Phenotyping technologies are essential for modern aquaculture, particularly for precise analysis of individual morphological traits. This study focuses on critical phenotype segmentation tasks for fish carcass and fins, which have significant applications in phenotypic assessment and breeding. In high-density underwater environments, fish frequently exhibit structural overlap and indistinct boundaries, making it difficult for conventional segmentation methods to obtain complete and accurate phenotypic regions. To address these challenges, a double-branch segmentation network is proposed for fish phenotype segmentation in high-density underwater scenes. An auxiliary saliency object detection (SOD) branch is introduced alongside the primary segmentation branch to localize structurally complete targets and suppress interference from overlapping or incomplete fish while inter-branch skip connections further enhance the model’s focus on salient targets and their boundaries. The network is trained under a multi-task learning framework, allowing the branches to specialize in edge detection and accurate region segmentation. Experiments on large yellow croaker (Larimichthys crocea) images collected under real farming conditions show that the proposed method achieves Dice scores of 97.58% for carcass segmentation and 88.88% for fin segmentation. The corresponding ASD values are 0.590 and 0.364 pixels, and the HD95 values are 3.521 and 1.222 pixels. The method outperforms nine existing algorithms across key metrics, confirming its effectiveness and reliability for practical aquaculture phenotyping.

The transforming growth factor β (TGFβ) signaling axis plays a pivotal role in orchestrating a wide array of biological functions, encompassing cellular growth, proliferation, and differentiation. The aim of the present study was to identify the members of TGFβ signaling pathway and their expression patterns in large yellow croaker (Larimichthys crocea) under different culture modes. TGFβ signaling pathway and their expression patterns in fish reared under two different culture modes: Group N (2400 fish in a 120 m³ cage) and Group V (168,000 fish in a 5600 m³ aquaculture vessel). After 120 days, we analyzed 15 fish from each group and found that Group V exhibited faster growth and a slender body shape compared to Group N. Bioinformatics analysis identified 48 TGFβ superfamily members in L. crocea, including 21 ligands, 10 receptors, and 3 Smads. mRNA expression levels indicated that these signaling molecules influence growth rate and body shape through five distinct ligand–receptor–R-Smad pathways, with the INHBB-, Nodal-, and GDF3-ACVR2A-ALK4-Smad2 axis playing a predominant role in regulating these traits.