Diagnostic Performance Using Automated Breast Ultrasound System for Breast Cancer in Chinese Women Aged 40 Years or Older: A Comparative Study

Zhang, Li; Bao, Liang; Tan, Yanlin; Zhu, Luo-Qian; Xu, Xiaojing; Zhu, Qingqing; Shan, Yanna; Zhao, Jingbo; Xie, Lesi; Liu, Jan

doi:10.1016/j.ultrasmedbio.2019.08.016

Cited by 13 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of benign and malignant breast lesion differential diagnosis, no confirmation was made in our study regarding the added benefit of using ABVS for coronal reconstruction. The results of Zhang et al are in agreement with those of our study which indicated that, regarding AUC values, ABVS diagnostic performance might not be significantly improved through coronal reconstruction [ 30 ]. In the study of Zhang et al, a suggestion was made that ABVS independent value limitation in the differential diagnosis is caused by the low sensitivity (37.0%) of the retraction phenomenon on the coronal plane [ 32 ].…”

Section: Discussionsupporting

confidence: 92%

“…It was found at the completion of the study that 496 (83%) of the 599 masses were benign while the remaining 103 (17%) were malignant, with the one-year follow-up information or pathological outcomes as the reference standards. As indicated by the BI-RADS classification for every unit, 258 units (258/320, 80.63%) had BI-RADS classification 1–2, 62 units (19.38%) had BI-RADS classification 3 while 155 lesions had the introductory BI-RADS classifications of 4–5 [ 30 ]. Choi et al confirmed 184 malignant cases of BI-RADS 4 and BI-RADS 5 classes, and 234 lesions were diagnosed as benign (BI-RADS 3) [ 31 ].…”

Section: Resultsmentioning

confidence: 99%

“…In a meta-analysis in Zhang et al, the same detection rate (100%) was found in both HHUS and ABVS in detecting breast cancer. However, ABVS demonstrated numerically greater specificity (86% vs. 82%) and sensitivity (93% vs. 90%) in comparison with HHUS [ 30 ]. On the other hand, Wang and Qi reported that ABVS and HHUS demonstrated similar specificity and sensitivity in discriminating benign breast lesions from malignant.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of Diagnostic Performance of Automatic Breast Volume Scanner Compared to Handheld Ultrasound on Different Breast Lesions: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

Objective: To compare the diagnostic performance of the automatic breast volume scanner (ABVS) against the handheld ultrasound (HHUS) in the differential diagnosis of benign and malignant breast lesions. Methods: A systematic search and review of studies involving ABVS and HHUS for breast cancer screening were performed. The search involved the data taken from Scopus, PubMed, and science direct databases and was conducted between the year 2011 to 2020. The prospective method was used in determining the inclusion and exclusion criteria while the evidence level was determined using the BI-RADS categories for diagnostic studies. In addition, the parameters of specificity, mean age, sensitivity, tumor number, and diagnostic accuracy of the ABVS and HHUS were summarized. Results: No systematic review or randomized controlled trial were identified in the systematic search while one cross-sectional study, eight retrospective studies, and 10 prospective studies were found. Sufficient follow-up of the subjects with benign and malignant findings were made only in 10 studies, in which only two had used ABVS and HHUS after performing mammographic screening and MRI. Analysis was made of 21 studies, which included 5448 lesions (4074 benign and 1374 malignant) taken from 6009 patients. The range of sensitivity was (0.72–1.0) for ABVS and (0.62–1.0) for HHUS; the specificity range was (0.52–0.98)% for ABVS and (0.49–0.99)% for HHUS. The accuracy range among the 11 studies was (80–99)% and (59–98)% for the HHUS and ABVS, respectively. The identified tumors had a mean size of 2.1 cm, and the detected cancers had a mean percentage of 94% (81–100)% in comparison to the non-cancer in all studies. Conclusions: The evidence available in the literature points to the fact that the diagnostic performance of both ABVS and HHUS are similar with reference to the differentiation of malignant and benign breast lesions.

show abstract

Section: Discussionsupporting

confidence: 92%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Diagnostic Performance of Automatic Breast Volume Scanner Compared to Handheld Ultrasound on Different Breast Lesions: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In comparisons of HHUS and ABUS evaluation of breast NML malignancy, most studies have reported higher sensitivity for ABUS but higher speci city and accuracy for HHUS [29], which is consistent with our ndings. ABUS can focus on a lesion from three orthogonal sections at the same time and display the accurate spatial position of the lesion in real-time, which allows a thorough and detailed evaluation [30].…”

Section: Discussionmentioning

confidence: 99%

Comparative study of multiple breast cancer screening methods in the evaluation of breast non-mass-like lesions

Zhang

Cai

Chen

et al. 2021

Preprint

View full text Add to dashboard Cite

Objective: To compare multiple breast cancer screening methods for evaluating breast non-mass-like lesions (NMLs) and to investigate the best screening method for breast non-mass-like lesions (NMLs). Methods: This retrospective study examined 253 patients aged 24 to 68 years who were diagnosed with breast NMLs from April 2017 to December 2019. All lesions were evaluated by MG, HHUS, and ABUS to determine BI-RADS classification, underwent pathological examination within six months or at least 2 years of follow-up. The sensitivity, specificity, accuracy, positive predictive values (PPV), and negative predictive values (NPV) of MG, HHUS, and ABUS features in the prediction of malignancy were compared. Independent risk factors for malignancy were assessed using non-conditional logistic regression. Results: MG, HHUS, and ABUS findings significantly differed between benign and malignant breast NML, including internal echo, hyperechoic spot, peripheral blood flow, internal blood flow, catheter change, peripheral change, coronal features of ABUS, and structural distortion, asymmetry, and calcification in MG. ABUS was superior to MG and HHUS in sensitivity, specificity, PPV, NPV, as well as in evaluating the necessity of biopsy and accuracy in identifying malignancy. MG was superior to HHUS in specificity, PPV, and accuracy in evaluating the need for biopsy. HHUS was distinctly superior to MG in sensitivity and NPV in determining malignancy; however, specificity, PPV, and accuracy were similar. Moreover, internal blood flow, calcification, and coronal plane feature were independent risk factors in distinguishing benign and malignant lesions. Conclusions: ABUS was superior to HHUS and MG in evaluating the need for biopsy and differentiating benign and malignant in breast NMLs. Compared to each other, HHUS and MG had their own relative advantages. Internal blood flow, calcification, and coronal plane feature were independent risk factors in identifying benign and malignant lesions.

show abstract

“…The Youden index is a common method to determine the threshold in other study, and we applied the same strategy to our methods. [37][38][39] The results in Table 3 showed that voting results from eight models achieved the best performance on the AUC index and the sensitivity indicator, which means that it was more sensitive to malignant-related features. Although the effect has declined on the external dataset, it can still be seen that the voting method is better than the baseline method.…”

Section: The Improvement Brought By the Uncertainty Boundarymentioning

confidence: 99%

The uncertainty of boundary can improve the classification accuracy of BI‐RADS 4A ultrasound image

Wang

et al. 2022

Medical Physics

View full text Add to dashboard Cite

Purpose The Breast Imaging‐Reporting and Data System (BI‐RADS) for ultrasound imaging provides a widely used reporting schema for breast imaging. Previous studies have shown that in ultrasound imaging, 90% of BI‐RADS 4A tumors are benign lesions after biopsies. Unnecessary biopsy procedures can be avoided by accurate classification of BI‐RADS 4A tumors. However, the classification task is challenging and has not been fully investigated by existing studies. For benign and malignant tumors of BI‐RADS 4A, the appearances of intra‐class tumors are highly variable, the characteristics of inter‐class tumors is overall‐similar. Discriminative features need to be found to improve classification accuracy of BI‐RADS 4A tumors. Methods In this study, we designed the network using the clinical features of BI‐RADS 4A tumors to improve the discrimination ability of network. The boundary information is embedded into the input of the network using the uncertainty. A fine‐grained data augmentation method is used to find discriminative features in tumor information embedded with boundary information. Two mathematical methods, voting‐based and variance‐based, are used to define the uncertainty of boundary, and the differences of these two definitions are compared in a classification network. Results The dataset we used to evaluate our method had 1155 2D grayscale images. Each image represented a unique BI‐RADS 4A tumor. Among them, 248 tumors were proven to be malignant by biopsy, and the remaining 907 were benign. A weakly supervised data augmentation network (WS‐DAN) was used as the backbone classification network, which showed competitive performance in finding discriminative features. Using the auxiliary input of the uncertain boundaries defined by the voting method, the area under the curve (AUC) value of our method was 0.8347 (sensitivity = 0.7774, specificity = 0.7459). The AUC value of the variance‐based uncertainty was 0.7789. The voting‐based uncertainty was higher than the baseline (AUC = 0.803), which only inputs the original image. Compared with the classic classification network, our method had a significant effect improvement (p < 0.01). Conclusions Using the uncertain boundaries defined by the voting methods as auxiliary information, we obtained a better performance in the classification of BI‐RADS 4A ultrasound images, while variance‐based uncertain boundaries had no effect on improving classification performance. Additionally, fine‐grained network helped find discriminative features comparing with the commonly used classification networks.

show abstract

Diagnostic Performance Using Automated Breast Ultrasound System for Breast Cancer in Chinese Women Aged 40 Years or Older: A Comparative Study

Cited by 13 publications

References 32 publications

Evaluation of Diagnostic Performance of Automatic Breast Volume Scanner Compared to Handheld Ultrasound on Different Breast Lesions: A Systematic Review

Evaluation of Diagnostic Performance of Automatic Breast Volume Scanner Compared to Handheld Ultrasound on Different Breast Lesions: A Systematic Review

Comparative study of multiple breast cancer screening methods in the evaluation of breast non-mass-like lesions

The uncertainty of boundary can improve the classification accuracy of BI‐RADS 4A ultrasound image

Contact Info

Product

Resources

About