Related Experiment Video
Updated: Jun 11, 2025
05:56
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
2.4K
Attention based UNet model for breast cancer segmentation using BUSI dataset.
Adel Sulaiman1,2, Vatsala Anand3, Sheifali Gupta3
1Department of Computer Science, College of Computer Science and Information Systems, Najran University, Najran, 61441, Saudi Arabia.
Scientific Reports
|September 28, 2024
Summary
This study introduces an Attention U-Net model for accurate breast cancer detection in ultrasound images. The model achieved high accuracy, aiding in early diagnosis and improved patient outcomes.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Breast cancer is a leading cause of mortality, making early detection crucial for effective treatment.
- Accurate segmentation of breast tumors in ultrasound images is vital for diagnosis.
Purpose of the Study:
- To develop and evaluate an Attention U-Net model for automated breast cancer segmentation.
- To improve the accuracy and efficiency of breast cancer identification using medical imaging.
Main Methods:
- Utilized the Breast Ultrasound Image Dataset (BUSI) with 780 images (benign, malignant, normal).
- Employed an Attention U-Net architecture with encoder and decoder blocks and attention gates for feature localization.
- Focused on accurate segmentation and delineation of tumor borders.
Main Results:
- Achieved an overall accuracy of 0.98.
- Demonstrated high precision (0.97), recall (0.90), and a Dice score of 0.92.
- The model effectively delineated tumor boundaries in ultrasound images.
Conclusions:
- The Attention U-Net model shows significant potential for automated breast cancer segmentation.
- This approach can enhance diagnostic capabilities, enabling prompt and targeted medical interventions.
- Early detection through advanced AI models improves patient health outcomes.
