Leveraging radiomics and machine learning to differentiate radiation necrosis from recurrence in patients with brain metastases.

OBJECTIVE: Radiation necrosis (RN) can be difficult to radiographically discern from tumor progression after stereotactic radiosurgery (SRS). The objective of this study was to investigate the utility of radiomics and machine learning (ML) to differentiate RN from recurrence in patients with brain metastases treated with SRS. METHODS: Patients with brain metastases treated with SRS who developed either RN or tumor reccurence were retrospectively identified. Image preprocessing and radiomic feature extraction were performed using ANTsPy and PyRadiomics, yielding 105 features from MRI T1-weighted post-contrast (T1c), T2, and fluid-attenuated inversion recovery (FLAIR) images. Univariate analysis assessed significance of individual features. Multivariable analysis employed various classifiers on features identified as most discriminative through feature selection. ML models were evaluated through cross-validation, selecting the best model based on area under the receiver operating characteristic (ROC) curve (AUC). Specificity, sensitivity, and F1 score were computed. RESULTS: Sixty-six lesions from 55 patients were identified. On univariate analysis, 27 features from the T1c sequence were statistically significant, while no features were significant from the T2 or FLAIR sequences. For clinical variables, only immunotherapy use after SRS was significant. Multivariable analysis of features from the T1c sequence yielded an AUC of 76.2% (standard deviation [SD] ± 12.7%), with specificity and sensitivity of 75.5% (± 13.4%) and 62.3% (± 19.6%) in differentiating radionecrosis from recurrence. CONCLUSIONS: Radiomics with ML may assist the diagnostic ability of distinguishing RN from tumor recurrence after SRS. Further work is needed to validate this in a larger multi-institutional cohort and prospectively evaluate it's utility in patient care.

MoTI: A Multi-Stage Algorithm for Moving Object Identification in SLAM.

Simultaneous localization and mapping (SLAM) algorithms are widely applied in fields such as autonomous driving and target tracking. However, the effect of moving objects on localization and mapping remains a challenge in natural dynamic scenarios. To overcome this challenge, this paper proposes an algorithm for dynamic point cloud detection that fuses laser and visual identification data, the multi-stage moving object identification algorithm (MoTI). The MoTI algorithm consists of two stages: rough processing and precise processing. In the rough processing stage, a statistical method is employed to preliminarily detect dynamic points based on the range image error of the point cloud. In the precise processing stage, the radius search strategy is used to statistically test the nearest neighbor points. Next, visual identification information and point cloud registration results are fused using a method of statistics and information weighting to construct a probability model for identifying whether a point cloud cluster originates from a moving object. The algorithm is integrated into the front-end of the LOAM system, which significantly improves the localization accuracy. The MoTI algorithm is evaluated on an actual indoor dynamic environment and several KITTI datasets, and the results demonstrate its ability to accurately detect dynamic targets in the background and improve the localization accuracy of the robot.

De-evolving human eyes: The effect of eye camouflage on human attention.

Eyes are communicative. But what happens when eyes are camouflaged? In the present study, while either wearing sunglasses (that camouflaged the eyes) or clear glasses, participants were presented with sexually provocative and neutral images, which they viewed in the presence of another person who they knew was observing their eyes. Unbeknownst to the participants, however, we also surreptitiously monitored and recorded their eye gaze in both conditions. People spontaneously looked more and for longer at the sexually provocative images when their eyes were camouflaged by sunglasses. This finding provides convergent evidence for the proposal that covert attention operates in service of overt social attention, and suggests that decoupling overt and covert attention is much more prevalent than previously assumed. In doing so it also sheds light on the relation between the evolution of human eye morphology and systems of attention.

Factors Influencing Continued Usage Behavior on Mobile Health Applications.

(1) Background: As people pay more attention to health, mobile health applications (mHealth apps) are becoming popular. These apps offer health services that run on mobile devices to help improve users' health behaviors. However, few studies explore what motivates users to continue to use these apps. This study proposes antecedents influencing users' electronic satisfaction (e-satisfaction) and their continued behaviors of using mHealth apps. Based on the extended Unified Theory of Acceptance and Use of Technology (UTAUT2), this study constructs a research model including perceived reliability and online review to predict the continued usage behavior on mHealth apps in China; (2) Methods: We conduct an online survey to collect data from participants who have used mHealth apps. This study receives 327 valid responses and tests the research model using the partial least squares structural equation model approach; (3) Results: Our results find that antecedents positively affect continued usage intention through the mediation role of e-satisfaction with mHealth apps. Interestingly, this study reveals that habit positively affects the continued usage behavior and moderates the effect of e-satisfaction and continued intention of using mHealth apps; (4) Conclusions: This study presents theoretical implications on the extended UTAUT2 and provides practical implications understanding of managing mHealth apps in China.

Autonomous Search of Radioactive Sources through Mobile Robots.

The research of robotic autonomous radioactivity detection or radioactive source search plays an important role in the monitoring and disposal of nuclear safety and biological safety. In this paper, a method for autonomously searching for radioactive sources through mobile robots was proposed. In the method, by using a partially observable Markov decision process (POMDP), the search of autonomous unknown radioactive sources was realized according to a series of radiation information measured by mobile robot. First, the factors affecting the accuracy of radiation measurement during the robot's movement were analyzed. Based on these factors, the behavior set of POMDP was designed. Secondly, the parameters of the radioactive source were estimated in the Bayesian framework. In addition, through the reward strategy, autonomous navigation of the robot to the position of the radiation source was achieved. The search algorithm was simulated and tested, and the TurtleBot robot platform was used to conduct a real search experiment on the radio source Cs-137 with an activity of 37 MBq indoors. The experimental results showed the effectiveness of the method. Additionally, from the experiments, it could been seen that the robot was affected by the linear velocity, angular velocity, positioning accuracy and the number of measurements in the process of autonomous search for the radioactive source. The proposed mobile robot autonomous search method can be applied to the search for lost radioactive sources, as well as for the leakage of substances (nuclear or chemical) in nuclear power plants and chemical plants.

SR9009 has REV-ERB-independent effects on cell proliferation and metabolism.

The nuclear receptors REV-ERBα and -ß link circadian rhythms and metabolism. Like other nuclear receptors, REV-ERB activity can be regulated by ligands, including naturally occurring heme. A putative ligand, SR9009, has been reported to elicit a range of beneficial effects in healthy as well as diseased animal models and cell systems. However, the direct involvement of REV-ERBs in these effects of SR9009 has not been thoroughly assessed, as experiments were not performed in the complete absence of both proteins. Here, we report the generation of a mouse model for conditional genetic deletion of REV-ERBα and -ß. We show that SR9009 can decrease cell viability, rewire cellular metabolism, and alter gene transcription in hepatocytes and embryonic stem cells lacking both REV-ERBα and -ß. Thus, the effects of SR9009 cannot be used solely as surrogate for REV-ERB activity.

Relationship Between Internet Health Information and Patient Compliance Based on Trust: Empirical Study.

BACKGROUND: The internet has become a major mean for acquiring health information; however, Web-based health information is of mixed quality and may markedly affect patients' health-related behavior and decisions. According to the social information processing theory, patients' trust in their physicians may potentially change due to patients' health-information-seeking behavior. Therefore, it is important to identify the relationship between internet health information and patient compliance from the perspective of trust. OBJECTIVE: The objective of our study was to investigate the effects of the quality and source of internet health information on patient compliance using an empirical study based on the social information processing theory and social exchange theory. METHODS: A Web-based survey involving 336 valid participants was conducted in China. The study included independent variables (internet health information quality and source of information), 2 mediators (cognition-based trust [CBT] and affect-based trust [ABT]), 1 dependent variable (patient compliance), and 3 control variables (gender, age, and job). All variables were measured using multiple-item scales from previously validated instruments, and confirmative factor analysis as well as structural equation modeling was used to test hypotheses. RESULTS: The questionnaire response rate was 77.16% (375/486), validity rate was 89.6% (336/375), and reliability and validity were acceptable. We found that the quality and source of internet health information affect patient compliance through the mediation of CBT and ABT. In addition, internet health information quality has a stronger influence on patient compliance than the source of information. However, CBT does not have any direct effect on patient compliance, but it directly affects ABT and then indirectly impacts patient compliance. Therefore, the effect of ABT seems stronger than that of CBT. We found an unexpected, nonsignificant relationship between the source of internet health information and ABT. CONCLUSIONS: From patients' perspective, internet health information quality plays a stronger role than its source in impacting their trust in physicians and the consequent compliance with physicians. Therefore, patient compliance can be improved by strengthening the management of internet health information quality. The study findings also suggest that physicians should focus on obtaining health information from health websites, thereby expanding their understanding of patients' Web-based health-information-seeking preferences, and enriching their knowledge structure to show their specialization and reliability in the communication with patients. In addition, the mutual demonstration of care and respect in the communication between physicians and patients is important in promoting patients' ABT in their physicians.

Mature or Emerging? The Impact of Treatment-Related Internet Health Information Seeking on Patients' Trust in Physicians.

Years of clinical trials have proven the maturity and safety of certain treatments, however, some of these mature treatments may not be highly effective. Several treatments have emerged through technological innovations, but their long-term safety, efficacy, and adverse effects remain unknown. At present, many patients seek information related to their treatments on the Internet, which may impact their attitudes towards different treatments and their trust in physicians. In this study, a research model was developed to examine how patients' trust in their physicians is influenced by related online information on mature or emerging treatments. The hypotheses were tested using confirmatory factor analysis (CFA) and structural equation modelling (SEM). A total of 336 valid responses were collected through an online survey. Mature treatments related health information was found to significantly improve patients' trust. Thus, physicians should pay more attention to mature treatments, and encourage their patients to seek related information online. Moreover, the quality of online information should be developed further to increase patients' satisfaction. Physicians should also consider their patients' psychological safety in communication with patients to strengthen their trust.