Transition of traditional method to deep learning based computer-aided system for breast cancer using Automated Breast Ultrasound System (ABUS) images: a review

被引：0
作者：
Dayangku Nur Faizah Pengiran Mohamad
Syamsiah Mashohor
Rozi Mahmud
Marsyita Hanafi
Norafida Bahari
机构：
[1] University Putra Malaysia (UPM),Department of Computer & Communication Systems Engineering, Faculty of Engineering
[2] University Putra Malaysia (UPM),Radiology Department, Faculty of Medicine & Health Science
来源：
Artificial Intelligence Review | 2023年 / 56卷
关键词：
Breast cancer; Automated Breast Ultrasound System (ABUS); Deep learning; Computer- aided (CAD) system;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Breast cancer (BC) is the leading cause of death among women worldwide. Early detection and diagnosis of BC can help significantly reduce the mortality rate. Ultrasound (US) can be an ideal screening tool for BC detection. However, the hand-held US (HHUS) is an impractical tool because it is operator-dependent, time-consuming, and increases the likelihood of false-positive results. Thus, to address these issues, the 3D Automated Breast Ultrasound System (ABUS) was designed for BC detection and diagnosis. This paper presents the transition from traditional approaches to deep learning (DL) based CAD systems in the ABUS image data set. The capabilities and limitations of both techniques are also reviewed rigorously. This review will help in understanding the current limitations to leverage their potential in diagnostic radiology to improve performance and BC patient care.
引用
收藏
页码：15271 / 15300
页数：29
相关论文
共 362 条
[41]  
Takada E(2020)Computer aided detection in automated 3-D breast ultrasound images: a survey Artif Intell Rev 53 178-1511
[42]  
Chang JM(2020)Fully automated lesion segmentation and visualization in automated whole breast ultrasound (ABUS) images Quant Imaging Med Surg 10 204-275
[43]  
Cha JH(2018)Segmentation of breast anatomy for automated whole breast ultrasound images with boundary regularized convolutional encoder–decoder network Neurocomputing 321 101753-1076
[44]  
Park JS(2021)Breast tumor segmentation in 3D automatic breast ultrasound using Mask scoring R CNN Med Phys 48 5669-463
[45]  
Kim SJ(2020)Self-co- attention neural network for anatomy segmentation in whole breast ultrasound Med Image Anal 64 364-1480
[46]  
Moon WK(2020)3D tumor detection in automated breast ultrasound using deep convolutional neural networks Med Phys 47 676-1034
[47]  
Cheng H(2008)Mammographic density and the risk and detection of breast cancer Breast Dis 18 1503-1200
[48]  
Shan J(2018)Deep learning MR imaging-based attenuation correction for PET/MR imaging Radiology 286 273-4885
[49]  
Ju W(2014)Multi-dimensional tumor detection in automated whole breast ultrasound using topographic watershed IEEE Trans Med Imaging 33 1056-22
[50]  
Guo Y(1963)Computer diagnosis of primary bone tumors: a preliminary report Radiology 80 456-1470
12345678910