2026-10-11T13:12:32Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34017008 2026-09-28T17:39:20Z category_146 category_7 category_12 category_21 category_272 category_734 category_106 portal_5 item_type_3 month_year_09_2026

<p>Ablation experiment result.</p> LeTian Wu (25132754) KeKe Liao (25132757) BingWei Song (25132760) ShenBo Guo (25132763) XingDong Gao (25132766) HuiFeng Shi (25132769) Space Science Medicine Cell Biology Biotechnology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Science Policy scale feature extraction present experimental setting manual visual assessment free attention module estimating peel thickness diverse sample populations controlled imaging conditions 093 original images standardized grading method study proposes fanet fructus aurantii identification fanet achieved 96 fa quality grading fructus aurantii quality grade preliminary grading xlink "> still required simple parameter simam ), results indicate physical dimensions outer diameter msdfm ), medication safety maps segmentation lightweight end enhances spatial end framework derived areas combines starnet closely related clinical efficacy adapted components 9 gflops <div><p>The quality grade of Fructus Aurantii(FA) is closely related to its clinical efficacy and medication safety; therefore, a standardized grading method is needed. However, FA samples show considerable morphological variation, and conventional grading depends largely on manual visual assessment, which is subjective and inefficient. This study proposes FAnet, a lightweight instance segmentation framework based on YOLOv8n-seg, for estimating peel thickness and outer diameter during FA quality grading. FAnet integrates three task-adapted components: C2Star, which combines StarNet and C2f to improve multi-scale feature extraction; the Simple Parameter-Free Attention Module (SimAM), which enhances spatial-channel feature weighting without introducing additional trainable parameters; and a multi-scale dynamic fitting module (MSDFM), which maps segmentation-derived areas to physical dimensions for grading. Using a self-built dataset containing 1,093 original images and 5,035 augmented training images, FAnet achieved 96.12% precision, 98.77% recall, 98.60% mAP@50, and 77.08% mAP@95, with 2.97 M parameters and 7.9 GFLOPs under the present experimental setting. The results indicate that FAnet can support automated FA segmentation and preliminary grading under controlled imaging conditions. Broader validation across larger and more diverse sample populations is still required before deployment-oriented application.</p></div> 2026-09-28T17:38:59Z Dataset Dataset 10.1371/journal.pone.0357781.t004 https://figshare.com/articles/dataset/_p_Ablation_experiment_result_p_/34017008 CC BY 4.0