The accumulation of excess fat in fish might impair the health of fish in aquaculture. This paper introduces an online sequential extreme learning machine (OS‐ELM) into region‐of‐interest (ROI) detection of adipose tissues in fish digitalized by means of magnetic resonance imaging (MRI). Three typical economic fish species, turbot (Scophthalmus maximus L.), large yellow croaker (Pseudosciaena crocea R.) and Japanese seabass (Lateolabrax japonicus), were selected to compose into digital physiological atlas. We manually labelled with ITK‐SNAP discriminating adipose tissue regions as standard references. Then, single‐hidden‐layer feedforward neural networks (SLFNs) were established to deduce the potential mathematical criterion for fat detection via OS‐ELM for each fish species. We further carried out classical adaptive segmentation to extract details in fat location and distribution of adipose tissues. The quantitative correspondence regarding adipose tissues regions, between 3D voxel representation in MRI and chemical measurement in real fish, have been statistically investigated across each species. The experimental results showed that our online fat detection automatically through MRI is consistent with the standard references, and the recognition rate for three fish species could be up to 89.13% ± 5.32%, 91.43% ± 6.68% and 93.08% ± 6.57% on average, with FAR rate 5.35%, 4.05%, 3.39% and FRRs of 5.52%, 4.52% and 3.53% respectively. Those 3D volumes involved in fat region counting keep pace with the real weights of adipose tissues across species, which implies we might utilize 3D voxel counting to quantify fat accumulation in adipose tissues in a species‐dependent manner. The proposed mechanism brings comparative performances for fat detection and evaluation at a much faster speed, which could help high‐throughput insights into fat metabolism process in fish.

中文翻译：

---

在线脂肪检测和评估中的数字生理鱼建模

鱼中多余脂肪的积累可能会损害水产养殖中鱼的健康。本文将在线顺序极限学习机（OS-ELM）引入到通过磁共振成像（MRI）数字化的鱼类脂肪组织的感兴趣区域（ROI）检测中。三种典型的经济鱼类，比目鱼（Scophthalmus maximus L.），大黄鱼（Pseudosciaena crocea R.）和日本鲈鱼（Lateolabrax japonicus）），以组成数字生理图集。我们用ITK-SNAP手动标记区分脂肪组织区域作为标准参考。然后，建立了单层前馈神经网络（SLFN），以推导通过OS-ELM对每种鱼类进行脂肪检测的潜在数学标准。我们进一步进行了经典的自适应分割，以提取脂肪位置和脂肪组织分布的细节。关于脂肪组织区域的定量对应关系，在MRI中的3D体素表示与真实鱼类的化学测量之间，已经在每个物种中进行了统计研究。实验结果表明，通过MRI自动进行的在线脂肪检测与标准参考文献相符，三种鱼类的识别率平均分别可达89.13％±5.32％，91.43％±6.68％和93.08％±6.57％，FAR率分别为5.35％，4.05％，3.39％和FRR分别为5.52％，4.52 ％和3.53％。那些涉及脂肪区域计数的3D体积与整个物种中脂肪组织的实际重量保持一致，这意味着我们可以利用3D体素计数以一种依赖于物种的方式量化脂肪在脂肪组织中的积累。所提出的机制以更快的速度带来了用于脂肪检测和评估的比较性能，这可以帮助高通量洞察鱼类的脂肪代谢过程。那些涉及脂肪区域计数的3D体积与物种中脂肪组织的实际重量保持一致，这意味着我们可以利用3D体素计数以一种依赖于物种的方式量化脂肪在脂肪组织中的积累。拟议的机制以更快的速度为脂肪检测和评估提供了比较性能，这可能有助于高通量洞察鱼类脂肪代谢过程。那些涉及脂肪区域计数的3D体积与整个物种中脂肪组织的实际重量保持一致，这意味着我们可以利用3D体素计数以一种依赖于物种的方式量化脂肪在脂肪组织中的积累。拟议的机制以更快的速度带来了用于脂肪检测和评估的比较性能，这可以帮助高通量洞察鱼类的脂肪代谢过程。