Micropterus salmoides is prone to bacterial and viral infections under recirculating aquaculture systems （RAS）. Characteristics of abnormal body surface in M. salmoides including redness and white spots may appear at the early stages of its illness. A YOLOv8-BCS model for detecting the characteristics of abnormal body surface in M. salmoides based on YOLOv8 was proposed to prevent large-scale mortality in aquaculture. A dynamic depthwise convolution（DIConv） feature extraction network， DIStarNet， was proposed based on the StarNet network. DIConv adaptively adjusted the convolution operation by designing a dynamic convolution kernel weight mechanism， thereby effectively capturing multi-scale feature information. A weighted bidirectional feature pyramid network（bi-directional feature pyramid network，BiFPN） was introduced into the neck network to enhance the feature fusion capability of multi-scale information from the backbone network. A convolutional block attention module （CBAM） attention mechanism was added before detection to improve the learning and extracting images of the characteristics of abnormal body surface in fish. The target recognition loss function was replaced with SCYLLA-intersection over union （SIoU） to improve the overlap between the model's predicted bounding boxes and the ground truth bounding boxes， thereby further enhancing the accuracy of recognizing the characteristics of abnormal body surface in fish. The results showed that YOLOv8 DBCS exhibited excellent performance of detection， with evaluation metrics including Precision， Recall， mAP₅₀， and mAP_50-95 being 95.8%， 92.4%， 97.5%， and 66.2%， respectively. Compared with that of the baseline model， these metrics increased by 3.6， 4.9， 7.0， and 3.4 percentage point， respectively. The model size of YOLOv8-DBCS was 1.85 million parameters， with a reduction of 38.5% compared with that of the baseline model. It will provide valuable reference for detecting the characteristics of abnormal body surface and early warning of diseases under recirculating aquaculture systems for M. salmoides.