Review — BUSI: Dataset of Breast Ultrasound Images

BUSI Dataset for Breast Ultrasound Images

Dataset of Breast Ultrasound Images,
BUSI, by Cairo University
2020 JDataInBrief, Over 270 Citations (Sik-Ho Tsang @ Medium)
Medical Image Analysis, Medical Imaging, Image Segmentation

• The dataset consists of the medical images of breast cancer using ultrasound scan, which is categorized into three classes: normal, benign, and malignant images.
• Breast ultrasound images can produce great results in classification, detection, and segmentation of breast cancer when combined with machine learning.
• Access: https://scholar.cu.edu.eg/?q=afahmy/pages/dataset

1. BUSI Dataset

The three classes of breast cases and the number of images in each case

• Ultrasound (US) images are generally in grayscale.
• At the beginning, the number of images collected was 1100. After performing preprocessing to the dataset, the number of images was reduced to 780 images.
• LOGIQ E9 ultrasound system and LOGIQ E9 Agile ultrasound system produce image resolution of 1280×1024.

Samples of original Ultrasound breast images dataset (Original images that are scanned by the LOGIQ E9 ultrasound system).

Samples of Ultrasound breast images dataset.

Samples of Ultrasound breast images dataset after refining.

• All images were cropped. The average image size of 500×500 pixels.
• The image annotation is added to the image name.

Samples of Ultrasound breast images and Ground Truth Images.

• A freehand segmentation is established for each image separately.

References

[2019 JDataInBrief] [BUSI]
Dataset of Breast Ultrasound Images

[Dataset] [BUSI]
https://scholar.cu.edu.eg/?q=afahmy/pages/dataset

4.3. Biomedical Image Multi-Task Learning

2018 … 2020 [BUSI] … 2021 [Ciga JMEDIA’21]

My Other Previous Paper Readings