| 1. |
- Mehta, Raghav, et al.
(författare)
-
QU-BraTS : MICCAI BraTS 2020 Challenge on QuantifyingUncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
- 2022
-
Ingår i: Journal of Machine Learning for Biomedical Imaging. - 2766-905X. ; , s. 1-54
-
Tidskriftsartikel (refereegranskat)abstract
- Deep learning (DL) models have provided the state-of-the-art performance in a wide variety of medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder the translation of DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties, could enable clinical review of the most uncertain regions, thereby building trust and paving the way towards clinical translation. Recently, a number of uncertainty estimation methods have been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019-2020 task on uncertainty quantification (QU-BraTS), and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions, and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentages of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, and hence highlight the need for uncertainty quantification in medical image analyses. Our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS
|
|
| 2. |
- McHugh, Laura, et al.
(författare)
-
Salient sights and sounds : comparing visual and auditory stimuli remembrance using audio set ontology and sonic mapping
- 2023
-
Ingår i: SMC 2023. - : Sound and Music Computing Network. ; , s. 426-432
-
Konferensbidrag (refereegranskat)abstract
- In this study, we explore how store customers recall their perceptual experience with a focus on comparing the remembrance of auditory and visual stimuli. The study was carried out using a novel mixed-methods approach that involved Deep Hanging Out, field study and interviews, including drawing sonic mind maps. The data collected was analysed using thematic analysis, sound classification with the Audio Set ontology, counting occurrences of different auditory and visual elements attended in the store, and rating the richness of their descriptions. The results showed that sights were more salient than sounds and that participants recalled music more frequently compared to the Deep Hanging Out observations, but remembered fewer varieties of sounds in general.
|
|
| 3. |
|
|
| 4. |
- Theurich, Melissa Ann, et al.
(författare)
-
Breastfeeding Rates and Programs in Europe : A Survey of 11 National Breastfeeding Committees and Representatives
- 2019
-
Ingår i: Journal of Pediatric Gastroenterology and Nutrition - JPGN. - : Lippincott Williams & Wilkins. - 0277-2116 .- 1536-4801. ; 68:3, s. 400-407
-
Tidskriftsartikel (refereegranskat)abstract
- INTRODUCTION: Among the world's regions, the WHO European Region has the lowest rates of exclusive breastfeeding at age 6 months with around 25%. Low rates and early cessation of breastfeeding have important adverse health consequences for women, infants and young children. Protecting, promoting and supporting breastfeeding are a public health priority.OBJECTIVES: National breastfeeding data and monitoring systems among selected European countries and the WHO European Region are compared. Mechanisms for the support, protection and promotion of breastfeeding are reviewed and successes and challenges in implementation of national programs are presented.METHODS: National representatives of national breastfeeding committees and initiatives in eleven European countries, including Belgium, Croatia, Denmark, Germany, Ireland, Italy, The Netherlands, Norway, Spain, Sweden and Switzerland, participated in a standardized survey. Results are evaluated and compared in a narrative review.RESULTS: Variation exists in Europe on breastfeeding rates, methodology for data collection and mechanisms for support, protection and promotion of breastfeeding. Directly after birth, between 56 and 98 % of infants in all countries were reported to receive any human milk, and at 6 months 38-71% and 13-39 % of infants to be breastfed or exclusively breastfed, respectively. National plans addressing breastfeeding promotion, protection and support exist in 6 of the 11 countries.CONCLUSIONS: National governments should commit to evidence-based breastfeeding monitoring and promotion activities, including financial and political support, to improve breastfeeding rates in the Europe. Renewed efforts for collaboration between countries in Europe, including a sustainable platform for information exchange, are needed.
|
|
