Purpose: Ultrasound (US) and Shear Wave Elastography (SWE) imaging are non-invasive methods used for breast lesion characterization. While US and SWE images provide both morphological information, SWE visualizes in addition the elasticity of tissue. In this study a Discriminative Convolutional Neural Network (DCNN) model is applied to US and SWE images and their combination to classify the breast lesions into malignant or benign cases. Furthermore, it is identified whether analysing only the region of the elastogram or including the surrounding B-mode image gives a superior performance.Methods: The dataset used in this study consists of 746 images obtained from 207 patients comprising 486 malignant and 260 benign breast lesions. From each image the US and SWE image was extracted, once including only the region of the elastogram and once including also the surrounding B-mode image. These four datasets were applied individually to a DCNN to determine their predictive capability. Each the best US and SWE dataset were used to examine different combination methods with DCNN. The results were compared to the manual assessment by an expert radiologist.Results: The combination of US and SWE images with the surrounding B-mode image using two ensembled DCNN models achieved best results with an accuracy of 93.53 %, sensitivity of 94.42 %, specificity of 90.75 % and area under the curve (AUC) of 96.55 %.Conclusion: This study showed that using the whole US and SWE images through DCNN was superior to methods, in which only the region of elastogram was used. Combining breast cancer US and SWE images with two ensembled DCNN models in parallel improved the results. The accuracy, sensitivity and AUC of the best combination method were significantly superior to the results of using a single dataset through DCNN and to the results of the expert radiologist.

This review provides an overview of existing accident prevention methods by monitoring the persons’ physiological state, observing movements, and physiological parameters. Firstly, different physiological parameters monitoring systems are introduced. Secondly, various systems dealing with position recognition on pressure sensing mats are presented. We conduct an in-depth literature search and quantitative analysis of papers published in this area and focus independently of the application (drivers, office and wheelchair users, etc.). Quantitative information about the number of subjects, investigated scenarios, sensor types, machine learning usage, and laboratory vs. real-world works is extracted. In posture recognition, most works recognize at least forward, backward, left and right movements on a seat. The remaining works use the pressure sensing mat for bedridden people. In physiological parameters measurement, most works detect the heart rate and often also add respiration rate recognition. Machine learning algorithms are used in most cases and are taking on an ever-greater importance for classification and regression problems. Although all solutions use different techniques, returning satisfactory results, none of them try to detect small movements, which can pose challenges in determining the optimal sensor topology and sampling frequency required to detect fine movements. For physiological measurements, there are lots of challenges to overcome in noisy environments, notably the detection of heart rate, blood pressure, and respiratory rate at very low signal-to-noise levels.