Literature DB >> 32964449

An attention-supervised full-resolution residual network for the segmentation of breast ultrasound images.

Xiaolei Qu1,2, Yao Shi1, Yaxin Hou3, Jue Jiang4.   

Abstract

PURPOSE: Breast cancer is the most common cancer among women worldwide. Medical ultrasound imaging is one of the widely applied breast imaging methods for breast tumors. Automatic breast ultrasound (BUS) image segmentation can measure the size of tumors objectively. However, various ultrasound artifacts hinder segmentation. We proposed an attention-supervised full-resolution residual network (ASFRRN) to segment tumors from BUS images.
METHODS: In the proposed method, Global Attention Upsample (GAU) and deep supervision were introduced into a full-resolution residual network (FRRN), where GAU learns to merge features at different levels with attention for deep supervision. Two datasets were employed for evaluation. One (Dataset A) consisted of 163 BUS images with tumors (53 malignant and 110 benign) from UDIAT Centre Diagnostic, and the other (Dataset B) included 980 BUS images with tumors (595 malignant and 385 benign) from the Sun Yat-sen University Cancer Center. The tumors from both datasets were manually segmented by medical doctors. For evaluation, the Dice coefficient (Dice), Jaccard similarity coefficient (JSC), and F1 score were calculated.
RESULTS: For Dataset A, the proposed method achieved higher Dice (84.3  ±  10.0%), JSC (75.2  ±  10.7%), and F1 score (84.3  ±  10.0%) than the previous best method: FRRN. For Dataset B, the proposed method also achieved higher Dice (90.7  ±  13.0%), JSC (83.7  ±  14.8%), and F1 score (90.7  ±  13.0%) than the previous best methods: DeepLabv3 and dual attention network (DANet). For Dataset A + B, the proposed method achieved higher Dice (90.5  ±  13.1%), JSC (83.3  ±  14.8%), and F1 score (90.5  ±  13.1%) than the previous best method: DeepLabv3. Additionally, the parameter number of ASFRRN was only 10.6 M, which is less than those of DANet (71.4 M) and DeepLabv3 (41.3 M).
CONCLUSIONS: We proposed ASFRRN, which combined with FRRN, attention mechanism, and deep supervision to segment tumors from BUS images. It achieved high segmentation accuracy with a reduced parameter number.
© 2020 American Association of Physicists in Medicine.

Entities:  

Keywords:  breast cancer; breast ultrasound image; deep learning; segmentation

Mesh:

Year:  2020        PMID: 32964449      PMCID: PMC7905659          DOI: 10.1002/mp.14470

Source DB:  PubMed          Journal:  Med Phys        ISSN: 0094-2405            Impact factor:   4.071


  20 in total

1.  Computerized lesion detection on breast ultrasound.

Authors:  Karen Drukker; Maryellen L Giger; Karla Horsch; Matthew A Kupinski; Carl J Vyborny; Ellen B Mendelson
Journal:  Med Phys       Date:  2002-07       Impact factor: 4.071

2.  Reducing Costs of Breast Examination: Ultrasound Performance and Inter-Observer Variability of Expert Radiologists Versus Residents.

Authors:  Graziella Di Grezia; Francesco Somma; Nicola Serra; Alfonso Reginelli; Salvatore Cappabianca; Roberto Grassi; Gianluca Gatta
Journal:  Cancer Invest       Date:  2016-07-20       Impact factor: 2.176

3.  A robust graph-based segmentation method for breast tumors in ultrasound images.

Authors:  Qing-Hua Huang; Su-Ying Lee; Long-Zhong Liu; Min-Hua Lu; Lian-Wen Jin; An-Hua Li
Journal:  Ultrasonics       Date:  2011-08-25       Impact factor: 2.890

4.  Squeeze-and-Excitation Networks.

Authors:  Jie Hu; Li Shen; Samuel Albanie; Gang Sun; Enhua Wu
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2019-04-29       Impact factor: 6.226

5.  Automated Breast Ultrasound Lesions Detection Using Convolutional Neural Networks.

Authors:  Moi Hoon Yap; Gerard Pons; Joan Marti; Sergi Ganau; Melcior Sentis; Reyer Zwiggelaar; Adrian K Davison; Robert Marti; Gerard Pons; Joan Marti; Sergi Ganau; Melcior Sentis; Reyer Zwiggelaar; Adrian K Davison; Robert Marti
Journal:  IEEE J Biomed Health Inform       Date:  2017-08-07       Impact factor: 5.772

6.  Breast imaging: A survey.

Authors:  Subbhuraam Vinitha Sree; Eddie Yin-Kwee Ng; Rajendra U Acharya; Oliver Faust
Journal:  World J Clin Oncol       Date:  2011-04-10

7.  Ultrasound as the Primary Screening Test for Breast Cancer: Analysis From ACRIN 6666.

Authors:  Wendie A Berg; Andriy I Bandos; Ellen B Mendelson; Daniel Lehrer; Roberta A Jong; Etta D Pisano
Journal:  J Natl Cancer Inst       Date:  2015-12-28       Impact factor: 13.506

8.  A cost-sensitive extension of AdaBoost with markov random field priors for automated segmentation of breast tumors in ultrasonic images.

Authors:  Atsushi Takemura; Akinobu Shimizu; Kazuhiko Hamamoto
Journal:  Int J Comput Assist Radiol Surg       Date:  2010-06-23       Impact factor: 2.924

9.  Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions.

Authors:  Anant Madabhushi; Dimitris N Metaxas
Journal:  IEEE Trans Med Imaging       Date:  2003-02       Impact factor: 10.048

10.  Sensitivity and specificity of mammography and adjunctive ultrasonography to screen for breast cancer in the Japan Strategic Anti-cancer Randomized Trial (J-START): a randomised controlled trial.

Authors:  Noriaki Ohuchi; Akihiko Suzuki; Tomotaka Sobue; Masaaki Kawai; Seiichiro Yamamoto; Ying-Fang Zheng; Yoko Narikawa Shiono; Hiroshi Saito; Shinichi Kuriyama; Eriko Tohno; Tokiko Endo; Akira Fukao; Ichiro Tsuji; Takuhiro Yamaguchi; Yasuo Ohashi; Mamoru Fukuda; Takanori Ishida
Journal:  Lancet       Date:  2015-11-05       Impact factor: 79.321

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.