Exploiting Patch Sizes and Resolutions for Multi-Scale Deep Learning in Mammogram Image Classification.

Recent progress in deep learning (DL) has revived the interest on DL-based computer aided detection or diagnosis (CAD) systems for breast cancer screening. Patch-based approaches are one of the main state-of-the-art techniques for 2D mammogram image classification, but they are intrinsically limited by the choice of patch size, as there is no unique patch size that is adapted to all lesion sizes. In addition, the impact of input image resolution on performance is not yet fully understood. In this work, we study the impact of patch size and image resolution on the classifier performance for 2D mammograms. To leverage the advantages of different patch sizes and resolutions, a multi patch-size classifier and a multi-resolution classifier are proposed. These new architectures perform multi-scale classification by combining different patch sizes and input image resolutions. The AUC is increased by 3% on the public CBIS-DDSM dataset and by 5% on an internal dataset. Compared with a baseline single patch size and single resolution classifier, our multi-scale classifier reaches an AUC of 0.809 and 0.722 in each dataset.

Fall detection using smart floor sensor and supervised learning.

Falls are a major risk for elderly people's health and independence. Fast and reliable fall detection systems can improve chances of surviving the accident and coping with its physical and psychological consequences. Recent research has come up with various solutions, all suffering from significant drawbacks, one of them being the intrusiveness into patient's life. This paper proposes a novel fall detection monitoring system based on a sensitive floor sensor made out of a piezoelectric material and a machine learning approach. The detection is done by a combination between a supervised Random Forest and an aggregation of its output over time. The database was made using acquisitions from 28 volunteers simulating falls and other behaviours. Unlike existent fall detection systems, our solution offers the advantages of having a passive sensor (no power supply is needed) and being completely unobtrusive since the sensor comes with the floor. Results are compared with state-of-the-art classification algorithms. On our database, good performance of fall detection was obtained with a True Positive Rate of 94.4% and a False Positive Rate of 2.4%.