RESUMO
Analyzing user behavior from usability evaluation can be a challenging and time-consuming task, especially as the number of participants and the scale and complexity of the evaluation grows. We propose UXSENSE, a visual analytics system using machine learning methods to extract user behavior from audio and video recordings as parallel time-stamped data streams. Our implementation draws on pattern recognition, computer vision, natural language processing, and machine learning to extract user sentiment, actions, posture, spoken words, and other features from such recordings. These streams are visualized as parallel timelines in a web-based front-end, enabling the researcher to search, filter, and annotate data across time and space. We present the results of a user study involving professional UX researchers evaluating user data using uxSense. In fact, we used uxSense itself to evaluate their sessions.
RESUMO
It is now well established that for tumour growth and survival, tumour vasculature is an important element. Studies have demonstrated that ultrasound-stimulated microbubble (USMB) treatment causes extensive endothelial cell death leading to tumour vascular disruption. The subsequent rapid vascular collapse translates to overall increases in tumour response to various therapies. In this study, we explored USMB involvement in the enhancement of hyperthermia (HT) treatment effects. Human prostate tumour (PC3) xenografts were grown in mice and were treated with USMB, HT, or with a combination of the two treatments. Treatment parameters consisted of ultrasound pressures of 0 to 740 kPa, the use of perfluorocarbon-filled microbubbles administered intravenously, and an HT temperature of 43°C delivered for various times (0-50 minutes). Single and multiple repeated treatments were evaluated. Tumour response was monitored 24 hours after treatments and tumour growth was monitored for up to over 30 days for a single treatment and 4 weeks for multiple treatments. Tumours exposed to USMB combined with HT exhibited enhanced cell death (p<0.05) and decreased vasculature (p<0.05) compared to untreated tumours or those treated with either USMB alone or HT alone within 24 hours. Deoxynucleotidyl transferase dUTP nick-end labeling (TUNEL) staining and cluster of differentiation 31 (CD31) staining were used to assess cell death and vascular content, respectively. Further, tumours receiving a single combined USMB and HT treatment exhibited decreased tumour volumes (p<0.05) compared to those receiving either treatment alone when monitored over the duration of 30 days. Additionally, tumour response monitored weekly up to 4 weeks demonstrated a reduced vascular index and tumour volume, increased fibrosis and lesser number of proliferating cells with combined treatment of USMB and HT. Thus in this study, we characterize a novel therapeutic approach that combines USMB with HT to enhance treatment responses in a prostate cancer xenograft model in vivo.
