Artificial Intelligence Computer-Assisted Diagnosis for Thyroid Nodules: Comparison of Diagnostic Performance Using Original and Mobile Ultrasonography Images

Background and Objectives@#This study investigated whether an artificial intelligence computer-assisted diagnosis (AI-CAD) software recently developed in our institution named the Severance Artificial intelligence program (SERA) could show similar diagnostic performance for thyroid cancers using ultrasonographic (US) images from a mobile phone (SERA_M) compared to using images directly downloaded from the pictures archive and communication system (PACS) (SERA_P). @*Materials and Methods@#From October 2019 to December 2019, 259 thyroid nodules from 259 patients were included. SERA was run on original and mobile images to evaluate SERA_P and SERA_M. Nodules were categorized according to the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS). To compare diagnostic performance, a logistic regression analysis was conducted using the Generalized Estimating Equation. The area under the curve (AUC) was calculated using the receiver operating characteristic (ROC) curve, and compared using the Delong Method. @*Results@#There were 40 cancers (15.4%) and 219 benign lesions (84.6%). The AUC and sensitivity of SERA_M (0.82 and 85%, respectively) were not statistically different from SERA_P (0.8 and 75%, respectively) (p=0.526 and p=0.091, respectively). The AUC of radiologists (0.856) was not significantly different compared to SERA_P and SERA_M (p=0.163 and p=0.414, respectively). The sensitivity of radiologists (77.5%) was not statistically different compared to SERA_P and SERA_M (p=0.739 and p=0.361, respectively). @*Conclusion@#AI-CAD software using pictures taken by a mobile phone showed comparable diagnostic performance with the same software using images directly from PACS.

Utility of a Three-Dimensional Interactive Augmented Reality Program for Balance and Mobility Rehabilitation in the Elderly: A Feasibility Study

OBJECTIVE: To improve lower extremity function and balance in elderly persons, we developed a novel, three-dimensional interactive augmented reality system (3D ARS). In this feasibility study, we assessed clinical and kinematic improvements, user participation, and the side effects of our system. METHODS: Eighteen participants (age, 56-76 years) capable of walking independently and standing on one leg were recruited. The participants received 3D ARS training during 10 sessions (30-minute duration each) for 4 weeks. Berg Balance Scale (BBS) and the Timed Up and Go (TUG) scores were obtained before and after the exercises. Outcome performance variables, including response time and success rate, and kinematic variables, such as hip and knee joint angle, were evaluated after each session. RESULTS: Participants exhibited significant clinical improvements in lower extremity balance and mobility following the intervention, as shown by improved BBS and TUG scores (p<0.001). Consistent kinematic improvements in the maximum joint angles of the hip and knee were observed across sessions. Outcome performance variables, such as success rate and response time, improved gradually across sessions, for each exercise. The level of participant interest also increased across sessions (p<0.001). All participants completed the program without experiencing any adverse effects. CONCLUSION: Substantial clinical and kinematic improvements were observed after applying a novel 3D ARS training program, suggesting that this system can enhance lower extremity function and facilitate assessments of lower extremity kinematic capacity.

Social Pressure-Induced Craving in Patients with Alcohol Dependence: Application of Virtual Reality to Coping Skill Training

OBJECTIVE: This study was conducted to assess the interaction between alcohol cues and social pressure in the induction of alcohol craving. METHODS: Fourteen male patients with alcohol dependence and 14 age-matched social drinkers completed a virtual reality coping skill training program composed of four blocks according to the presence of alcohol cues (x2) and social pressure (x2). Before and after each block, the craving levels were measured using a visual analogue scale. RESULTS: Patients with alcohol dependence reported extremely high levels of craving immediately upon exposure to a virtual environment with alcohol cues, regardless of social pressure. In contrast, the craving levels of social drinkers were influenced by social pressure from virtual avatars. CONCLUSION: Our findings imply that an alcohol cue-laden environment should interfere with the ability to use coping skills against social pressure in real-life situations.