TY - JOUR
T1 - BIRADS features-oriented semi-supervised deep learning for breast ultrasound computer-Aided diagnosis
AU - Zhang, Erlei
AU - Zhang, Erlei
AU - Seiler, Stephen
AU - Chen, Mingli
AU - Lu, Weiguo
AU - Gu, Xuejun
N1 - Publisher Copyright:
© 2020 Institute of Physics and Engineering in Medicine.
PY - 2020/6/21
Y1 - 2020/6/21
N2 - We propose a novel BIRADS-SSDL network that integrates clinically-Approved breast lesion characteristics (BIRADS features) into task-oriented semi-supervised deep learning (SSDL) for accurate diagnosis of ultrasound (US) images with a small training dataset. Breast US images are converted to BIRADS-oriented feature maps (BFMs) using a distance-Transformation coupled with a Gaussian filter. Then, the converted BFMs are used as the input of an SSDL network, which performs unsupervised stacked convolutional auto-encoder (SCAE) image reconstruction guided by lesion classification. This integrated multi-Task learning allows SCAE to extract image features with the constraints from the lesion classification task, while the lesion classification is achieved by utilizing the SCAE encoder features with a convolutional network. We trained the BIRADS-SSDL network with an alternative learning strategy by balancing the reconstruction error and classification label prediction error. To demonstrate the effectiveness of our approach, we evaluated it using two breast US image datasets. We compared the performance of the BIRADS-SSDL network with conventional SCAE and SSDL methods that use the original images as inputs, as well as with an SCAE that use BFMs as inputs. The experimental results on two breast US datasets show that BIRADS-SSDL ranked the best among the four networks, with a classification accuracy of around 94.23 3.33% and 84.38 3.11% on two datasets. In the case of experiments across two datasets collected from two different institutions/and US devices, the developed BIRADS-SSDL is generalizable across the different US devices and institutions without overfitting to a single dataset and achieved satisfactory results. Furthermore, we investigate the performance of the proposed method by varying the model training strategies, lesion boundary accuracy, and Gaussian filter parameters. The experimental results showed that a pre-Training strategy can help to speed up model convergence during training but with no improvement of the classification accuracy on the testing dataset. The classification accuracy decreases as the segmentation accuracy decreases. The proposed BIRADS-SSDL achieves the best results among the compared methods in each case and has the capacity to deal with multiple different datasets under one model. Compared with state-of-The-Art methods, BIRADS-SSDL could be promising for effective breast US computer-Aided diagnosis using small datasets.
AB - We propose a novel BIRADS-SSDL network that integrates clinically-Approved breast lesion characteristics (BIRADS features) into task-oriented semi-supervised deep learning (SSDL) for accurate diagnosis of ultrasound (US) images with a small training dataset. Breast US images are converted to BIRADS-oriented feature maps (BFMs) using a distance-Transformation coupled with a Gaussian filter. Then, the converted BFMs are used as the input of an SSDL network, which performs unsupervised stacked convolutional auto-encoder (SCAE) image reconstruction guided by lesion classification. This integrated multi-Task learning allows SCAE to extract image features with the constraints from the lesion classification task, while the lesion classification is achieved by utilizing the SCAE encoder features with a convolutional network. We trained the BIRADS-SSDL network with an alternative learning strategy by balancing the reconstruction error and classification label prediction error. To demonstrate the effectiveness of our approach, we evaluated it using two breast US image datasets. We compared the performance of the BIRADS-SSDL network with conventional SCAE and SSDL methods that use the original images as inputs, as well as with an SCAE that use BFMs as inputs. The experimental results on two breast US datasets show that BIRADS-SSDL ranked the best among the four networks, with a classification accuracy of around 94.23 3.33% and 84.38 3.11% on two datasets. In the case of experiments across two datasets collected from two different institutions/and US devices, the developed BIRADS-SSDL is generalizable across the different US devices and institutions without overfitting to a single dataset and achieved satisfactory results. Furthermore, we investigate the performance of the proposed method by varying the model training strategies, lesion boundary accuracy, and Gaussian filter parameters. The experimental results showed that a pre-Training strategy can help to speed up model convergence during training but with no improvement of the classification accuracy on the testing dataset. The classification accuracy decreases as the segmentation accuracy decreases. The proposed BIRADS-SSDL achieves the best results among the compared methods in each case and has the capacity to deal with multiple different datasets under one model. Compared with state-of-The-Art methods, BIRADS-SSDL could be promising for effective breast US computer-Aided diagnosis using small datasets.
KW - BIRADS features
KW - breast cancer
KW - computer-Aided diagnosis
KW - semi-supervised deep learning
KW - ultrasound
UR - http://www.scopus.com/inward/record.url?scp=85086995088&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85086995088&partnerID=8YFLogxK
U2 - 10.1088/1361-6560/ab7e7d
DO - 10.1088/1361-6560/ab7e7d
M3 - Article
C2 - 32155605
AN - SCOPUS:85086995088
SN - 0031-9155
VL - 65
JO - Physics in medicine and biology
JF - Physics in medicine and biology
IS - 12
M1 - 125005
ER -