Aquaculture produces more than 122 million tons of fish globally. Among the several economically important species are the Serrasalmidae, which are valued for their nutritional and sensory characteristics. To meet the growing demand, there is a need for automation and accuracy of processes, at a lower cost. Convolutional neural networks (CNNs) are a viable alternative for automation, reducing human intervention, work time, errors, and production costs. Therefore, the objective of this work is to evaluate the efficacy of convolutional neural networks (CNNs) in counting round fish fingerlings (Serrasalmidae) at different densities using 390 color photographs in an illuminated environment. The photographs were submitted to two convolutional neural networks for object detection: one model was adapted from a pre-trained CNN and the other was an online platform based on AutoML. The metrics used for performance evaluation were precision (P), recall (R), accuracy (A), and F1-Score. In conclusion, convolutional neural networks (CNNs) are effective tools for detecting and counting fish. The pre-trained CNN demonstrated outstanding performance in identifying fish fingerlings, achieving accuracy, precision, and recall rates of 99% or higher, regardless of fish density. On the other hand, the AutoML exhibited reduced accuracy and recall rates as the number of fish increased.

This study evaluates the efficacy of a new florfenicol-based drug, both in vitro and in vivo, in Nile tilapia (Oreochromis niloticus) against pathogens commonly found in fish farming and its withdrawal period. The drug’s efficacy was tested using prophylactic, metaphylactic, and therapeutic approaches against Streptococcus agalactiae (serotypes Ib and III) and Francisella orientalis. The minimum inhibitory concentration of florfenicol was 4, 5, and 128 μg/mL for the different pathogens. Fish mortality was lower in the prophylactic treatment compared to the metaphylactic and therapeutic treatments for S. agalactiae. No difference in mortality was observed for F. orientalis across treatments. Mild to moderate lesions suggestive of intoxication were observed, mainly in the liver of fish treated with overdoses or exposed to low temperatures. Florfenicol reduced mortality rates, especially with early treatment (metaphylactic), in fish experimentally challenged with the pathogens. Moreover, prophylactic antimicrobial use is not recommended, as it promotes the selection of multidrug-resistant bacterial strains. Additionally, the residual concentration of the drug in muscle tissue lasted for a shorter period than that recommended by the manufacturer, and at lower concentrations than required by national and international legislation.

Fish production faces various challenges throughout its cycle, from rearing to consumption. Organic acids have emerged as an effective fish feed and meat treatment solution. They promote health and well-being, control pathogens, improve digestion, and contribute to food preservation. This study was therefore carried out to evaluate the evolution of publications on the use of organic acids in aquaculture over time, identifying the leading journals, authors, countries, and relevant organizations associated with the publications and determining the keywords most used in publications and research trends on this type of accommodation using bibliometric analysis. For this analysis, the Web of Science (WoS) and Scopus databases were used, with the keywords and Boolean operators “organic acid*” AND (“pathogens” OR “microorganism*” OR “bacteria” OR “fungi”) AND (“fish” OR “fry” OR “pisciculture”). Ninety-six articles were found in 44 journals, with the participation of 426 authors and 188 institutions, from 1995 to 2024. The most crucial publication source with the highest impact factor was the journal Aquaculture, with 14 articles, 2 of which were written by the most relevant author, Koh C., who received the highest number of citations and had the highest impact factor among the 426 authors. China had the most scientific production, with 26 publications on organic acids in aquaculture. However, Malaysia was the country that published the most cited documents, a total of 386. The most relevant affiliation was the University of Sains Malaysia, which participated in the publication of eight articles. The 10 most frequent keywords were fish, organic acids, citric acid, article, bacteria, growth, microorganisms, Oncorhynchus mykiss, animals, and digestibility. The results indicate increased publications on the benefits of using organic acids in aquaculture, highlighting their effectiveness as antibacterial agents and promoters of zootechnical development. However, gaps still require more in-depth research into the ideal dosages, mechanisms of action, and long-term impacts of these compounds.

Identifying and counting fish are crucial for managing stocking, harvesting, and marketing of farmed fish. Researchers have used convolutional networks for these tasks and explored various approaches to enhance network learning. Batch normalization is one technique that improves network stability and accuracy. This study aimed to evaluate machine learning for identifying and counting pirapitinga Piaractus brachypomus fry with different batch sizes. The researchers used one thousand photographic images of Pirapitinga fingerlings, labeled with bounding boxes. They trained the adapted convolutional network model with batch normalization layers added at the end of each convolution block. They set the training to one hundred and fifty epochs and tested batch sizes of 5, 10, and 20. Furthermore, they measured network performance using precision, recall, and mAP@0.5. Models with smaller batch sizes performed less effectively. The training with a batch size of 20 achieved the best performance, with a precision of 96.74%, recall of 95.48%, mAP@0.5 of 97.08%, and accuracy of 98%. This indicates that larger batch sizes improve accuracy in detecting and counting pirapitinga fry across different fish densities.

The aim of this study was to develop a mathematical model to predict the body weight of tilapia fingerlings using variables obtained through computer vision. A total of 2092 tilapia fingerlings and juveniles, weighing between 10 and 100 g, were fasted for 12 h, anesthetized, weighed, and photographed using an iPhone 12 Pro Max at 33 cm height in a closed container with different bottom colors. Images were segmented using Roboflow’s instance segmentation model, achieving 99.5% mean average precision, 99.9% precision, and 100% recall. From the segmented images, area, perimeter, major axis (MA), minor axis (SA), X and Y centroids, compactness, eccentricity, and the MA/SA ratio were extracted. Seventy percent of the data was used to build the model, and 30% for validation. Stepwise multiple regression (backward selection) was performed, using body weight as the dependent variable. The prediction model was: −17.7677 + 0.0007539(area) – 0.0848303 (MA) – 0.108338(SA) + 0.0034496(CX). The validation model showed similar coefficients and R² = 0.99. The second validation, using observed versus predicted values, also yielded an R² of 0.99 and a mean absolute error of 1.57 g. Correlation and principal component analyses revealed strong positive associations among body weight, area, axes, and predicted values. Computer vision proved effective for predicting tilapia fingerlings’ weight.

Antimicrobial resistance in bacteria associated with aquaculture, such as Edwardsiella spp., represents an emerging challenge because of their relevance to fish health and their potential impact on animal, environmental, and human health. In this study, we primarily investigated the antimicrobial susceptibility profiles of Edwardsiella anguillarum isolated from farmed Nile tilapia (Oreochromis niloticus) in Brazil. Based on our findings, herein, we propose provisional local epidemiological cut-off values (pECVs) using the normalized resistance interpretation method, with data for Edwardsiella tarda included as an exploratory context. Fifty isolates (31 E. anguillarum and 19 E. tarda) collected between 2017 and 2025 were tested against 28 antibacterial agents using the disk diffusion method. Based on the pECVs, isolates were classified as wild type (WT) or non-WT (NWT), and the multiple antibiotic resistance (MAR) index was calculated. Most E. anguillarum isolates remained susceptible to several classes, although NWT and multidrug-resistant profiles were detected with a MAR index of 0.68, suggesting selective pressure in intensive tilapia farming systems. These findings support the use of local, species-specific pECVs for resistance surveillance in aquaculture, highlighting the importance of continuous antimicrobial resistance monitoring in aquaculture from a One Health perspective.