Home | Help Center

Endless possibilities in academia

Application of traditional methods and deep learning in breast ultrasound image segmentation

Fangfang Chen1, Miao Zhou2, Jintao Duan1, Yuxiang Wang1, Liangqing Lin4, Wenhui Guo3, Yongchu Hu5


1School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China. 2Jiangsu Cancer Hospital, Nanjing 213164, Jiangsu Province, China. 3School of Anesthesiology, Naval Medical University, Shanghai 200433, China. 4The First Hospital of Putian, Putian 351100, Fujian Province, China. 5The Department of Anesthesiology, Long March Hospital, Shanghai 200003, China.


Address correspondence to: Wenhui Guo, School of Anesthesiology, Naval Medical University, No.25 Zhongyuan Road, Shanghai 200093, China. E-mail: wendyguo17@outlook.com. Yongchu Hu, The De-partment of Anesthesiology, Long March Hospital, No.415 Fengyang Road, Shanghai 200003, China. E-mail address: Adsfoxcn@sina.com.cn.


DOI: https://doi.org/10.61189/341921wbvxvz


Received September 27, 2024; Accepted January 22, 2025; Published April 1, 2025


Highlights

● Comparison of Methods: This article compares traditional techniques, such as thresholding and edge detection, with deep learning-based methods for breast ultrasound segmentation.

● U-Net’s Effectiveness: U-Net is identified as the benchmark for medical image segmentation due to its efficiency and ability to preserve details.

● Advantages of Deep Learning: Deep learning models, like CNNs and FCNs, improve segmentation accuracy by learning directly from raw data, while also mitigating noise.

Abstract

Breast ultrasound image segmentation is vital in medical imaging, enabling precise delineation of tissues and lesions, which contributes to the diagnosis and treatment of breast diseases. This article reviews both tradition-al methods and recent advancements in deep learning techniques for breast ultrasound image segmentation. The discussion begins by highlighting the significance of image segmentation in breast disease diagnosis and its background within medical imaging. Traditional segmentation methods, such as thresholding, edge detection, and region growing, are examined, with an analysis of their applications and limitations in breast ultrasound segmen-tation. Subsequently, the focus shifts to deep learning approaches, including classic models like Convolutional Neural Networks, Fully Convolutional Networks, and U-Net, along with their improved algorithms. These methods learn hierarchical features directly from raw data, reducing reliance on manual preprocessing. U-Net, in particular, is highlighted as the benchmark for medical image segmentation due to its efficient data usage and ability to pre-serve fine-grained details. Comparative analysis demonstrates the advantages of deep learning in enhancing seg-mentation accuracy, reducing noise, and handling complex texture structures. The article concludes by summariz-ing current achievements and challenges in the field, while offering an outlook on the future developments aimed at advancing breast ultrasound image segmentation for improved diagnosis and treatment of breast diseases.

Keywords: Breast ultrasound image segmentation, medical imaging, deep learning

Chen FF, Zhou M, Duan JT, Wang YX, Lin LQ, Guo WH, Hu YC. Application of traditional methods and deep learning in breast ultrasound image segmentation. Med Artif Intell 2025 Apr; 1(1): 14-26.
Copy