CRIS
Permanent URI for this communityhttps://investigadores.udd.cl/handle/123456789/1
Browse
12 results
Search Results
Now showing 1 - 10 of 12
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Interpretable multimodal classification for age-related macular degeneration diagnosis(2024); Xu Yanwu<jats:p>Explainable Artificial Intelligence (XAI) is an emerging machine learning field that has been successful in medical image analysis. Interpretable approaches are able to “unbox” the black-box decisions made by AI systems, aiding medical doctors to justify their diagnostics better. In this paper, we analyze the performance of three different XAI strategies for medical image analysis in ophthalmology. We consider a multimodal deep learning model that combines optical coherence tomography (OCT) and infrared reflectance (IR) imaging for the diagnosis of age-related macular degeneration (AMD). The classification model is able to achieve an accuracy of 0.94, performing better than other unimodal alternatives. We analyze the XAI methods in terms of their ability to identify retinal damage and ease of interpretation, concluding that grad-CAM and guided grad-CAM can be combined to have both a coarse visual justification and a fine-grained analysis of the retinal layers. We provide important insights and recommendations for practitioners on how to design automated and explainable screening tests based on the combination of two image sources.</jats:p>Scopus© Citations 7 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Cross-cultural adaptation and evaluation of the psychometric properties of the University of Wisconsin Running Injury and Recovery Index questionnaire in Spanish (UWRI-S)(2022); Evan O. NelsonScopus© Citations 6 5 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Computer-guided implant surgery and immediate loading with a modifiable radiographic template in a patient with partial edentulism: A clinical report(2015)36Scopus© Citations 7 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, The Combination of Digital Surface Scanners and Cone Beam Computed Tomography Technology for Guided Implant Surgery Using 3Shape Implant Studio Software: A Case History Report(2015)Scopus© Citations 46 3 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, 5Scopus© Citations 52 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Navigation in anterior cruciate ligament reconstruction: State of the art(2022); ; Scopus© Citations 17 1 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Interoception Primes Emotional Processing: Multimodal Evidence from Neurodegeneration(2021)7Scopus© Citations 80 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Students With High Metacognition Are Favourable Towards Individualism When Anxious(2022); <jats:p>Metacognitive ability has been described as an important predictor of several processes involved in learning, including problem-solving. Although this relationship is fairly documented, little is known about the mechanisms that could modulate it. Given its relationship with both constructs, we decided to evaluate the impact of self-knowledge on PS. In addition, we inspected whether emotional (self-reported anxiety) and interpersonal (attitudes towards social interdependence) variables could affect the relationship between metacognition and problem-solving. We tested a sample of 32 undergraduate students and used behavioural tasks and self-report questionnaires. Contrary to the literature, we found no significant relationship between metacognition and problem-solving performance, nor a significant moderating effect when including emotional and interpersonal variables in the model. In contrast, we observed a significant moderating model combining metacognition, self-reported anxiety and attitudes towards social interdependence. It was found that participants with high metacognition reported attitudes unfavourable towards interdependence when they felt high anxiety. These results suggest that already anxious individuals with high metacognition would prefer to work alone rather than with others, as a coping mechanism against further anxiety derived from cooperation. We hypothesise that in anxiogenic contexts, metacognition is used as a tool to compare possible threats with one’s own skills and act accordingly, in order to maximise one’s own performance. Further studies are needed to understand how metacognition works in contexts adverse to learning.</jats:p>Scopus© Citations 2 1 1 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Right cerebral motor areas that support accurate speech production following damage to cerebellar speech areas(2021)19Scopus© Citations 4 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Evaluation of the precision and accuracy of a food registry survey with digital image support in real time(2019)8Scopus© Citations 2