Design of a mice head position and posture monitoring system based on the YOLO v5 algorithm
WANG Kui1,2, ZHOU Xiangbao1,2, ZHOU Tianhao1,2, LI Huajun1,2, QIU Yuhang1,2, WEI Qingyang1,2
1. School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China; 2. Beijing Engineering Research Center of Industrial Spectrum Imaging, University of Science and Technology Beijing, Beijing 100083, China
Abstract：[Objective] Nuclear medicine imaging is a dynamic imaging technique that enables researchers to analyze the physiological and pathological processes, especially in the brain. When imaging awake and unconstrained mice, the free movement of their heads can cause motion artifacts in the nuclear medicine images. These artifacts reduce image resolution, decrease the concentration of the tracer in the region of interest, and affect the quantification of the standard uptake value and the estimation of tracer kinetic model parameters. Therefore, the elimination of head motion artifacts is crucial for improving the quality of brain positron emission tomography (PET) images. In recent years, some researchers have been using markers attached to the mice's heads to track their movement. However, attaching markers to the mice's heads may cause discomfort and anxiety. In addition, the freedom of movement of the head during imaging can lead to relative sliding or detachment of the markers, resulting in incorrect motion estimation. [Methods] In this study, we design a mouse head motion tracking system based on the you only live once (YOLO) v5 algorithm. This system can accurately monitor the position and posture of the mice's heads in real time, providing precise motion information for motion correction in nuclear medicine images. In contrast to traditional motion tracking systems, this system does not require markers attached to the mice's heads, effectively addressing the limitations of previous tracking methods. The proposed motion tracking system consists of three main stages, namely feature point recognition and positioning, three-dimensional reconstruction of feature points, and calculation of the rotation and translation parameters. First, the YOLO v5 algorithm automatically identifies and locates existing feature points on the mice's heads to obtain the pixel coordinates of each feature point. Then, using the parallax effect and triangulation principles, we reconstruct the three-dimensional coordinates of the feature points in the world coordinate system. Finally, we calculate the Euler angles of the mice's heads using the symmetry of the feature points and utilize inter-frame pose differential methods to compute the translation and rotation parameters of the head pose change between adjacent frames. [Results] To verify the performance of the designed motion tracking system, we place a mouse phantom in a stationary position and measure the changes in its head position and posture angles using the designed system. The experimental results show that for the X, Y, and Z axes, the root-mean-square errors of the translational degrees of freedom are 0.04, 0.19, and 0.03 mm, whereas the root-mean-square errors of the rotational degrees of freedom are 0.58°, 0.34°, and 2.03°. We use the MATLAB function to obtain the histogram statistics of the detected translation and rotation parameters, all of which conform to a normal distribution. [Conclusions] The results indicate that the designed motion tracking system can accurately monitor the movement of the mice's heads during nuclear medicine imaging. The detected parameters of six degrees of freedom conform to a normal distribution, further confirming the reliability of the system. Moreover, this system does not rely on markers, effectively avoiding the risk of marker detachment. The motion data obtained through this system can be used to compensate for and correct motion artifacts of the mice's heads in nuclear medicine imaging, thereby enhancing the quality of nuclear medicine images.
王魁, 周湘堡, 周天浩, 李华君, 邱宇航, 魏清阳. 基于YOLO v5算法的小鼠头部位置和姿态监测系统设计[J]. 清华大学学报（自然科学版）, 2025, 65(5): 1000-1008.
WANG Kui, ZHOU Xiangbao, ZHOU Tianhao, LI Huajun, QIU Yuhang, WEI Qingyang. Design of a mice head position and posture monitoring system based on the YOLO v5 algorithm. Journal of Tsinghua University(Science and Technology), 2025, 65(5): 1000-1008.
[1] 马天予,张德斌,王瑞,等.心肌血流灌注SPECT新技术进展及其临床价值[J].协和医学杂志, 2023, 14(4):691-697. MA T Y, ZHANG D B, WANG R, et al. Recent advances in SPECT myocardial perfusion imaging and their clinical application values[J]. Medical Journal of Peking Union Medical College Hospital, 2023, 14(4):691-697.(in Chinese) [2] IKING J, STANISZEWSKA M, KESSLER L, et al. Imaging inflammation with positron emission tomography[J]. Biomedicines, 2021, 9(2):212-236. [3] 江年铭,刘帆,程李,等.国产SPECT/CT系统的定量性能研究[J].清华大学学报(自然科学版), 2024, 64(8):1509-1515. JIANG N M, LIU F, CHENG L, et al. Study on quantification performance evaluation of a domestic SPECT/CT system[J]. Journal of Tsinghua University (Science&Technology), 2024, 64(8):1509-1515.(in Chinese) [4] 戴甜甜,刘亚强,马天予,等.高分辨率小动物SPECT成像系统的设计与性能评估[J].原子能科学技术, 2011, 45(3):369-373. DAI T T, LIU Y Q, MA T Y, et al. Design and performance evaluation of high-resolution small animal SPECT system[J]. Atomic Energy Science and Technology, 2011, 45(3):369-373.(in Chinese) [5] ZHANG Y R, WEN X J, WANG Y J, et al. Longitudinal MicroSPECT imaging of systemic sclerosis model mice with[99mTc]Tc-HYNFA via folate receptor targeting[J]. Molecular Pharmaceutics, 2023, 20(1):473-480. [6] 魏清阳,周荣,吴朝霞,等.基于GATE程序的MicroPET系统设计Monte Carlo模拟验证[J].清华大学学报(自然科学版), 2010, 50(12):1934-1938. WEI Q Y, ZHOU R, WU Z X, et al. Monte Carlo simulation using GATE to verify the MicroPET system design[J]. Journal of Tsinghua University (Science&Technology), 2010, 50(12):1934-1938.(in Chinese) [7] MIAO Y, ZHANG L F, ZHANG M, et al. Therapeutic delivery of miR-143 targeting tumor metabolism in poorly differentiated thyroid cancer xenografts and efficacy evaluation using 18F-FDG MicroPET-CT[J]. Human Gene Therapy, 2019, 30(7):882-892. [8] WEI Q Y, WANG S, MA T Y, et al. Performance evaluation of a compact PET/SPECT/CT tri-modality system for small animal imaging applications[J]. Nuclear Instruments and Methods in Physics Research Section A:Accelerators, Spectrometers, Detectors and Associated Equipment, 2015, 786:147-154. [9] 周坤,孟祥溪,谢肇恒,等.一种新型的小动物四模态分子医学影像系统[J].中国医疗设备, 2015, 30(2):7-10. ZHOU K, MENG X X, XIE Z H, et al. A new quad-modality integrated molecular imaging system for small animals[J]. China Medical Devices, 2015, 30(2):7-10.(in Chinese) [10] ROE A W. Long-term optical imaging of intrinsic signals in anesthetized and awake monkeys[J]. Applied Optics, 2007, 46(10):1872-1880. [11] MARTIN C, MARTINDALE J, BERWICK J, et al. Investigating neural-hemodynamic coupling and the hemodynamic response function in the awake rat[J]. Neuroimage, 2006, 32(1):33-48. [12] BABA J S, ENDRES C J, FOSS C A, et al. Molecular imaging of conscious, unrestrained mice with awakeSPECT[J]. Journal of Nuclear Medicine, 2013, 54(6):969-976. [13] FUEGER B J, CZERNIN J, HILDEBRANDT I, et al. Impact of animal handling on the results of 18F-FDG PET studies in mice[J]. Journal of Nuclear Medicine, 2006, 47(6):999-1006. [14] 向晓辉,文小青,夏时海.一种无伪影小动物头部成像固定装置的设计[J].中国医学装备, 2015, 12(10):1-4. XIANG X H, WEN X Q, XIA S H. Design of artifact-free head holder for small animal imaging[J]. China Medical Equipment, 2015, 12(10):1-4.(in Chinese) [15] MIZUMA H, SHUKURI M, HAYASHI T, et al. Establishment of in vivo brain imaging method in conscious mice[J]. Journal of Nuclear Medicine, 2010, 51(7):1068-1075. [16] HILDEBRANDT I J, SU H, WEBER W A. Anesthesia and other considerations for in vivo imaging of small animals[J]. ILAR Journal, 2008, 49(1):17-26. [17] WANG J J, RAO H Y, WETMORE G S, et al. Perfusion functional MRI reveals cerebral blood flow pattern under psychological stress[J]. Proceedings of the National Academy of Sciences of the United States of America, 2005, 102(49):17804-17809. [18] VASKA P, WOODY C L, SCHLYER D J, et al. RatCAP:Miniaturized head-mounted PET for conscious rodent brain imaging[J]. IEEE Transactions on Nuclear Science, 2004, 51(5):1780-1784. [19] KYME A, SE S, MEIKLE S, et al. Markerless motion tracking of awake animals in positron emission tomography[J]. IEEE Transactions on Medical Imaging, 2014, 33(11):2180-2190. [20] WEISENBERGER A G, GLEASON S S, GODDARD J, et al. A restraint-free small animal SPECT imaging system with motion tracking[J]. IEEE Transactions on Nuclear Science, 2005, 52(3):638-644. [21] SUN X R, WU H N, YU G, et al. Research on the automatic detection of ship targets based on an improved YOLO v5 algorithm and model optimization[J]. Mathematics, 2024, 12(11):1714. [22] 李校林,王复港,张鹏飞,等.基于多尺度特征提取的YOLOv5s算法优化[J].计算机工程与科学, 2023, 45(6):1054-1062. LI X L, WANG F G, ZHANG P F, et al. YOLOv5s algorithm optimization based on multi-scale feature extraction[J]. Computer Engineering&Science, 2023, 45(6):1054-1062.(in Chinese) [23] WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet:A new backbone that can enhance learning capability of CNN[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle, USA:IEEE, 2020:390-391. [24] 周彦,孟江南,吴佳,等.改进YOLOv5s的钢板表面缺陷检测算法[J].激光与光电子学进展, 2023, 60(4):0415009. ZHOU Y, MENG J N, WU J, et al. Steel-plate surface-defect detection algorithm based on improved YOLOv5s[J]. Laser&Optoelectronics Progress, 2023, 60(4):0415009.(in Chinese) [25] 韩俊杰,骆开庆,邱健,等.基于双目相机的眼动仪头部姿态估计方法[J].激光与光电子学进展, 2021, 58(14):1410022. HAN J J, LUO K Q, QIU J, et al. Head pose estimation method of eye tracker based on binocular camera[J]. Laser&Optoelectronics Progress, 2021, 58(14):1410022.(in Chinese) [26] 何林杰.基于双目视觉的工业机器人目标识别与定位技术研究[D].成都:电子科技大学, 2022. HE L J. Research on target recognition and localization technology of industrial robot based on binocular vision[D]. Chengdu:University of Electronic Science and Technology of China, 2022.(in Chinese) [27] 储昭碧,李子朋,高金辉.一种基于双目相机与单点激光测距仪的标定方法[J].仪器仪表学报, 2023, 44(5):232-239.CHU Z B, LI Z P, GAO J H. Calibration method based on binocular camera and single point laser rangefinder[J]. Chinese Journal of Scientific Instrument, 2023, 44(5):232-239.(in Chinese) [28] 吴林慧.基于双目立体视觉的三维重建研究[D].武汉:武汉工程大学, 2022. WU L H. Research on 3D reconstruction based on binocular stereo vision[D]. Wuhan:Wuhan Institute of Technology, 2022.(in Chinese)
2025, Vol. 65 
