Development of a deep learning-based system for automatic screening of turbot (scophthalmus maximus) chronic furunculosis

The sustained growth of the aquaculture industry brings signifi- cant challenges to which artificial intelligence is emerging as an answer. Indeed, improving the detection and management of anomalies and diseases in large fish populations is one of them. In this work, a deep learning-based model has...

Full description

Bibliographic Details
Authors: Moreno, Iván, Souto, Xoel, Rosa, Gonzalo, Cebrián, Pedro L., Bermudez, Roberto, Chavarrías, Miguel, Quiroga, María Isabel, Pescador, Fernando
Format: article
Publication Date:2025
Country:España
Institution:Universitat Politècnica de Catalunya (UPC)
Repository:UPCommons. Portal del coneixement obert de la UPC
Language:English
OAI Identifier:oai:upcommons.upc.edu:2117/449448
Online Access:https://hdl.handle.net/2117/449448
https://dx.doi.org/10.5821/iwp.2025.24.13990
Access Level:Open access
Keyword:Oceanography -- Research
Oceanography -- Equipment and supplies
Mariculture
Artificial intelligence
Turbot
Flatfish
Aeromonas salmonicida subsp.
Aquaculture
Deep learning
Image
Classification
Oceanografia -- Investigació
Oceanografia -- Aparells i instruments
Aqüicultura marina
Intel·ligència artificial
Àrees temàtiques de la UPC::Enginyeria civil::Geologia::Oceanografia
Àrees temàtiques de la UPC::Enginyeria electrònica::Instrumentació i mesura
Àrees temàtiques de la UPC::Enginyeria agroalimentària::Pesca::Aqüicultura
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
Description
Summary:The sustained growth of the aquaculture industry brings signifi- cant challenges to which artificial intelligence is emerging as an answer. Indeed, improving the detection and management of anomalies and diseases in large fish populations is one of them. In this work, a deep learning-based model has been validated for accurate screening of chronic furunculosis in turbot using a low- cost, scalable and transferable system. The results show a preci- sion of 82% and a processing time below 1s per fish.