Literature DB >> 34079700

Detection and recognition of ultrasound breast nodules based on semi-supervised deep learning: a powerful alternative strategy.

Yanhua Gao1,2, Bo Liu2, Yuan Zhu2, Lin Chen3, Miao Tan4, Xiaozhou Xiao5, Gang Yu5, Youmin Guo1.   

Abstract

BACKGROUND: The successful recognition of benign and malignant breast nodules using ultrasound images is based mainly on supervised learning that requires a large number of labeled images. However, because high-quality labeling is expensive and time-consuming, we hypothesized that semi-supervised learning could provide a low-cost and powerful alternative approach. This study aimed to develop an accurate semi-supervised recognition method and compared its performance with supervised methods and sonographers.
METHODS: The faster region-based convolutional neural network was used for nodule detection from ultrasound images. A semi-supervised classifier based on the mean teacher model was proposed to recognize benign and malignant nodule images. The general performance of the proposed method on two datasets (8,966 nodules) was reported.
RESULTS: The detection accuracy was 0.88±0.03 and 0.86±0.02, respectively, on two testing sets (1,350 and 2,220 nodules). When 800 labeled training nodules were available, the proposed semi-supervised model plus 4,396 unlabeled nodules performed better than the supervised learning model (area under the curve (AUC): 0.934±0.026 vs. 0.83±0.050; 0.916±0.022 vs. 0.815±0.049). The performance of the semi-supervised model trained on 800 labeled and 4,396 unlabeled nodules was close to that of the supervised learning model trained on a massive number of labeled nodules (n=5,196) (AUC: 0.934±0.026 vs. 0.952±0.027; 0.916±0.022 vs. 0.918±0.017). Moreover, the semi-supervised model was better than the average accuracy of five human sonographers (AUC: 0.922 vs. 0.889).
CONCLUSIONS: The semi-supervised model can achieve excellent performance for nodule recognition and be useful for medical sciences. The method reduced the number of labeled images required for training, thus significantly alleviating the difficulty in data preparation of medical artificial intelligence. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.

Entities:  

Keywords:  Deep learning; recognition; semi-supervised learning; ultrasound breast nodules

Year:  2021        PMID: 34079700      PMCID: PMC8107344          DOI: 10.21037/qims-20-12b

Source DB:  PubMed          Journal:  Quant Imaging Med Surg        ISSN: 2223-4306


  26 in total

1.  Cancer statistics, 2019.

Authors:  Rebecca L Siegel; Kimberly D Miller; Ahmedin Jemal
Journal:  CA Cancer J Clin       Date:  2019-01-08       Impact factor: 508.702

2.  Ultrasound Aided Vertebral Level Localization for Lumbar Surgery.

Authors:  Nora Baka; Sieger Leenstra; Theo van Walsum
Journal:  IEEE Trans Med Imaging       Date:  2017-08-10       Impact factor: 10.048

3.  Ultrasound Standard Plane Detection Using a Composite Neural Network Framework.

Authors:  Hao Chen; Lingyun Wu; Qi Dou; Jing Qin; Shengli Li; Jie-Zhi Cheng; Dong Ni; Pheng-Ann Heng
Journal:  IEEE Trans Cybern       Date:  2017-03-30       Impact factor: 11.448

4.  A deep learning framework for supporting the classification of breast lesions in ultrasound images.

Authors:  Seokmin Han; Ho-Kyung Kang; Ja-Yeon Jeong; Moon-Ho Park; Wonsik Kim; Won-Chul Bang; Yeong-Kyeong Seong
Journal:  Phys Med Biol       Date:  2017-09-15       Impact factor: 3.609

5.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

Authors:  Shaoqing Ren; Kaiming He; Ross Girshick; Jian Sun
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2016-06-06       Impact factor: 6.226

Review 6.  Computer-aided detection/diagnosis of breast cancer in mammography and ultrasound: a review.

Authors:  Afsaneh Jalalian; Syamsiah B T Mashohor; Hajjah Rozi Mahmud; M Iqbal B Saripan; Abdul Rahman B Ramli; Babak Karasfi
Journal:  Clin Imaging       Date:  2012-11-13       Impact factor: 1.605

7.  Classification of benign and malignant breast tumors using neural networks and three-dimensional power Doppler ultrasound.

Authors:  S-J Kuo; Y-H Hsiao; Y-L Huang; D-R Chen
Journal:  Ultrasound Obstet Gynecol       Date:  2008-07       Impact factor: 7.299

Review 8.  Screening Algorithms in Dense Breasts: AJR Expert Panel Narrative Review.

Authors:  Wendie A Berg; Elizabeth A Rafferty; Sarah M Friedewald; Carrie B Hruska; Habib Rahbar
Journal:  AJR Am J Roentgenol       Date:  2020-12-23       Impact factor: 3.959

9.  Prevalence of Women with Dense Breasts in Korea: Results from a Nationwide Cross-sectional Study.

Authors:  Hye-Mi Jo; Eun Hye Lee; Kyungran Ko; Bong Joo Kang; Joo Hee Cha; Ann Yi; Hae Kyoung Jung; Jae Kwan Jun
Journal:  Cancer Res Treat       Date:  2019-01-29       Impact factor: 4.679

10.  Preparing Medical Imaging Data for Machine Learning.

Authors:  Martin J Willemink; Wojciech A Koszek; Cailin Hardell; Jie Wu; Dominik Fleischmann; Hugh Harvey; Les R Folio; Ronald M Summers; Daniel L Rubin; Matthew P Lungren
Journal:  Radiology       Date:  2020-02-18       Impact factor: 11.105

View more
  5 in total

Review 1.  The use of deep learning technology for the detection of optic neuropathy.

Authors:  Mei Li; Chao Wan
Journal:  Quant Imaging Med Surg       Date:  2022-03

2.  Intelligent Research Based on Deep Learning Recognition Method in Vehicle-Road Cooperative Information Interaction System.

Authors:  Hongbin Jiao
Journal:  Comput Intell Neurosci       Date:  2022-06-29

3.  Application of deep learning to identify ductal carcinoma in situ and microinvasion of the breast using ultrasound imaging.

Authors:  Meng Zhu; Yong Pi; Zekun Jiang; Yanyan Wu; Hong Bu; Ji Bao; Yujuan Chen; Lijun Zhao; Yulan Peng
Journal:  Quant Imaging Med Surg       Date:  2022-09

4.  Establishment of a deep-learning system to diagnose BI-RADS4a or higher using breast ultrasound for clinical application.

Authors:  Tetsu Hayashida; Erina Odani; Masayuki Kikuchi; Aiko Nagayama; Tomoko Seki; Maiko Takahashi; Noriyuki Futatsugi; Akiko Matsumoto; Takeshi Murata; Rurina Watanuki; Takamichi Yokoe; Ayako Nakashoji; Hinako Maeda; Tatsuya Onishi; Sota Asaga; Takashi Hojo; Hiromitsu Jinno; Keiichi Sotome; Akira Matsui; Akihiko Suto; Shigeru Imoto; Yuko Kitagawa
Journal:  Cancer Sci       Date:  2022-08-03       Impact factor: 6.518

5.  Identification of benign and malignant thyroid nodules based on dynamic AI ultrasound intelligent auxiliary diagnosis system.

Authors:  Bing Wang; Zheng Wan; Chen Li; Mingbo Zhang; YiLei Shi; Xin Miao; Yanbing Jian; Yukun Luo; Jing Yao; Wen Tian
Journal:  Front Endocrinol (Lausanne)       Date:  2022-09-27       Impact factor: 6.055

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.