Yanhua Gao1,2, Bo Liu2, Yuan Zhu2, Lin Chen3, Miao Tan4, Xiaozhou Xiao5, Gang Yu5, Youmin Guo1. 1. Department of Medical Imaging, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China. 2. Department of Ultrasound, The Third Affiliated Hospital of Xi'an Jiaotong University, Shaanxi Provincial People's Hospital, Xi'an, China. 3. Department of Pathology, The Third Affiliated Hospital of Xi'an Jiaotong University, Shaanxi Provincial People's Hospital, Xi'an, China. 4. Department of Surgery, The Third Affiliated Hospital of Xi'an Jiaotong University, Shaanxi Provincial People's Hospital, Xi'an, China. 5. Department of Biomedical Engineering, School of Basic Medical Science, Central South University, Changsha, China.
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.
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
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
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
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