Introduction #
The authors of the Breast Ultrasound Images Dataset address breast cancer, a leading cause of mortality among women globally, emphasizing the importance of early detection for reducing fatalities. The dataset pertains to medical images obtained through ultrasound scans for breast cancer assessment.
The data collection process involved gathering baseline ultrasound images of breasts from women aged between 25 and 75 years. This data accumulation was conducted in the year 2018, encompassing a total of 600 female patients. The dataset comprises 780 images, each with an average size of 500 Γ 500 pixels, and is stored in PNG format. The images are systematically divided into the three classes: normal, benign, and malignant.
The procedure for dataset collection involved capturing grayscale ultrasound images, which were stored in DICOM format at Baheya hospital. This comprehensive endeavor, including image collection and annotation, spanned approximately a year. Initially, 1100 images were gathered; however, following data preprocessing, the dataset was refined to 780 images. To eliminate redundant information and improve the dataset quality, radiologists from Baheya hospital reviewed and corrected erroneous annotations. LOGIQ E9 ultrasound systems and LOGIQ E9 Agile ultrasound systems were employed for image acquisition, producing images with a resolution of 1280 Γ 1024. The transducers utilized were 1β5 MHz on an ML6-15-D Matrix linear probe.
After data collection, preprocessing was executed to enhance dataset utility. Duplicate images were removed, and incorrect annotations were rectified through expert radiologist review. Conversion from DICOM to PNG format was achieved utilizing a DICOM converter application. Refinement procedures led to a reduction in the dataset size, resulting in 780 ultrasound images. To enhance dataset quality, images were cropped to different sizes, effectively eliminating extraneous boundaries. Fast photo crops facilitated this cropping process. The inclusion of image annotation into the image name was performed, and rigorous validation by Baheya hospital radiologists ensured data integrity.
Ground truth annotation plays a pivotal role in enhancing the datasetβs utility. This annotation was carried out using Matlab, where a freehand segmentation technique was employed for each image.
Summary #
Breast Ultrasound Images is a dataset for semantic segmentation and classification tasks. It is used in the medical industry.
The dataset consists of 780 images with 647 labeled objects belonging to 2 different classes including benign and malignant.
Images in the Breast Ultrasound Images dataset have pixel-level semantic segmentation annotations. There are 133 (17% of the total) unlabeled images (i.e. without annotations). There are no pre-defined train/val/test splits in the dataset. Alternatively, the dataset could be split into 3 classification sets: benign (437 images), malignant (210 images), and normal (133 images). The dataset was released in 2021 by the Cairo University, Egypt.
Explore #
Breast Ultrasound Images dataset has 780 images. Click on one of the examples below or open "Explore" tool anytime you need to view dataset images with annotations. This tool has extended visualization capabilities like zoom, translation, objects table, custom filters and more. Hover the mouse over the images to hide or show annotations.
Class balance #
There are 2 annotation classes in the dataset. Find the general statistics and balances for every class in the table below. Click any row to preview images that have labels of the selected class. Sort by column to find the most rare or prevalent classes.
Class γ
€ | Images γ
€ | Objects γ
€ | Count on image average | Area on image average |
---|---|---|---|---|
benignβ mask | 437 | 437 | 1 | 6.7% |
malignantβ mask | 210 | 210 | 1 | 14.72% |
Co-occurrence matrix #
Co-occurrence matrix is an extremely valuable tool that shows you the images for every pair of classes: how many images have objects of both classes at the same time. If you click any cell, you will see those images. We added the tooltip with an explanation for every cell for your convenience, just hover the mouse over a cell to preview the description.
Images #
Explore every single image in the dataset with respect to the number of annotations of each class it has. Click a row to preview selected image. Sort by any column to find anomalies and edge cases. Use horizontal scroll if the table has many columns for a large number of classes in the dataset.
Object distribution #
Interactive heatmap chart for every class with object distribution shows how many images are in the dataset with a certain number of objects of a specific class. Users can click cell and see the list of all corresponding images.
Class sizes #
The table below gives various size properties of objects for every class. Click a row to see the image with annotations of the selected class. Sort columns to find classes with the smallest or largest objects or understand the size differences between classes.
Class | Object count | Avg area | Max area | Min area | Min height | Min height | Max height | Max height | Avg height | Avg height | Min width | Min width | Max width | Max width |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
benign mask | 437 | 6.7% | 51.3% | 0.28% | 24px | 4.79% | 412px | 73.46% | 107px | 21.53% | 37px | 6.1% | 685px | 98.18% |
malignant mask | 210 | 14.72% | 56.29% | 0.21% | 26px | 5.52% | 444px | 88.79% | 208px | 41.97% | 44px | 7.73% | 728px | 96.21% |
Spatial Heatmap #
The heatmaps below give the spatial distributions of all objects for every class. These visualizations provide insights into the most probable and rare object locations on the image. It helps analyze objects' placements in a dataset.
Objects #
Table contains all 647 objects. Click a row to preview an image with annotations, and use search or pagination to navigate. Sort columns to find outliers in the dataset.
Object ID γ
€ | Class γ
€ | Image name click row to open | Image size height x width | Height γ
€ | Height γ
€ | Width γ
€ | Width γ
€ | Area γ
€ |
---|---|---|---|---|---|---|---|---|
1β | benign mask | benign (124).png | 614 x 645 | 58px | 9.45% | 155px | 24.03% | 1.91% |
2β | benign mask | benign (217).png | 396 x 603 | 86px | 21.72% | 307px | 50.91% | 8.7% |
3β | malignant mask | malignant (208).png | 664 x 617 | 355px | 53.46% | 578px | 93.68% | 35.48% |
4β | benign mask | benign (43).png | 495 x 554 | 53px | 10.71% | 54px | 9.75% | 0.85% |
5β | benign mask | benign (178).png | 576 x 772 | 167px | 28.99% | 250px | 32.38% | 7.25% |
6β | benign mask | benign (56).png | 711 x 806 | 159px | 22.36% | 304px | 37.72% | 6.01% |
7β | benign mask | benign (332).png | 531 x 703 | 58px | 10.92% | 76px | 10.81% | 0.97% |
8β | benign mask | benign (135).png | 582 x 776 | 105px | 18.04% | 133px | 17.14% | 2.47% |
9β | malignant mask | malignant (55).png | 556 x 786 | 155px | 27.88% | 221px | 28.12% | 4.75% |
10β | benign mask | benign (289).png | 393 x 468 | 99px | 25.19% | 249px | 53.21% | 10.26% |
License #
Citation #
If you make use of the Breast Ultrasound Images data, please cite the following reference:
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.
If you are happy with Dataset Ninja and use provided visualizations and tools in your work, please cite us:
@misc{ visualization-tools-for-breast-ultasound-images-dataset,
title = { Visualization Tools for Breast Ultrasound Images Dataset },
type = { Computer Vision Tools },
author = { Dataset Ninja },
howpublished = { \url{ https://datasetninja.com/breast-ultasound-images } },
url = { https://datasetninja.com/breast-ultasound-images },
journal = { Dataset Ninja },
publisher = { Dataset Ninja },
year = { 2024 },
month = { dec },
note = { visited on 2024-12-08 },
}
Download #
Dataset Breast Ultrasound Images can be downloaded in Supervisely format:
As an alternative, it can be downloaded with dataset-tools package:
pip install --upgrade dataset-tools
β¦ using following python code:
import dataset_tools as dtools
dtools.download(dataset='Breast Ultrasound Images', dst_dir='~/dataset-ninja/')
Make sure not to overlook the python code example available on the Supervisely Developer Portal. It will give you a clear idea of how to effortlessly work with the downloaded dataset.
The data in original format can be downloaded here.
Disclaimer #
Our gal from the legal dep told us we need to post this:
Dataset Ninja provides visualizations and statistics for some datasets that can be found online and can be downloaded by general audience. Dataset Ninja is not a dataset hosting platform and can only be used for informational purposes. The platform does not claim any rights for the original content, including images, videos, annotations and descriptions. Joint publishing is prohibited.
You take full responsibility when you use datasets presented at Dataset Ninja, as well as other information, including visualizations and statistics we provide. You are in charge of compliance with any dataset license and all other permissions. You are required to navigate datasets homepage and make sure that you can use it. In case of any questions, get in touch with us at hello@datasetninja.com.