medical imaging are another crucial driver for the ABUS market. Innovations such as 3D imaging and artificial intelligence (AI) integration have enhanced the accuracy and efficiency of ABUS, making it a preferred choice among healthcare providers. These systems offer improved visualization of dense breast tissues, which is often a limitation with traditional mammography. This has led to higher adoption rates of ABUS in both developed and emerging economies.

Government initiatives and favorable reimbursement policies also play a vital role in market growth. Various governments are implementing screening programs and funding research to improve breast cancer detection rates. For instance, the U.S. Preventive Services Task Force (USPSTF) recommends biennial screening mammography, and several insurance companies cover the cost of supplementary screening modalities like ABUS, particularly for women with dense breast tissue. These initiatives help in making advanced diagnostic tools accessible to a larger population.

Geographically, North America holds the largest share of the ABUS market, followed by Europe and the Asia Pacific. The high prevalence of breast cancer and a well-established healthcare infrastructure are key factors contributing to the dominant market position of North America. However, the Asia Pacific region is anticipated to witness the fastest growth during the forecast period, driven by increasing healthcare expenditure, rising awareness, and improving healthcare infrastructure.

Product Type Analysis

The product type segment of the ABUS market is divided into Automated Breast Ultrasound Systems and Automated Breast Volume Scanners. Automated Breast Ultrasound Systems are widely adopted for routine breast cancer screening, especially in women with dense breast tissue where mammograms are less effective. These systems provide a comprehensive 3D image of the entire breast, improving the detection rates of small lesions and invasive cancers that might be missed by traditional imaging methods. The growing preference for non-invasive, quick, and accurate diagnostic tools is boosting the demand for Automated Breast Ultrasound Systems.

Automated Breast Volume Scanners, on the other hand, offer a more detailed volumetric analysis of breast tissue. These scanners are particularly useful in pre-operative planning and assessing the extent of disease in patients diagnosed with breast cancer. The market for Automated Breast Volume Scanners is expected to grow steadily as they provide valuable information that can guide surgical and therapeutic interventions. The integration of advanced imaging software and AI algorithms further enhances the diagnostic capabilities of these scanners, making them indispensable in modern oncology practices.

In terms of market share, Automated Breast Ultrasound Systems currently dominate the market due to their widespread application in routine screening programs. The ease of use, shorter examination time, and ability to detect minute abnormalities make them a preferred choice among radiologists and healthcare facilities. However, the Automated Breast Volume Scanners segment is expected to see significant growth due to the increasing demand for precise pre-operative evaluation tools.

Innovation in product design and functionality is also propelling the market forward. Manufacturers are focusing on developing compact, user-friendly, and cost-effective ABUS devices to cater to the needs of small and medium-sized healthcare centers. The introduction

Dataset assosiated with the MICCAI Workshop on Data Engineering in Medical Imaging paper: "Pre-training with Simulated Ultrasound Images for Breast Mass Segmentation and Classification"

🎗️ Breast Ultrasound Dataset for nnU-Net v2

This repository contains the formatted dataset for breast ultrasound segmentation, prepared for use with nnU-Net v2. The dataset has been preprocessed and structured according to the nnUNet v2 dataset format for easy training and inference.

  📌 Dataset Overview

Original Dataset: Breast Ultrasound Images Dataset Task: Breast Ultrasound Segmentation Input Data: 2D ultrasound images of the breast Target Labels: Segmentation… See the full description on the dataset page: https://huggingface.co/datasets/veyselozdemir/nnUNet-Breast-Cancer-Ultrasound.

Background: Breast ultrasound is the first choice for breast tumor diagnosis in China, but the Breast Imaging Reporting and Data System (BI-RADS) categorization routinely used in the clinic often leads to unnecessary biopsy. Radiologists have no ability to predict molecular subtypes with important pathological information that can guide clinical treatment.Materials and Methods: This retrospective study collected breast ultrasound images from two hospitals and formed training, test and external test sets after strict selection, which included 2,822, 707, and 210 ultrasound images, respectively. An optimized deep learning model (DLM) was constructed with the training set, and the performance was verified in both the test set and the external test set. Diagnostic results were compared with the BI-RADS categorization determined by radiologists. We divided breast cancer into different molecular subtypes according to hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) expression. The ability to predict molecular subtypes using the DLM was confirmed in the test set.Results: In the test set, with pathological results as the gold standard, the accuracy, sensitivity and specificity were 85.6, 98.7, and 63.1%, respectively, according to the BI-RADS categorization. The same set achieved an accuracy, sensitivity, and specificity of 89.7, 91.3, and 86.9%, respectively, when using the DLM. For the test set, the area under the curve (AUC) was 0.96. For the external test set, the AUC was 0.90. The diagnostic accuracy was 92.86% with the DLM in BI-RADS 4a patients. Approximately 70.76% of the cases were judged as benign tumors. Unnecessary biopsy was theoretically reduced by 67.86%. However, the false negative rate was 10.4%. A good prediction effect was shown for the molecular subtypes of breast cancer with the DLM. The AUC were 0.864, 0.811, and 0.837 for the triple-negative subtype, HER2 (+) subtype and HR (+) subtype predictions, respectively.Conclusion: This study showed that the DLM was highly accurate in recognizing breast tumors from ultrasound images. Thus, the DLM can greatly reduce the incidence of unnecessary biopsy, especially for patients with BI-RADS 4a. In addition, the predictive ability of this model for molecular subtypes was satisfactory,which has specific clinical application value.

Dataset

This dataset was created by Mohammed Tarek GadAllah

Contents

Definition of the abbreviations.

The global market for Automatic Breast Ultrasound Imaging Systems is experiencing robust growth, projected to reach $1883 million in 2025 and maintain a Compound Annual Growth Rate (CAGR) of 9.2% from 2025 to 2033. This expansion is driven by several key factors. The increasing prevalence of breast cancer globally necessitates more effective and efficient screening methods. Automatic systems offer advantages over traditional manual ultrasound, including improved consistency, reduced operator dependence, and potentially faster scan times, leading to increased throughput and earlier detection. Technological advancements are also contributing to market growth, with innovations in image processing, AI-powered diagnostic support, and the development of more compact and portable systems enhancing accessibility and affordability. The adoption of these systems is being fueled by rising healthcare expenditure, increasing awareness about early breast cancer detection, and favorable reimbursement policies in various regions. However, the high initial investment cost associated with these systems and the need for skilled professionals to interpret the results could pose challenges to broader adoption, particularly in resource-constrained settings. The competitive landscape features established players like Siemens and GE alongside emerging innovative companies like Delphinus Medical Technologies and iSono Health. These companies are focusing on product innovation, strategic partnerships, and geographic expansion to gain market share. The segmental breakdown of the market (though not explicitly provided) likely includes distinctions based on system type (e.g., 2D, 3D, elastography), application (screening, diagnostic), and end-user (hospitals, clinics, imaging centers). Regional variations in market growth are expected, with developed regions like North America and Europe likely leading the adoption, followed by emerging markets in Asia-Pacific and Latin America, driven by increasing healthcare infrastructure investments and rising awareness. Further market expansion will depend on the continued innovation of automated features to improve diagnostic accuracy, streamline workflows, and reduce costs. The long-term outlook remains positive, underpinned by the escalating global burden of breast cancer and the continuous improvement of the technology.

The formula of performance measure.

The global 3D breast ultrasound diagnostic system market is experiencing steady growth, projected to reach a value of $118.3 million in 2025 and maintain a Compound Annual Growth Rate (CAGR) of 3.8% from 2025 to 2033. This expansion is driven by several key factors. The increasing prevalence of breast cancer globally necessitates more accurate and efficient diagnostic tools, fueling demand for advanced imaging technologies like 3D ultrasound. Improved image quality and the ability to detect subtle abnormalities compared to traditional 2D ultrasound contribute significantly to its adoption. Furthermore, the rising awareness among women about breast health and the increasing accessibility of advanced imaging systems in both developed and developing countries are bolstering market growth. Technological advancements leading to more compact, portable, and user-friendly systems also play a crucial role. While the market faces some restraints, such as the high initial investment cost associated with adopting this technology and the need for skilled professionals for accurate interpretation of the images, the overall market trajectory remains positive. Key players like QT Imaging and iSono Health are actively contributing to market expansion through innovation and market penetration. The market's steady growth trajectory suggests a promising future for 3D breast ultrasound diagnostic systems. Factors like continuous technological advancements resulting in enhanced image clarity, reduced examination times, and improved patient comfort will likely fuel further market expansion. The integration of AI and machine learning into these systems for automated analysis and improved diagnostic accuracy will also play a significant role in shaping the market. While regulatory approvals and reimbursement policies influence market penetration, the overall positive impact of early and accurate breast cancer detection will ensure the sustained demand for these systems throughout the forecast period. The relatively low market penetration rate indicates significant untapped potential for growth, particularly in emerging economies with growing healthcare infrastructure.

Introduction

The Automated Breast Ultrasound Systems (ABUS) market is projected to grow from USD 1.9 billion in 2024 to approximately USD 4.8 billion by 2034. This represents a strong compound annual growth rate (CAGR) of 9.7% during the forecast period. The increasing global focus on early breast cancer detection and rising awareness among women about regular screenings are key elements contributing to this growth. ABUS offers valuable advantages over traditional methods, especially for women with dense breast tissue, where standard mammography may be less effective in detecting abnormalities.

One of the primary drivers of the ABUS market is the rising incidence of breast cancer. According to the World Health Organization (WHO), breast cancer remains the most frequently diagnosed cancer among women worldwide. Early detection is critical in improving survival rates. ABUS provides detailed and consistent three-dimensional imaging, which improves diagnostic accuracy. It is particularly effective in identifying lesions that might be missed with conventional two-dimensional mammograms, making it an essential tool in modern breast cancer screening protocols.

Technological advancements have significantly enhanced the performance of ABUS devices. These systems now offer automated scanning and AI-assisted image analysis. This helps radiologists detect anomalies more efficiently and reduces the chances of human error. AI integration also speeds up workflow in imaging centers, ensuring quicker turnaround times for results. As hospitals and diagnostic clinics increasingly invest in advanced imaging technologies, the demand for ABUS is expected to continue its upward trajectory.

Government support through screening initiatives and regulatory approvals has also encouraged the use of ABUS. For instance, the U.S. Food and Drug Administration (FDA) has cleared devices like the SoftVueâ„¢ system to be used alongside mammography for better screening of dense breast tissue. These endorsements promote the adoption of ABUS systems in clinical practice. Additionally, many public health agencies have implemented awareness campaigns emphasizing the importance of early detection, further supporting ABUS deployment in national screening strategies.

Another factor driving market growth is the patient-friendly nature of the procedure. ABUS is non-invasive and free from radiation exposure, making it safer for regular use. The scanning process is generally comfortable and quicker than traditional methods, which encourages more women to undergo periodic screenings without hesitation. This aspect is crucial for increasing patient compliance and expanding the reach of screening programs, particularly in underserved areas. Together, these trends position ABUS as a vital tool in the global effort to combat breast cancer through early detection.