Automatic detection and classification of the masses in mammograms are still a big challenge and play a crucial role to assist radiologists for accurate diagnosis. In this paper, we propose a novel computer-aided diagnose (CAD) system based on one of the regional deep learning techniques: a ROI-based Convolutional Neural Network (CNN) which is called You Only Look Once (YOLO). Our proposed YOLO-based CAD system contains four main stages: mammograms preprocessing, feature extraction utilizing multi convolutional deep layers, mass detection with confidence model, and finally mass classification using fully connected neural network (FC-NN). A set of training mammograms with the information of ROI masses and their types are used to train YOLO. The trained YOLO-based CAD system detects the masses and classifies their types into benign or malignant. Our results show that the proposed YOLO-based CAD system detects the mass location with an overall accuracy of 96.33%. The system also distinguishes between benign and malignant lesions with an overall accuracy of 85.52%. Our proposed system seems to be feasible as a CAD system capable of detection and classification at the same time. It also overcomes some challenging breast cancer cases such as the mass existing in the pectoral muscles or dense regions.

Dual high and low energy images of Dual Energy X-ray Absorptiometry (DEXA) suffer from noises due to the use of weak amount of X-rays. Denoising these DEXA images could be a key process to enhance and improve a Bone Mineral Density (BMD) map which is derived from a pair of high and low energy images. This could further improve the accuracy of diagnosis of bone fractures, osteoporosis, and etc. In this paper, we present a denoising technique for dual high and low energy images of DEXA via non-local means filter (NLMF). The noise of dual DEXA images is modeled based on both source and detector noises of a DEXA system. Then, the parameters of the proposed NLMF are optimized for denoising utilizing the experimental data from uniform phantoms. The optimized NLMF is tested and verified with the DEXA images of the uniform phantoms and real human spine. The quantitative evaluation shows the improvement of Signal-to-Noise Ratio (SNR) for the high and low phantom images on the order of 30.36% and 27.02% and for the high and low real spine images on the order of 22.28% and 33.43%, respectively. Our work suggests that denoising via NLMF could be a key preprocessing process for clinical DEXA imaging.

Recognizing and recording human activities using a smart sensor device is an essential technology for smart living. The recorded activities (i.e., life logs) could be used as valuable information to support smart life, lifecare, and healthcare services. For sensing human activities, smart sensors are required and most smart devices such as smart phones, smart bands, and smart watches incorporate Inertial Measurement Units (IMUs) which could be utilized for this purpose. However, implementing a robust Human Activity Recognition (HAR) system with high recognition accuracy using only a single sensor (i.e., no multiple sensors) is still a technical challenge. In this paper, we propose novel deep learning-based HAR systems with a single wrist IMU sensor. We used time series activity data from only one IMU sensor at a wrist to build two deep learning algorithm-based HAR systems: one is based on Convolutional Neural Nets (CNN) and the other Recurrent Neural Nets (RNN). Our two HAR systems are evaluated by 5-fold cross-validation tests to compare the performance of both systems. Five primary daily activities including standing, walking, running, walking downstairs, and walking upstairs were recognized. Our results show that the CNN-based HAR system achieved an average accuracy of 95.43% and the RNN-based HAR system an accuracy of 96.95%.