Application of deep learning for the analysis of stomata: A review of current methods and future directions.

Plant physiology and metabolism relies on the function of stomata, structures on the surface of above ground organs, which facilitate the exchange of gases with the atmosphere. The morphology of the guard cells and corresponding pore which make up the stomata, as well as the density (number per unit area) are critical in determining overall gas exchange capacity. These characteristics can be quantified visually from images captured using microscopes, traditionally relying on time-consuming manual analysis. However, deep learning (DL) models provide a promising route to increase the throughput and accuracy of plant phenotyping tasks, including stomatal analysis. Here we review the published literature on the application of DL for stomatal analysis. We discuss the variation in pipelines used; from data acquisition, pre-processing, DL architecture and output evaluation to post processing. We introduce the most common network structures, the plant species that have been studied, and the measurements that have been performed. Through this review, we hope to promote the use of DL methods for plant phenotyping tasks and highlight future requirements to optimise uptake; predominantly focusing on the sharing of datasets and generalisation of models as well as the caveats associated with utilising image data to infer physiological function.

Diabetes management in older adults who fall: a study amongst older adults presenting to the emergency department.

INTRODUCTION: Type 2 diabetes mellitus (T2D) is associated with poor health outcomes whilst tight glycaemic targets are questionable in those aged over 70 years with increased frailty. Our aim was to examine whether people with T2D admitted to hospital with a fall, were more likely to have greater frailty, increased mortality and co-morbidity burden, or risk factors for falls than people without T2D, and whether these differences were associated with medications used for the treatment of T2D. METHODS: The Older Persons Assessment Service (OPAS) is a local emergency department (ED) service, which accepts patients on frailty criteria. The OPAS accepts patients primarily aged over 70 years who present with frailty and geriatric syndromes such as falls, with retrieval from the ED department directly to the service from triage. The OPAS databank was analysed for people with T2D admitted with a fall between June 2020-September 2022. We examined clinical outcomes relating to medication, age, Charlson co-morbidity index (CCI) and clinical frailty score (CFS). RESULTS: 1081 patients were included: 294 (27.2%) with T2D and a mean HbA1c of 53.9 (± 15.8) mmol/mol [7.1%]. People with T2D had a similar mean CFS and age compared to those without T2D, but higher mean CCI (7.0 ± 2.2 vs 5.9 ± 2.1, p < 0.001). Of those people with T2D, 175 (59.5%) and 240 (81.6%) had a HbA1c ≤ 53 mmol/mol [7.0%] and ≤ 64 mmol/mol [8.0%], respectively. In total, 48 (16.3%) people with T2D were identified to have a capillary blood glucose below 4.0 mmol/L on admission to the ED. At 12 months' follow-up, 831 (76.9%) patients were alive and 250 (23.1%) had died. People with T2D treated with insulin and/or gliclazide had a greater 1-year mortality (36.6% vs 23.6%, p < 0.05), greater frequency of hypoglycaemia (35.4% vs 11.8%, p < 0.001), and greater HbA1c (65.5 ± 17.2 mmol/mol [8.2] vs 48.9 ± 12.1 mmol/mol [6.6%]) compared to those who used other agents. Logistic regression confirmed a diagnosis of T2D was associated with 1-year mortality, but mortality was not significantly associated with hypoglycaemic-inducing agents. People with T2D were not more likely to live in deprived areas. CONCLUSIONS: A diagnosis of T2D is associated with greater 1-year mortality, and may be influenced by use of hypoglycaemia-inducing diabetes medications. Clinician awareness can support de-prescribing for patients with frailty and HbA1c < 64 mmol/mol.

Improving crop yield potential: Underlying biological processes and future prospects.

The growing world population and global increases in the standard of living both result in an increasing demand for food, feed and other plant-derived products. In the coming years, plant-based research will be among the major drivers ensuring food security and the expansion of the bio-based economy. Crop productivity is determined by several factors, including the available physical and agricultural resources, crop management, and the resource use efficiency, quality and intrinsic yield potential of the chosen crop. This review focuses on intrinsic yield potential, since understanding its determinants and their biological basis will allow to maximize the plant's potential in food and energy production. Yield potential is determined by a variety of complex traits that integrate strictly regulated processes and their underlying gene regulatory networks. Due to this inherent complexity, numerous potential targets have been identified that could be exploited to increase crop yield. These encompass diverse metabolic and physical processes at the cellular, organ and canopy level. We present an overview of some of the distinct biological processes considered to be crucial for yield determination that could further be exploited to improve future crop productivity.

Photoacclimation and entrainment of photosynthesis by fluctuating light varies according to genotype in Arabidopsis thaliana.

Acclimation of photosynthesis to light intensity (photoacclimation) takes days to achieve and so naturally fluctuating light presents a potential challenge where leaves may be exposed to light conditions that are beyond their window of acclimation. Experiments generally have focused on unchanging light with a relatively fixed combination of photosynthetic attributes to confer higher efficiency in those conditions. Here a controlled LED experiment and mathematical modelling was used to assess the acclimation potential of contrasting Arabidopsis thaliana genotypes following transfer to a controlled fluctuating light environment, designed to present frequencies and amplitudes more relevant to natural conditions. We hypothesize that acclimation of light harvesting, photosynthetic capacity and dark respiration are controlled independently. Two different ecotypes were selected, Wassilewskija-4 (Ws), Landsberg erecta (Ler) and a GPT2 knock out mutant on the Ws background (gpt2-), based on their differing abilities to undergo dynamic acclimation i.e. at the sub-cellular or chloroplastic scale. Results from gas exchange and chlorophyll content indicate that plants can independently regulate different components that could optimize photosynthesis in both high and low light; targeting light harvesting in low light and photosynthetic capacity in high light. Empirical modelling indicates that the pattern of 'entrainment' of photosynthetic capacity by past light history is genotype-specific. These data show flexibility of photoacclimation and variation useful for plant improvement.

Sunflecks in the upper canopy: dynamics of light-use efficiency in sun and shade leaves of Fagus sylvatica.

Sunflecks are transient patches of direct radiation that provide a substantial proportion of the daily irradiance to leaves in the lower canopy. In this position, faster photosynthetic induction would allow for higher sunfleck-use efficiency, as is commonly reported in the literature. Yet, when sunflecks are too few and far between, it may be more beneficial for shade leaves to prioritize efficient photosynthesis under shade. We investigated the temporal dynamics of photosynthetic induction, recovery under shade, and stomatal movement during a sunfleck, in sun and shade leaves of Fagus sylvatica from three provenances of contrasting origin. We found that shade leaves complete full induction in a shorter time than sun leaves, but that sun leaves respond faster than shade leaves due to their much larger amplitude of induction. The core-range provenance achieved faster stomatal opening in shade leaves, which may allow for better sunfleck-use efficiency in denser canopies and lower canopy positions. Our findings represent a paradigm shift for future research into light fluctuations in canopies, drawing attention to the ubiquitous importance of sunflecks for photosynthesis, not only in lower-canopy leaves where shade is prevalent, but particularly in the upper canopy where longer sunflecks are more common due to canopy openness.

A Deep Learning Method for Fully Automatic Stomatal Morphometry and Maximal Conductance Estimation.

Stomata are integral to plant performance, enabling the exchange of gases between the atmosphere and the plant. The anatomy of stomata influences conductance properties with the maximal conductance rate, g smax, calculated from density and size. However, current calculations of stomatal dimensions are performed manually, which are time-consuming and error prone. Here, we show how automated morphometry from leaf impressions can predict a functional property: the anatomical gsmax. A deep learning network was derived to preserve stomatal morphometry via semantic segmentation. This forms part of an automated pipeline to measure stomata traits for the estimation of anatomical gsmax. The proposed pipeline achieves accuracy of 100% for the distinction (wheat vs. poplar) and detection of stomata in both datasets. The automated deep learning-based method gave estimates for gsmax within 3.8 and 1.9% of those values manually calculated from an expert for a wheat and poplar dataset, respectively. Semantic segmentation provides a rapid and repeatable method for the estimation of anatomical gsmax from microscopic images of leaf impressions. This advanced method provides a step toward reducing the bottleneck associated with plant phenotyping approaches and will provide a rapid method to assess gas fluxes in plants based on stomata morphometry.

The effect of canopy architecture on the patterning of "windflecks" within a wheat canopy.

Under field conditions, plants are subject to wind-induced movement which creates fluctuations of light intensity and spectral quality reaching the leaves, defined here as windflecks. Within this study, irradiance within two contrasting wheat (Triticum aestivum) canopies during full sun conditions was measured using a spectroradiometer to determine the frequency, duration and magnitude of low- to high-light events plus the spectral composition during wind-induced movement. Similarly, a static canopy was modelled using three-dimensional reconstruction and ray tracing to determine fleck characteristics without the presence of wind. Corresponding architectural traits were measured manually and in silico including plant height, leaf area and angle plus biomechanical properties. Light intensity can differ up to 40% during a windfleck, with changes occurring on a sub-second scale compared to ~5 min in canopies not subject to wind. Features such as a shorter height, more erect leaf stature and having an open structure led to an increased frequency and reduced time interval of light flecks in the CMH79A canopy compared to Paragon. This finding illustrates the potential for architectural traits to be selected to improve the canopy light environment and provides the foundation to further explore the links between plant form and function in crop canopies.