AI-Driven Realtime Monitoring of Early Indicators for Ichthyophthirius multifiliis Infection of Rainbow Trout.

A novel video-based real-time system based on AI (artificial intelligence) was developed to detect clinical signs in fish exposed to pathogens. We selected a White Spot Disease model involving rainbow trout as the experimental animal and the parasitic ciliate Ichthyophthirius multifiliis as a pathogen. We compared two identical fish tank systems: one tank was infected by co-habitation, whereas the other tank was kept non-infected (sham infection). The two fish tanks were separately video monitored (full top and side view) during the course of infection, during which fish were removed whenever they developed clinical signs (direct visual inspection by the observer). Image analysis (object detection, classification and tracking) was used to track behavioural changes in fish (in every recorded video frame), focusing on movement patterns and spatial localisation. Initially, the two fish groups (infected and non-infected) exhibited similar behaviour and non-infected fish did not change behaviour during the 15 d observation period (from 5 d before infection until 10 dpi). At 4, 7, 8, 9 and 10 dpi some infected fish showed clinical signs (equilibrium disturbance, gasping and lethargy) and were removed from the experiment. Anorexia occurred from 5 dpi and a gradual progression of gasping behaviour was noted, whereas the frequency of fish flashing (rubbing/scratching against objects) was low. Equilibrium disturbances and the development of white spots in the skin appeared to be a much later (8-10 dpi at this temperature) indicator of infection. The video analysis showed a general distribution of non-infected fish in all parts of the fish tank during the entire experiment, whereas infected fish already at 4-5 dpi moved towards higher water currents in the top and bottom positions. This change of fish positioning within the tank appeared as a promising early indicator of infection. The study suggests that continuous monitoring of fish behaviour using AI can potentially optimise the timing of humane endpoints, indicate disease signs earlier and thereby improve animal welfare in both animal experimentation and in aquaculture settings.

Levels and risk assessment of chemical contaminants in byproducts for animal feed in Denmark.

With aim to provide information on chemical contaminants in byproducts in animal feed, the data from an official control by the Danish Plant Directorate during 1998-2009, were reviewed and several samples of citrus pulp and dried distillers grains with solubles (DDGS) were additionally collected for analysis and risk assessment. The levels of contaminants in the samples from the official control were below maximum limits from EU regulations with only a few exceptions in the following groups; dioxins and dioxin-like polychlorobiphenyls (PCBs) in fish-containing byproducts and dioxins in vegetable and animal fat, hydrogen cyanide in linseed, and cadmium in sunflowers. The levels of pesticides and mycotoxins in the additionally collected samples were below maximum limits. Enniatin B (ENN B) was present in all DDGS samples. The hypothetical cases of carry-over of contamination from these byproducts were designed assuming total absorption and accumulation of the ingested contaminant in meat and milk and high exposure (a byproduct formed 15-20% of the feed ration depending on the species). The risk assessment was refined based on literature data on metabolism in relevant animal species. Risk assessment of contaminants in byproducts is generally based on a worst-case approach, as data on carry-over of a contaminant are sparse. This may lead to erroneous estimation of health hazards. The presence of ENN B in all samples of DDGS indicates that potential impact of this emerging mycotoxin on feed and food safety deserves attention. A challenge for the future is to fill up gaps in toxicological databases and improve models for carry-over of contaminants.

Effect of Stocking Density during CO2 Stunning of Pigs on Induction Time and Activity Level Measured Using AI.

During the CO2 stunning of pigs, a variation in their reaction to the gas and the duration of the induction period is observed. The stunning process can be affected by several conditions, such as stressful events and previous experiences, but the stocking density in the gondola may also have an impact. The objective was to investigate the effect of stocking density on the stunning process under commercial conditions. To quantify the pigs' reactions under industrial settings with a stocking density of up to eight pigs pr. Gondola (3.91 m2), the activity level was measured using an AI solution. Compared with a simulation of the expected induction period, a significantly longer induction period was found in gondolas containing seven and eight pigs (p < 0.001) but not when the gondolas contained three or four pigs. Both high and mean activity levels were significantly higher when stocking density was increased from three or four pigs to seven or eight pigs. The stunning process was thus negatively affected when increasing the stocking density. More knowledge is needed to explain this effect and to make statements on optimal stocking density. The measured activity levels may be a useful tool for obtaining information under commercial conditions and for documenting animal welfare.