| 1. |
- Eeraerts, Maxime, et al.
(author)
-
Synthesis of highbush blueberry pollination research reveals region-specific differences in the contributions of honeybees and wild bees
- 2023
-
In: Journal of Applied Ecology. - 0021-8901. ; 60:12, s. 2528-2539
-
Research review (peer-reviewed)abstract
- Highbush blueberry production has expanded worldwide in recent decades. To safeguard future yields, it is essential to understand if insect pollination is limiting current blueberry production and which insects contribute to pollination in different production regions. We present a systematic review including a set of meta-analyses on insect-mediated pollination in highbush blueberry. We summarize the geographic distribution of research, the abundance of different pollinator taxa and their relative pollination contributions. Using raw data from 21 studies, totalling 496 site replicates, we determine the degree of pollination service and pollen limitation (i.e. combining open pollination levels with experimental bagged and/or hand pollination treatments), as well as the contribution of honeybees and wild bees to pollination (i.e. observational, open pollination). Most studies originate from North America, focusing on only a few cultivars. Honeybees are the dominant pollinator, and wild bees are occasionally abundant. Wild bees are more efficient pollinators on a single-visit basis compared to honeybees, which increases their relative pollination contribution compared to their relative abundance. Insect-mediated pollination services increased blueberry fruit set, berry weight and seed set (R2 values: 64.8%, 75.9% and 75.2% respectively). We often detected pollen limitation, indicated by an increase in fruit set, berry weight and seed set (R2: 10.1%, 18.2% and 21.5%, respectively), with additional hand pollination. Increasing visitation of honeybees and wild bees contributed to blueberry pollination by increasing fruit set (R2: 5.4% and 3.5%), berry weight (R2: 6.5% and 2.8%) and seed set (R2: 6.4% and 3.8%) respectively. Bee contributions to fruit set and berry weight were variable across regions. Synthesis and application: A diverse community of insects, primarily bees, contributes to highbush blueberry pollination and yield. However, pollination deficits are common. The finding that both honeybees and wild bees enhance pollination highlights the possibility of adopting different management strategies that utilize honeybees, wild bees or both depending on the specific context and region. This further emphasizes the general importance of conserving pollinator health and diversity. Our synthesis highlights data gaps and areas for future research to better understand the pollination contribution of different pollinators to crops that are expanding globally.
|
|
| 2. |
- Morton Colbert, Zachery, et al.
(author)
-
Repurposing traditional U-Net predictions for sparse SAM prompting in medical image segmentation
- 2024
-
In: Biomedical Engineering & Physics Express. - : IOP Publishing. - 2057-1976. ; 10:2
-
Journal article (peer-reviewed)abstract
- Objective:Automated medical image segmentation (MIS) using deep learning has traditionally relied on models built and trained from scratch, or at least fine-tuned on a target dataset. The Segment Anything Model (SAM) by Meta challenges this paradigm by providing zero-shot generalisation capabilities. This study aims to develop and compare methods for refining traditional U-Net segmentations by repurposing them for automated SAM prompting.Approach:A 2D U-Net with EfficientNet-B4 encoder was trained using 4-fold cross-validation on an in-house brain metastases dataset. Segmentation predictions from each validation set were used for automatic sparse prompt generation via a bounding box prompting method (BBPM) and novel implementations of the point prompting method (PPM). The PPMs frequently produced poor slice predictions (PSPs) that required identification and substitution. A slice was identified as a PSP if it (1) contained multiple predicted regions per lesion or (2) possessed outlier foreground pixel counts relative to the patient's other slices. Each PSP was substituted with a corresponding initial U-Net or SAM BBPM prediction. The patients' mean volumetric dice similarity coefficient (DSC) was used to evaluate and compare the methods' performances.Main results:Relative to the initial U-Net segmentations, the BBPM improved mean patient DSC by 3.93 ± 1.48% to 0.847 ± 0.008 DSC. PSPs constituted 20.01-21.63% of PPMs' predictions and without substitution performance dropped by 82.94 ± 3.17% to 0.139 ± 0.023 DSC. Pairing the two PSP identification techniques yielded a sensitivity to PSPs of 92.95 ± 1.20%. By combining this approach with BBPM prediction substitution, the PPMs achieved segmentation accuracies on par with the BBPM, improving mean patient DSC by up to 4.17 ± 1.40% and reaching 0.849 ± 0.007 DSC.Significance:The proposed PSP identification and substitution techniques bridge the gap between PPM and BBPM performance for MIS. Additionally, the uniformity observed in our experiments' results demonstrates the robustness of SAM to variations in prompting style. These findings can assist in the design of both automatically and manually prompted pipelines.
|
|
