Top

Published in:

30-04-2022 | Breast Cancer | Ultrasound

Performance of novel deep learning network with the incorporation of the automatic segmentation network for diagnosis of breast cancer in automated breast ultrasound

Authors: Qiucheng Wang, He Chen, Gongning Luo, Bo Li, Haitao Shang, Hua Shao, Shanshan Sun, Zhongshuai Wang, Kuanquan Wang, Wen Cheng

Published in: European Radiology | Issue 10/2022

Abstract

Objective

To develop novel deep learning network (DLN) with the incorporation of the automatic segmentation network (ASN) for morphological analysis and determined the performance for diagnosis breast cancer in automated breast ultrasound (ABUS).

Methods

A total of 769 breast tumors were enrolled in this study and were randomly divided into training set and test set at 600 vs. 169. The novel DLNs (Resent v2, ResNet50 v2, ResNet101 v2) added a new ASN to the traditional ResNet networks and extracted morphological information of breast tumors. The accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under the receiver operating characteristic (ROC) curve (AUC), and average precision (AP) were calculated. The diagnostic performances of novel DLNs were compared with those of two radiologists with different experience.

Results

The ResNet34 v2 model had higher specificity (76.81%) and PPV (82.22%) than the other two, the ResNet50 v2 model had higher accuracy (78.11%) and NPV (72.86%), and the ResNet101 v2 model had higher sensitivity (85.00%). According to the AUCs and APs, the novel ResNet101 v2 model produced the best result (AUC 0.85 and AP 0.90) compared with the remaining five DLNs. Compared with the novice radiologist, the novel DLNs performed better. The F1 score was increased from 0.77 to 0.78, 0.81, and 0.82 by three novel DLNs. However, their diagnostic performance was worse than that of the experienced radiologist.

Conclusions

The novel DLNs performed better than traditional DLNs and may be helpful for novice radiologists to improve their diagnostic performance of breast cancer in ABUS.

Key Points

• A novel automatic segmentation network to extract morphological information was successfully developed and implemented with ResNet deep learning networks.

• The novel deep learning networks in our research performed better than the traditional deep learning networks in the diagnosis of breast cancer using ABUS images.

• The novel deep learning networks in our research may be useful for novice radiologists to improve diagnostic performance.

Available only for authorised users

Sung H, Ferlay J, Siegel RL et al (2021) Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71:209–249PubMed

Birnbaum JK, Duggan C, Anderson BO, Etzioni R (2018) Early detection and treatment strategies for breast cancer in low-income and upper middle-income countries: a modelling study. Lancet Glob Health 6:e885–e893PubMedPubMedCentralCrossRef

Li E, Guida JL, Tian Y et al (2019) Associations between mammographic density and tumor characteristics in Chinese women with breast cancer. Breast Cancer Res Treat 177:527–536PubMedPubMedCentralCrossRef

Boyd NF, Guo H, Martin LJ et al (2007) Mammographic density and the risk and detection of breast cancer. N Engl J Med 356:227–236PubMedCrossRef

Vachon CM, Pankratz VS, Scott CG et al (2007) Longitudinal trends in mammographic percent density and breast cancer risk. Cancer Epidemiol Biomark Prev 16:921–928CrossRef

Jia M, Lin X, Zhou X et al (2020) Diagnostic performance of automated breast ultrasound and handheld ultrasound in women with dense breasts. Breast Cancer Res Treat 181:589–597PubMedCrossRef

Yun G, Kim SM, Yun B, Ahn HS, Jang M (2019) Reliability of automated versus handheld breast ultrasound examinations of suspicious breast masses. Ultrasonography 38:264–271PubMedCrossRef

Brem RF, Tabár L, Duffy SW et al (2015) Assessing improvement in detection of breast cancer with three-dimensional automated breast US in women with dense breast tissue: the SomoInsight Study. Radiology 274:663–673PubMedCrossRef

Wilczek B, Wilczek HE, Rasouliyan L, Leifland K (2016) Adding 3D automated breast ultrasound to mammography screening in women with heterogeneously and extremely dense breasts: report from a hospital-based, high-volume, single-center breast cancer screening program. Eur J Radiol 85:1554–1563PubMedCrossRef

10.

Rella R, Belli P, Giuliani M et al (2018) Automated Breast Ultrasonography (ABUS) in the screening and diagnostic setting: indications and practical use. Acad Radiol 25:1457–1470PubMedCrossRef

11.

Zhang L, Bao LY, Tan YJ et al (2019) Diagnostic performance using automated breast ultrasound system for breast cancer in Chinese women aged 40 years or older: a comparative study. Ultrasound Med Biol 45:3137–3144PubMedCrossRef

12.

Kelly KM, Dean J, Comulada WS, Lee SJ (2010) Breast cancer detection using automated whole breast ultrasound and mammography in radiographically dense breasts. Eur Radiol 20:734–742PubMedCrossRef

13.

van Zelst JCM, Tan T, Clauser P et al (2018) Dedicated computer-aided detection software for automated 3D breast ultrasound; an efficient tool for the radiologist in supplemental screening of women with dense breasts. Eur Radiol 28:2996–3006PubMedPubMedCentralCrossRef

14.

van Zelst JCM, Tan T, Platel B et al (2017) Improved cancer detection in automated breast ultrasound by radiologists using computer aided detection. Eur J Radiol 89:54–59PubMedCrossRef

15.

Akkus Z, Galimzianova A, Hoogi A, Rubin DL, Erickson BJ (2017) Deep learning for brain MRI segmentation: state of the art and future directions. J Digit Imaging 30:449–459PubMedPubMedCentralCrossRef

16.

Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts H (2018) Artificial intelligence in radiology. Nat Rev Cancer 18:500–510PubMedPubMedCentralCrossRef

17.

Chambara N, Ying M (2019) The diagnostic efficiency of ultrasound computer-aided diagnosis in differentiating thyroid nodules: a systematic review and narrative synthesis. Cancers 11:1759PubMedCentralCrossRef

18.

Ha T, Jung Y, Kim JY, Park SY, Kang DK, Kim TH (2019) Comparison of the diagnostic performance of abbreviated MRI and full diagnostic MRI using a computer-aided diagnosis (CAD) system in patients with a personal history of breast cancer: the effect of CAD-generated kinetic features on reader performance. Clin Radiol 74:817.e815–817.e821CrossRef

19.

Wang Y, Wang N, Xu M et al (2020) Deeply-supervised networks with threshold loss for cancer detection in automated breast ultrasound. IEEE Trans Med Imaging 39:866–876PubMedCrossRef

20.

Li Y, Wu W, Chen H, Cheng L, Wang S (2020) 3D tumor detection in automated breast ultrasound using deep convolutional neural network. Med Phys 47:5669–5680PubMedCrossRef

21.

Wang Y, Choi EJ, Choi Y, Zhang H, Jin GY, Ko SB (2020) Breast cancer classification in automated breast ultrasound using multiview convolutional neural network with transfer learning. Ultrasound Med Biol 46:1119–1132PubMedCrossRef

22.

Jiang Y, Inciardi MF, Edwards AV, Papaioannou J (2018) Interpretation time using a concurrent-read computer-aided detection system for automated breast ultrasound in breast cancer screening of women with dense breast tissue. AJR Am J Roentgenol 211:452–461PubMedCrossRef

23.

Yang S, Gao X, Liu L et al (2019) Performance and reading time of automated breast US with or without computer-aided detection. Radiology 292:540–549PubMedCrossRef

24.

Moon WK, Huang YS, Hsu CH et al (2020) Computer-aided tumor detection in automated breast ultrasound using a 3-D convolutional neural network. Comput Methods Prog Biomed 190:105360CrossRef

25.

Chiang TC, Huang YS, Chen RT, Huang CS, Chang RF (2019) Tumor detection in automated breast ultrasound using 3-D CNN and prioritized candidate aggregation. IEEE Trans Med Imaging 38:240–249PubMedCrossRef

26.

He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 770-778. https://doi.org/10.1109/CVPR.2016.90

27.

American College of Radiology (2013) ACR BI-RADS® Atlas. Breast Imaging Reporting and Data System, 5th edn. Acadmerican College of Radiology, Reston

28.

Zheng FY, Yan LX, Huang BJ et al (2015) Comparison of retraction phenomenon and BI-RADS-US descriptors in differentiating benign and malignant breast masses using an automated breast volume scanner. Eur J Radiol 84:2123–2129PubMedCrossRef

29.

Kim WH, Moon WK, Kim SJ et al (2013) Ultrasonographic assessment of breast density. Breast Cancer Res Treat 138:851–859PubMedCrossRef

30.

Noble JA, Boukerroui D (2006) Ultrasound image segmentation: a survey. IEEE Trans Med Imaging 25:987–1010PubMedCrossRef

31.

Gu P, Lee WM, Roubidoux MA, Yuan J, Wang X, Carson PL (2016) Automated 3D ultrasound image segmentation to aid breast cancer image interpretation. Ultrasonics 65:51–58PubMedCrossRef

32.

Liu L, Li K, Qin W et al (2018) Automated breast tumor detection and segmentation with a novel computational framework of whole ultrasound images. Med Biol Eng Comput 56:183–199PubMedPubMedCentralCrossRef

33.

Pan P, Chen H, Li Y, Cai N, Cheng L, Wang S (2021) Tumor segmentation in automated whole breast ultrasound using bidirectional LSTM neural network and attention mechanism. Ultrasonics 110:106271PubMedCrossRef

34.

Calas MJ, Almeida RM, Gutfilen B, Pereira WC (2010) Intraobserver interpretation of breast ultrasonography following the BI-RADS classification. Eur J Radiol 74:525–528PubMedCrossRef

35.

Li XA, Tai A, Arthur DW et al (2009) Variability of target and normal structure delineation for breast cancer radiotherapy: an RTOG multi-institutional and multiobserver study. Int J Radiat Oncol Biol Phys 73:944–951PubMedPubMedCentralCrossRef

36.

Hu Y, Guo Y, Wang Y et al (2019) Automatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model. Med Phys 46:215–228PubMedCrossRef

37.

Lei Y, He X, Yao J et al (2021) Breast tumor segmentation in 3D automatic breast ultrasound using Mask scoring R-CNN. Med Phys 48:204–214PubMedCrossRef

38.

Zhou Y, Chen H, Li Y et al (2021) Multi-task learning for segmentation and classification of tumors in 3D automated breast ultrasound images. Med Image Anal 70:101918PubMedCrossRef

39.

Wang F, Liu X, Yuan N et al (2020) Study on automatic detection and classification of breast nodule using deep convolutional neural network system. J Thorac Dis 12:4690–4701PubMedPubMedCentralCrossRef

40.

Xu X, Bao L, Tan Y, Zhu L, Kong F, Wang W (2018) 1000-case reader study of radiologists’ performance in interpretation of automated breast volume scanner images with a computer-aided detection system. Ultrasound Med Biol 44:1694–1702PubMedCrossRef

Title: Performance of novel deep learning network with the incorporation of the automatic segmentation network for diagnosis of breast cancer in automated breast ultrasound
Authors: Qiucheng Wang
He Chen
Gongning Luo
Bo Li
Haitao Shang
Hua Shao
Shanshan Sun
Zhongshuai Wang
Kuanquan Wang
Wen Cheng
Publication date: 30-04-2022
Publisher: Springer Berlin Heidelberg
Keywords: Breast Cancer
Breast Ultrasound
Breast Cancer
Published in: European Radiology / Issue 10/2022
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-022-08836-x

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Performance of novel deep learning network with the incorporation of the automatic segmentation network for diagnosis of breast cancer in automated breast ultrasound

Abstract

Objective

Methods

Results

Conclusions

Key Points

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objective

Methods

Results

Conclusions

Key Points

Please log in to get access to this content

Other articles of this Issue 10/2022

Standardized measurement of abdominal muscle by computed tomography: association with cardiometabolic risk in the Framingham Heart Study

Machine learning-based prediction of insufficient contrast enhancement in coronary computed tomography angiography

Incidental findings in brain imaging research: spotlight on ethical considerations

Deep learning–based atherosclerotic coronary plaque segmentation on coronary CT angiography

Transradial versus transfemoral access without closure device for transarterial chemoembolization in patients with hepatocellular carcinoma: a randomized trial

A novel clinical radiomics nomogram at baseline to predict mucosal healing in Crohn’s disease patients treated with infliximab