Deep convolutional neural networks (CNNs) have been widely used in various medical imaging tasks. However, due to the intrinsic locality of convolution operations, CNNs generally cannot model long-range dependencies well, which are important for accurately identifying or mapping corresponding breast lesion features computed from unregistered multiple mammograms. This motivated us to leverage the architecture of Multi-view Vision Transformers to capture long-range relationships of multiple mammograms from the same patient in one examination. For this purpose, we employed local transformer blocks to separately learn patch relationships within four mammograms acquired from two-view (CC/MLO) of two-side (right/left) breasts. The outputs from different views and sides were concatenated and fed into global transformer blocks, to jointly learn patch relationships between four images representing two different views of the left and right breasts. To evaluate the proposed model, we retrospectively assembled a dataset involving 949 sets of mammograms, which included 470 malignant cases and 479 normal or benign cases. We trained and evaluated the model using a five-fold cross-validation method. Without any arduous preprocessing steps (e.g., optimal window cropping, chest wall or pectoral muscle removal, two-view image registration, etc.), our four-image (two-view-two-side) transformer-based model achieves case classification performance with an area under ROC curve (AUC = 0.818 ± 0.039), which significantly outperforms AUC = 0.784 ± 0.016 achieved by the state-of-the-art multi-view CNNs (p = 0.009). It also outperforms two one-view-two-side models that achieve AUC of 0.724 ± 0.013 (CC view) and 0.769 ± 0.036 (MLO view), respectively. The study demonstrates the potential of using transformers to develop high-performing computer-aided diagnosis schemes that combine four mammograms.
In order to monitor the rail base, the dispersion characteristics and propagation properties of the guided wave are studied. Firstly, two modes named as Modes V1 and V2 are selected by the semianalytical finite element method (SAFE). The region at the bottom edge can be monitored by Mode V1, while the junction of the base edge and the flange can be detected by Mode V2. Then, the characteristics in the propagation process are analyzed using the finite element method (FEM). The two modes can be separated about 0.6 ms after they are excited. Thirdly, a wave attenuation algorithm based on mean is proposed to quantify the wave attenuation. Both waves can have weak attenuation and be detected within 5 m. Finally, a mode-identified experiment is performed to validate the aforementioned analysis. And a defect detection experiment is performed to demonstrate the excellent monitoring characteristics using Mode V2. These results can be used to monitor the rail base in practice engineering.
Cochlear implant (CI) surgery is one of the most utilized treatments for severe hearing loss. However, the effects of a successful scala tympani insertion on the mechanics of hearing are not yet fully understood. This paper presents a finite element (FE) model of the chinchilla inner ear for studying the interrelationship between the mechanical function and the insertion angle of a CI electrode. This FE model includes a three-chambered cochlea and full vestibular system, accomplished using µ-MRI and µ-CT scanning technologies. This model’s first application found minimal loss of residual hearing due to insertion angle after CI surgery, and this indicates that it is a reliable and helpful tool for future applications in CI design, surgical planning, and stimuli setup.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.