Automated breast ultrasound (ABUS) lesion segmentation is challenging. The nnU-Net has been recognized for its high accuracy and efficiency on medical image segmentation. However, its effectiveness on ABUS image segmentation remains unknown. This study designs four experiments using nnU-Net (NET), the net with post-processing (NETp), the net with data augmentation (NETd), and the net with data augmentation and post-processing (NETdp). On 100 cases with five-fold cross validation, the performance is assessed with the Dice coefficient (DC) and relative volume error (RVE). Experimental results suggest that NETp (DC = 0.81 ± 0.01; RVE = 0.23 ± 0.11), NETpd (DC = 0.79 ± 0.02; RVE = 0.24 ± 0.13) and NET (DC = 0.79 ± 0.01; RVE = 0.27 ± 0.12) are comparable, and NETd leads to DC = 0.64 ± 0.03 and RVE = 0.03 ± 0.00. Further investigation indicates that the nnU-Net fails on several low-quality ABUS images in consistency. In the future work, how to improve ABUS imaging quality as well as how to design effective segmentation networks become important.
Objective: In Transthoracic echocardiographic (TTE) examination, it is essential to identify the cardiac views accurately. Computer-aided recognition is expected to improve the accuracy of the TTE examination. Methods: This paper proposes a new method for automatic recognition of cardiac views based on deep learning, including three strategies. First, A spatial transform network is performed to learn cardiac shape changes during the cardiac cycle, which reduces intra-class variability. Second, a channel attention mechanism is introduced to adaptively recalibrates channel-wise feature responses. Finally, unlike conventional deep learning methods, which learned each input images individually, the structured signals are applied by a graph of similarities among images. These signals are transformed into the graph-based image embedding, which act as unsupervised regularization constraints to improve the generalization accuracy. Results: The proposed method was trained and tested in 171792 cardiac images from 584 subjects. Compared with the known result of the state of the art, the overall accuracy of the proposed method on cardiac image classification is 99.10% vs. 91.7%, and the mean AUC is 99.36%. Moreover, the overall accuracy is 98.15%, and the mean AUC is 98.96% on an independent test set with 34211 images from 100 subjects. Conclusion: The method of this paper achieved the results of the state of the art, which is expected to be an automated recognition tool for cardiac views recognition. The work confirms the potential of deep learning on ultrasound medicine.
Background: The successful application of deep learning in medical images requires a large amount of annotation data for supervised training. However, massive labeling of medical data is expensive and time consuming. This paper proposes a semi-supervised deep learning method for the detection and classification of benign and malignant breast nodules in ultrasound images, which include two phases. Methods: The nodule position in the ultrasound image is firstly detected using the faster RCNN network. Second, the recognition network is used to identify the benign and malignant types of nodules. The method in this paper uses a semi-supervised learning strategy, using 800 labeled nodules and 4396 unlabeled nodules. Results: Based on mean teacher training strategy, the proposed semi-supervised network has obtained excellent results, which is similar to currently used with supervised training networks. On the two test data sets, the AUC of semi-supervised learning and supervised learning were: 93.7% vs 94.2% and 92% vs 92.3%. Conclusions: The paper proves that semi-supervised learning strategies have good application potential in medical images. Based on a special learning strategy, the result of semi-supervised learning is expected to achieve close or even achieve similar result of supervised deep learning, which only need a small number of labeled samples and a large number of unlabeled samples. It means deep learning analysis of breast lesion will be more feasible and more efficient.