Advanced Techniques for the Intelligent Diagnosis of Fish Diseases: A Review

Unlocking the Biological Enigma: Influence of Host Length and Infection Site on Parasite Abundance in Ompok bimaculatus

PURPOSE

The influence of two key factors, host length and infection site, on the host-parasite interaction in Ompok bimaculatus (Butter catfish) from Mukutmanipur Dam Lake, were investigated.

METHODS

Present study involved 192 specimens of Ompok bimaculatus with varying body lengths, subjected to diverse statistical analyses. One-way analysis of variance (ANOVA) was performed for the parasite numbers for three groups (cestode, nematode and trematode). Subsequently, we conducted one-way permutational multivariate analysis of variance (PERMANOVA) followed by pairwise test to assess parasite numbers across three body sites (intestine, mesentery, and bodycavity), employing the Bray-Curtis index. Additionally, Principal Coordinate Analysis (PCoA) for the same dataset was performed using the same index. Linear regression analysis was performed for the fish length-cestode number, fish length-nematode number, fish length-trematode number and fish length-total parasite number.

RESULTS

One-way ANOVA revealed no significant differences in parasite numbers among the three endo-helminth groups (cestode, nematode, and trematode). The results of PERMANOVA revealed significant differences in parasite numbers across the three body sites of the host fishes (groups) (F = 9.41, p = 0.0001). Pairwise tests further demonstrated significant differences between the intestine-mesentery, intestine-body-cavity, and mesentery-body-cavity. Additionally, Principal Coordinate Analysis (PCoA) unveiled a significant relationship between infection site and parasite number. However, linear regression analysis examining the relationship between fish length and parasite abundance indicated no significant associations.

CONCLUSIONS

Through a detailed exploration of the statistical analyses, we provide insights into the host-parasite interaction, elucidating both established knowledge and novel findings in fish parasitology.

A Scoping Review on GIS Technologies Applied to Farmed Fish Health Management

Finfish aquaculture, one of the fastest growing intensive sectors worldwide, is threatened by numerous transmissible diseases that may have devastating impacts on its economic sustainability. This review (2010-2022) used a PRISMA extension for scoping reviews and a text mining approach to explore the extent to which geographical information systems (GIS) are used in farmed fish health management and to unveil the main GIS technologies, databases, and functions used to update the spatiotemporal data underpinning risk and predictive models in aquatic surveillance programmes. After filtering for eligibility criteria, the literature search provided 54 records, highlighting the limited use of GIS technologies for disease prevention and control, as well as the prevalence of GIS application in marine salmonid farming, especially for viruses and parasitic diseases typically associated with these species. The text mining generated five main research areas, underlining a limited range of investigated species, rearing environments, and diseases, as well as highlighting the lack of GIS-based methodologies at the core of such publications. This scoping review provides a source of information for future more detailed literature analyses and outcomes to support the development of geospatial disease spread models and expand in-field GIS technologies for the prevention and mitigation of fish disease epidemics.

Wearable Bioimpedance-Based Deep Learning Techniques for Live Fish Health Assessment under Waterless and Low-Temperature Conditions

(1) Background: At present, physiological stress detection technology is a critical means for precisely evaluating the comprehensive health status of live fish. However, the commonly used biochemical tests are invasive and time-consuming and cannot simultaneously monitor and dynamically evaluate multiple stress levels in fish and accurately classify their health levels. The purpose of this study is to deploy wearable bioelectrical impedance analysis (WBIA) sensors on fish skin to construct a deep learning-based stress dynamic evaluation model for precisely estimating their accurate health status. (2) Methods: The correlation of fish (turbot) muscle nutrients and their stress indicators are calculated using grey relation analysis (GRA) for allocating the weight of the stress factors. Next, WBIA features are sieved using the maximum information coefficient (MIC) in stress trend evaluation modeling, which is closely related to the key stress factors. Afterward, a convolutional neural network (CNN) is utilized to obtain the features of the WBIA signals. Then, the long short-term memory (LSTM) method learns the stress trends with residual rectification using bidirectional gated recurrent units (BiGRUs). Furthermore, the Z-shaped fuzzy function can accurately classify the fish health status by the total evaluated stress values. (3) Results: The proposed CNN-LSTM-BiGRU-based stress evaluation model shows superior accuracy compared to the other machine learning models (CNN-LSTM, CNN-GRU, LSTM, GRU, SVR, and BP) based on the MAPE, MAE, and RMSE. Moreover, the fish health classification under waterless and low-temperature conditions is thoroughly verified. High accuracy is proven by the classification validation criterion (accuracy, F1 score, precision, and recall). (4) Conclusions: the proposed health evaluation technology can precisely monitor and track the health status of live fish and provides an effective technical reference for the field of live fish vital sign detection.