AI 中文总结
该研究构建了含1655帧的大鼠辐射热成像数据集，配解剖分割掩码与温度矩阵，用U-Net实现0.895±0.006的分割精度，为热语义分割等提供基准。
AI 中文摘要
红外热成像是一种非接触、无需约束的表面温度记录方法，是实验室动物应激与药理学研究中体温调节反应的重要指标。然而，这类图像的分析目前受限于解剖区域的手动勾勒，至今尚无公开数据集提供大鼠的辐射热帧与像素级身体部位标签的配对数据。我们构建了一个包含25只实验室大鼠的1655帧经质量控制的辐射热帧数据集，每帧均配有四类密集解剖分割掩码（背景、头部、躯体、尾部）及原始480×640（行×列）的摄氏度温度矩阵，确保每个标签直接对应其所描述的物理温度而非颜色映射渲染。这些帧来自两个药理学队列，其中干预措施以相反方向改变体温调节：乙醇诱导外周血管舒张，氯胺酮影响中枢体温调节，提供了广泛且生理多样的表面温度范围。数据集汇总后，各类别的物理单位温度遵循头部>躯体>尾部的排序。为证明该数据支持直接从辐射通道进行像素级分割，我们提出了一个探索性U-Net分割流程，其受试者级交叉验证平均交并比达0.895±0.006。该数据集为热语义分割及下游生理、应激表型分析提供了可复用的基准。
英文摘要
Infrared thermography provides a contact-free, restraint-free method to record surface temperatures. It serves as a valuable marker for thermoregulatory responses in laboratory animal stress and pharmacology research. However, the analysis of these images is currently bottlenecked by the manual delineation of anatomical regions. To date, no public dataset has provided paired radiometric thermal frames of rats with pixel-level body-part labels. We present a dataset of 1,655 quality-controlled radiometric thermal frames from 25 laboratory rats. Each frame is paired with a dense four-class anatomical segmentation mask (background, head, body, and tail) and the raw $480 \times 640$ temperature matrix (rows $\times$ columns) in degrees Celsius. This ensures every label is registered directly to the physical temperature it describes rather than a color-mapped rendering. The frames originate from two pharmacological cohorts where interventions alter thermoregulation in opposite directions: ethanol, which induces peripheral vasodilation, and ketamine, which affects central thermoregulation. This provides a wide and physiologically diverse range of surface temperature regimes. Aggregated across the dataset, the per-class temperatures follow a head~$>$~body~$>$~tail ordering in physical units. To demonstrate that the data support pixel-level segmentation directly from the radiometric channel, we present an exploratory U-Net segmentation pipeline that attains a subject-level cross-validated mean intersection-over-union of $0.895 \pm 0.006$. The dataset provides a reuse-ready benchmark for thermal semantic segmentation and for downstream physiological and stress-phenotyping analyses.
