The main goal of this study is to build an artificial intelligence (AI) architecture for automated extraction of dual-modal image features from both shear-wave elastography (SWE) and B-mode ultrasound, and to evaluate the AI architecture for classification between benign and malignant breast tumors. In this AI architecture, ultrasound images were segmented by the reaction diffusion level set model combined with the Gabor-based anisotropic diffusion algorithm. Then morphological features and texture features were extracted from SWE and B-mode ultrasound images at the contourlet domain. Finally, we employed a framework for feature learning and classification with the deep polynomial network (DPN) on dual-modal features to distinguish between malignant and benign breast tumors. With the leave-one-out cross validation, the DPN method on dual-modal features achieved a sensitivity of 97.8%, a specificity of 94.1%, an accuracy of 95.6%, a Youden's index of 91.9% and an area under the receiver operating characteristic curve of 0.961, which was superior to the classic single-modal methods, and the dual-modal methods using the principal component analysis and multiple kernel learning. These results have demonstrated that the dual-modal AI-based technique with DPN has the potential for breast tumor classification in future clinical practice.
Endoscopic ultrasound (EUS), an interventional imaging technology, utilizes a circular array to delineate the cross-sectional morphology of internal organs through the gastrointestinal (GI) track. However, the performance of conventional EUS transducers has scope for improvement because of the ordinary piezoelectric parameters of Pb(Zr,Ti)O3 (PZT) bulk ceramic as well as its inferior mechanical flexibility which can cause material cracks during the circular shaping process. To achieve both prominent imaging capabilities and high device reliability, a 128-element 6.8-MHz circular array transducer is developed using a Pb(Mg1/3Nb2/3)O3-PbTiO3 (PMN-PT) 1-3 composite with a high electromechanical coupling coefficient (kt ~ 0.78) and good mechanical flexibility. The characterization results exhibit a large average bandwidth of 58%, a high average sensitivity of 100 mVpp, and a crosstalk of less than -37 dB near the center frequency. Imaging performance of the PMN-PT composite-based array transducer is evaluated by a wire phantom, an anechoic cyst phantom, and an ex vivo swine intestine. This work demonstrates the superior performance of the crucial ultrasonic device based on an advanced PMN-PT composite material and may lead to the development of next generation biomedical ultrasonic devices for clinical diagnosis and treatment.
Background: Lung ultrasound (LUS) can be an important imaging tool for the diagnosis and assessment of lung involvement. Ultrasound sonograms have been confirmed to illustrate damage to a person’s lungs, which means that the correct classification and scoring of a patient’s sonogram can be used to assess lung involvement. Methods: The purpose of this study was to establish a lung involvement assessment model based on deep learning. A novel multimodal channel and receptive field attention network combined with ResNeXt (MCRFNet) was proposed to classify sonograms, and the network can automatically fuse shallow features and determine the importance of different channels and respective fields. Finally, sonogram classes were transformed into scores to evaluate lung involvement from the initial diagnosis to rehabilitation. Results and conclusion: Using multicenter and multimodal ultrasound data from 104 patients, the diagnostic model achieved 94.39% accuracy, 82.28% precision, 76.27% sensitivity, and 96.44% specificity. The lung involvement severity and the trend of COVID-19 pneumonia were evaluated quantitatively.