Application of artificial intelligence in tongue diagnosis of traditional Chinese medicine:A review

Tongue diagnosis is an important process to non-invasively assess the condition of a patient’s internal organs in traditional Chinese medicine(TCM)and each part of the tongue is related to corresponding internal organs.Due to continuing computer technological advances,especially the artificial intelligence(AI)methods have achieved significant success in tackling tongue image acquisition,processing,and classification,novel AI methods are being introduced in traditional Chinese medicine tongue diagnosis medical practices.Traditional tongue diagnose depends on observations of tongue characteristics,such as color,shape,texture,moisture,etc.by traditional Chinese medicine physicians.The appearance of the tongue color,texture and coating reflects the improvement or deterioration of patient’s conditions.Moreover,AI can now distinguish patient’s condition through tongue images,texture or coating,which is all possible increasingly with help from traditional Chinese medicine physicians under the traditional Chinese medicine tongue theory.AI has enabled humans to do what was previously unimagined:traditional Chinese medicine tongue diagnosis with feeding a large amount of tongue image and tongue texture/coating data to train the AI modes.This review focuses on the research advances of AI in TCM tongue diagnosis thus far to identify the major scientific methods and prospects.In this article,we tried to review the AI application in resolving the tongue diagnosis of traditional Chinese medicine on color correction,tongue image extraction,tongue texture/coating segmentation.

Application of Multiple Sensor Data Fusion for the Analysis of Human Dynamic Behavior in Space: Assessment and Evaluation of Mobility-Related Functional Impairments

The authors have applied a systems analysis approach to describe the musculoskeletal system as consisting of a stack of superimposed kinematic hier-archical segments in which each lower segment tends to transfer its motion to the other superimposed segments. This segmental chain enables the derivation of both conscious perception and sensory control of action in space. This applied systems analysis approach involves the measurements of the complex motor behavior in order to elucidate the fusion of multiple sensor data for the reliable and efficient acquisition of the kinetic, kinematics and electromyographic data of the human spatial behavior. The acquired kinematic and related kinetic signals represent attributive features of the internal recon-struction of the physical links between the superimposed body segments. In-deed, this reconstruction of the physical links was established as a result of the fusion of the multiple sensor data. Furthermore, this acquired kinematics, kinetics and electromyographic data provided detailed means to record, annotate, process, transmit, and display pertinent information derived from the musculoskeletal system to quantify and differentiate between subjects with mobility-related disabilities and able-bodied subjects, and enabled an inference into the active neural processes underlying balance reactions. To gain insight into the basis for this long-term dependence, the authors have applied the fusion of multiple sensor data to investigate the effects of Cerebral Palsy, Multiple Sclerosis and Diabetic Neuropathy conditions, on biomechanical/neurophysiological changes that may alter the ability of the human loco-motor system to generate ambulation, balance and posture.

Foreign body granuloma in the tongue differentiated from tongue cancer:A case report

BACKGROUND Embedded foreign bodies in the tongue are rarely seen in clinical settings.An untreated foreign body can cause a granuloma which often presents as an enlarged tongue mass.However,if foreign body ingestion status is unknown,physical examination and magnetic resonance imaging(MRI)tend to lead to suspicion of tongue cancer,especially in older patients.Thus,differential diagnosis of an enlarged tongue mass is important,especially because it is closely related to the choice of treatment method.CASE SUMMARY A 61-year-old woman was admitted to the hospital with pain and noticeable swelling in the tongue that had persisted for over 1 mo.She had no previous medical history.MRI revealed abnormal signal intensities that were indicative of a neoplasm.Thus,the oral surgeon and radiologist arrived at a primary diagnosis of tongue cancer.The patient visited the Ear Nose and Throat Department for further consultation and underwent an ultrasound examination of the tongue.The ultrasonography was consistent with a linear hyperechoic foreign body which was indicative of an embedded foreign body(bone)in the tongue,even though the patient denied any history of foreign body ingestion.Complete surgical enucleation of the lesion was conducted.The mass which included a fish bone was completely removed.The post-operative pathological examination confirmed that the mass was a granuloma containing collagen fibers,macrophages and chronic inflammatory cells.The patient recovered without complications over a 2 mo follow-up period.CONCLUSION We report a rare case of foreign body granuloma in the tongue that was primarily diagnosed as tongue cancer.The MRI and ultrasound examinations revealed a piece of bone in the left lateral aspect of the tongue.The granuloma,which contained a fish bone,was completely removed via surgery and confirmed via biopsy.Differential diagnosis of the enlarged tongue mass was critical to the selection of treatment method.

Evaluation of the Changes in Anterior Segment Morphology with Ultrasound Biomicroscopy after Vitrectomy without Use of Tamponade in Pseudophakic Eyes

Aim: In this study we investigated the changes in anterior segment morphology in pseudophakia patients that underwent ultrasound biomicroscopy (UBM) after pars plana vitrectomy (PPV) operation without use of tamponade. Method: Pseudophakic patients who undergo PPV were enrolled in this prospective study between October 2012 and April 2015. Study included patients in whom intraocular tamponade was not used during PPV operation. UBM measurements were performed both before and 10 days after the operation. Anterior chamber depth (ACD) was measured using axial images of anterior segment. Trabecular meshwork-iris angle (TIA), ciliary body thickness (CBT), sclera thickness (ST), trabecular meshwork-ciliary process distance (T-CPD), iris-ciliary processes distance (I-CPD), and iris thickness (IT) were measured at temporal quadrant based on radial section images of the angle. Values measured before and after the operation were statistically compared with each other. Results: This study included 30 patients (18 females, 12 males) that underwent an operation ultrasound biomicroscopy (UBM) after pars plana vitrectomy (PPV) operation without use of tamponade. Mean age was 69.6 ± 9.1 (55 - 85) years. Eighteen operations occurred on the left eye whereas twelve operations occurred on the right eye. CBT1, CBT2, CBT Max, T-CPD, and I-CPD were significantly decreased after operation when compared with the values of baseline (before) (p = 0.018, p = 0.012, p = 0.001, p = 0.033, p = 0.015, respectively). Other evaluated parameters did not show statistically significant changes after the operation (p > 0.05). Discussion: PPV results in significant changes in ciliary body morphology together with changes in anterior segment parameters in pseudophakic cases.

A Novel Apprehension of the Primary Lung Meridian, Sinew Channel, Divergent Channel, Luo-Connecting Channel Acting as a Single Unit System to Serve Respiration Function Based on Modern Neurophysiology and Kinesiology

The TCM philosophy of a meridian and associated channels pertains to the specific function of one or more organs. We define the Lung Primary Meridian (LUM) together with the Lung Sinew (LUSC), Divergent (LUDC), Luo-connecting (LULCC) Channels as a system of routes plus some parts of the body (such as muscles) to fulfil respiration, as a main function under different situations. There is very limited information about the Lung associated channels in classical literature of TCM. With a clear focus on the function of respiration, we have carried out a detailed analysis of the biomedical consequence of stimulating the LUM, analysed the roles played by LUSC, LUDC, and LULCC. The updated LUM and LUDC include acupoints of other meridians, serving the same purpose of performing satisfactory respiration starting from checking the quality of the inflow through the nose. The LUSC includes the respiratory muscles (plus the associated connective tissues) extending to various parts of the body. The muscles of the limb (as part of the LUSC) embrace the nerves that provide routes for somatosensory reflexes and play the role of locomotion, providing voluntary respiration via the pectoralis muscles. The muscles of LUSC are bounded by stiff connective tissue layers, forming compartments, and are part of the pulley system for various body locomotions. Within a compartment, the interstitial fluid, blood, lymph flows must be potent to protect the associated nerves related to LUM;the healthy state of the LUSC also provides freedom of various types of locomotion. The LULCC exists because the vagus nerve has a part of it passing through the spinal cords all the way down to the sacrum domain, with exiting nerve innervating two-third of the large intestine. The crucial steps of our deductions are supported by experimental evidence based on modern neurophysiology and kinesiology. We discover that all the four channels stated above work as a unit system to allow respiration to be possible under various postures/conditions. The complexity of structures and processes is eased off by providing 29 figures and 13 tables for the relevant muscles and nerves. In addition to respiration, the Lung system in TCM context includes interaction of this system with the sweat gland and neuroendocrine system;such aspects will be left to another study.

Template Guided Live Wire and Its Application on Automatic Extraction of Tongue in Digital Image

In this paper, we propose a novel automatic object extraction algorithm, named the Template Guided Live Wire, based on the popularly used live-wire techniques. We discuss in details the novel method’s applications on tongue extraction in digital images. With the guides of a given template curve which approximates the tongue’s shape, our method can finish the extraction of tongue without any human intervention. In the paper, we also discussed in details how the template guides the live wire, and why our method functions more effectively than other boundary based segmentation methods especially the snake algorithm. Experimental results on some tongue images are as well provided to show our method’s better accuracy and robustness than the snake algorithm.

Deer Body Adaptive Threshold Segmentation Algorithm Based on Color Space

In large-scale deer farming image analysis,K-means or maximum between-class variance(Otsu)algorithms can be used to distinguish the deer from the background.However,in an actual breeding environment,the barbed wire or chain-link fencing has a certain isolating effect on the deer which greatly interferes with the identification of the individual deer.Also,when the target and background grey values are similar,the multiple background targets cannot be completely separated.To better identify the posture and behaviour of deer in a deer shed,we used digital image processing to separate the deer from the background.To address the problems mentioned above,this paper proposes an adaptive threshold segmentation algorithm based on color space.First,the original image is pre-processed and optimized.On this basis,the data are enhanced and contrasted.Next,color space is used to extract the several backgrounds through various color channels,then the adaptive space segmentation of the extracted part of the color space is performed.Based on the segmentation effect of the traditional Otsu algorithm,we designed a comparative experiment that divided the four postures of turning,getting up,lying,and standing,and successfully separated multiple target deer from the background.Experimental results show that compared with K-means,Otsu and hue saturation value(HSV)+K-means,this method is better in performance and accuracy for adaptive segmentation of deer in artificial breeding scenes and can be used to separate artificially cultivated deer from their backgrounds.Both the subjective and objective aspects achieved good segmentation results.This article lays a foundation for the effective identification of abnormal behaviour in sika deer.

Theoretical Analysis and Experimental Verification on Valve-less Piezoelectric Pump with Hemisphere-segment Bluff-body

Existing researches on no-moving part valves in valve-less piezoelectric pumps mainly concentrate on pipeline valves and chamber bottom valves, which leads to the complex structure and manufacturing process of pump channel and chamber bottom. Furthermore, position fixed valves with respect to the inlet and outlet also makes the adjustability and controllability of flow rate worse. In order to overcome these shortcomings, this paper puts forward a novel implantable structure of valve-less piezoelectric pump with hemisphere-segments in the pump chamber. Based on the theory of flow around bluff-body, the flow resistance on the spherical and round surface of hemisphere-segment is different when fluid flows through, and the macroscopic flow resistance differences thus formed are also different. A novel valve-less piezoelectric pump with hemisphere-segment bluff-body （HSBB） is presented and designed. HSBB is the no-moving part valve. By the method of volume and momentum comparison, the stress on the bluff-body in the pump chamber is analyzed. The essential reason of unidirectional fluid pumping is expounded, and the flow rate formula is obtained. To verify the theory, a prototype is produced. By using the prototype, experimental research on the relationship between flow rate, pressure difference, voltage, and frequency has been carried out, which proves the correctness of the above theory. This prototype has six hemisphere-segments in the chamber filled with water, and the effective diameter of the piezoelectric bimorph is 30mm. The experiment result shows that the flow rate can reach 0.50 mL/s at the frequency of 6 Hz and the voltage of 110 V. Besides, the pressure difference can reach 26.2 mm H20 at the frequency of 6 Hz and the voltage of 160 V. This research proposes a valve-less piezoelectric pump with hemisphere-segment bluff-body, and its validity and feasibility is verified through theoretical analysis and experiment.

Management and treatment of bizarre open globe trauma in three steps:a case report

This is a case presentation of a very bizarre open globe trauma with anterior segment foreign body-fishing hook stuck in the cornea and iris. Complications due to this kind of eye trauma might be very hazardous and with serious impact on visual function. We are representing our approach and experience of three step management of this kind of eye injury: first-extract the foreign body, close and reconstruct the eyeball, second-fight inflammation, and third-restore the visual function by cataract surgery.

A Tongue-images Segmentation Method Based on Local Restoration and Watershed Algorithm

Objective: To propose a method to segment tongue- images efficiently, and extract tongue- body accurately and quickly. Methods: Firstly, a kind of color- images' pre- processing technique was used to solve tongue- surface reflection problem. Neighbouring and similar region's information was used to restore the region with tongue- surface reflection problem by replacement. Secondly, the restored image was transformed into a gray one, and then processed by mathematical morphological operation- dilation to get a closed- loop edge. The third technique used was watershed algorithm, which is an usual tool in image segmentation. 'Watershed' function of matlab software was used to complete this algorithm. After that, region- combination technique was used. Through measuring neighbourship and similarity of regions, a non- objective and non- background region was merged into one of its neighbouring regions. This step was repeated until only two regions, objective and background regions, were left in the image. At last, corresponding to the merged image, tongue- body image was got from the original image. Results: 316 images were randomly taken from the image library for experiments, and 299 images were correctly segmented, so, the successful ratio is 94.62%. On the other hand, average time of running this method was about 50 s under whole sampling environment. Conclusion: The method presented in this paper can segment a tongue- body image from its original one effectively, and thus laying a good foundation for the following analysis work.

Occurrence of Fibonacci numbers in development and structure of animal forms: Phylogenetic observations and epigenetic significance

A survey of zoological literature affirmed the wide occurrence of Fibonacci numbers in the organization of acellular and prokaryotic life forms as well as in some eukaryotic protistans and in the embryonic development and adult forms of many living and fossil remains of metazoan animals. A detailed comparative analysis of the axial skeleton of a fossil fish and humans revealed a new rule of the “nested triad” of bones organized along the proximal to distal axis of limb appendages. This growth pattern and its ubiquity among living vertebrates appear to underlie a profound rule of pattern formation that is dictated in part by the genetics and epigenetic mechanisms of stem cell clonal development.

自走式马铃薯捡拾装袋机设计与试验

针对马铃薯分段收获中,人工捡拾劳动强度大、效率低、成本高的问题,设计了一种自走式马铃薯捡拾装袋机。该自走式马铃薯捡拾装袋机能一次性完成马铃薯捡拾、薯土分离、除秧和装袋的工作。阐述了自走式马铃薯捡拾装袋机整体结构,并对捡拾装置、升运链装置、三级输送链装置、分拣台以及卸料装置等关键部件进行详细设计;运用DEM-MBD耦合的方法对马铃薯在两级输送链交接处的运动过程及受力情况进行分析;运用Box-Behnken试验方法,以漏薯率和伤薯率为评价指标,以整机前进速度、捡拾装置输送链线速度、升运链线速度、三级输送链线速度为试验因素,对该机工作参数进行四因素三水平试验,使用Design-Expert软件建立二次多项式回归模型。对回归模型进行优化后,绘制响应面,并得出该机最优工作参数。田间试验表明:当前进速度为0.70 m/s、捡拾装置输送链线速度为1.10 m/s、升运链线速度为1.20 m/s、三级输送链线速度为1.30 m/s时,漏薯率为2.82%,伤薯率为3.61%,满足马铃薯捡拾收获作业要求。

基于四电极多频率扫描的生物阻抗法人体成分测试仪设计

生物阻抗包含丰富的人体病理和生理电信号,可以作为医务人员准确判断病人症状和治疗疾病的主要依据。基于此,提出一种基于Cole-Cole理论的人体多种参数测量系统。构建人体阻抗模型,通过碳纳米材料电极对人体阻抗进行采集分析,得到人体的各种成分参数。通过信号发生电路产生注入人体的低频信号,利用幅度检测电路检测流经人体电流产生的电压,采用分段检测法测得人体不同分段的阻抗信息;信号经放大电路输入RT1052微处理器,对数据和人体成分参数相关性进行分析,得到人体各种成分参数并显示测量结果。通过对系统进行测试分析,得出所设计系统能够准确地对人体蛋白质、脂肪等参数进行测量,误差范围可以控制在5%以内,具有很好的应用前景。

带辅助轮摆臂的履带式机器人越障能力分析

履带式移动机器人因具有良好的环境适应性被广泛应用于军事和安全领域。为了改善现有摆臂履带式机器人结构复杂、重量和体积较大等不足,进一步提高其越障能力,提出一种带辅助轮摆臂的履带式移动机器人,设计该机器人的几何模型,分析其越障机理,推导摆臂的正逆运动学方程,分别建立有/无滑移条件下机器人的运动学模型。采用柔性体有限段模型法建立履带的多体动力学仿真模型。通过履带滑转率、机器人主体质心高度,履带与地面接触力及摆轮受力的变化,综合分析该机器人越障时的动力性能。在越阶、爬坡和越沟壑不同工况下,提出的带辅助轮摆臂的履带式机器人表现出良好的越障性能。

宽体飞机地面主轮协同转弯控制律设计

主轮协同转弯技术能有效提高飞机的地面机动性,降低主起落架在转弯过程中受到的附加侧向扭矩,减小重载飞机地面转弯半径,但目前实现此技术的前主轮转角控制律设计方法尚不明确。提出以主起落架受力为约束条件,计算不同滑行速度下的前主轮转角关系,在全速度范围内进行分段选择并离散化,据此设计前主轮协同转弯控制律,以原理样机为对象进行仿真分析,验证了该控制律能有效降低两侧主起落架扭矩和的峰值。提出的设计方法对多轮系地面运载装备的复合转弯控制律设计具有一定的理论指导意义。

CBCT辅助定位取出舌根内鱼刺异物1例

在口腔颌面外科临床中,因“口腔异物”就诊的患者较多见。异物存留常见的部位为牙龈、舌体、口底及咽上部,但舌根内部异物较为罕见且可引起一系列并发症。本文报道舌根内鱼刺异物在锥束计算机断层扫描(cone-beam computed tomography,CBCT)辅助定位下手术取出病例1例。

基因体甲基化在舌粘膜癌变中的变化

目的了解舌粘膜癌变中基因体甲基化的差异表达基因。方法用浓度50 mg/L的4-硝基喹啉-1-氧化物(4NQO)诱导C57BL/6小鼠舌癌。基因芯片和甲基化DNA免疫沉淀测序(MeDIP-Seq)检测0周、12周、28周(代表正常、癌前、癌变)的舌粘膜的基因表达和基因组DNA甲基化。在人正常舌粘膜和癌前病变组织中用qRT-PCR和飞行质谱检测泛素羧基水解酶CYLD的mRNA表达和基因体甲基化。结果正常、癌前和舌癌3组间基因体MeDIP-score(mean±s)分别是(5.58±14.80)、(5.79±13.35)、(5.83±17.25),差异无统计学意义(H=100.75,P>0.05)。3组间145个差异表达基因伴基因体甲基化改变。CYLD在人癌前病变组织中表达降低伴有基因体甲基化降低(P<0.05)。结论舌粘膜癌变有多个基因体甲基化异常的差异表达基因,CYLD在人癌前病变中低表达可能与基因体甲基化有关。

基于YOLO v8n-seg-FCA-BiFPN的奶牛身体分割方法

奶牛身体部位的精准分割广泛应用于奶牛体况评分、姿态检测、行为分析及体尺测量等领域。受奶牛表面污渍和遮挡等因素的影响,现有奶牛部位精准分割方法实用性较差。本研究在YOLO v8n-seg模型的基础上,加入多尺度融合模块与双向跨尺度加权特征金字塔结构,提出了YOLO v8n-seg-FCA-BiFPN奶牛身体部位分割模型。其中,多尺度融合模块使模型更好地提取小目标几何特征信息,双向跨尺度加权特征金字塔结构实现了更高层次的特征融合。首先在奶牛运动通道处采集奶牛侧面图像作为数据集,为保证数据集质量,采用结构相似性算法剔除相似图像,共得到1 452幅图像。然后对目标奶牛的前肢、后肢、乳房、尾部、腹部、头部、颈部和躯干8个部位进行标注并输入模型训练。测试结果表明,模型精确率为96.6%,召回率为94.6%,平均精度均值为97.1%,参数量为3.3×10^(6),检测速度为6.2 f/s。各部位精确率在90.3%~98.2%之间,平均精度均值为96.3%。与原始YOLO v8n-seg相比,YOLO v8n-seg-FCA-BiFPN的精确率提高3.2个百分点,召回率提高2.6个百分点,平均精度均值提高3.1个百分点,改进后的模型在参数量基本保持不变的情况下具有更强的鲁棒性。遮挡情况下该模型检测结果表明,精确率为93.8%,召回率为91.67%,平均精度均值为93.15%。结果表明,YOLO v8n-seg-FCA-BiFPN网络可以准确、快速地实现奶牛身体部位精准分割。

基于双编码特征提取路径的舌体分割方法

针对舌图像舌体边缘分割模糊、小区域分割错误等问题,本研究设计了一种双编码特征提取路径的方法,以获取丰富的信息特征,辅助舌体精确分割。首先,设计双编码特征提取路径,其中,空间信息路径保留空间信息并生成高分辨率特征图,上下文信息路径提高网络提取多尺度特征能力;其次,采用一种特征融合模块,融合空间信息路径和上下文信息路径的输出特征;最后,采用轻量级解码器模块减少模型参数量,提高模型计算效率。结果显示,该方法精确率、召回率、F1分数和平均交并比(mean intersection over union,MIoU)分别达98.82%、98.53%、98.60%和97.67%,模型总参数量和每秒浮点运算次数(floating point operations per second,FLOPs)为7.54 M和67.09 G。结果表明,该方法可有效提高舌体的分割精度,显著改善舌体小区域分割错误和边缘模糊性,为中医舌象智能辅助分析提供必要支撑。

身材认知在服装分割设计中的感性工学应用

为探讨服装分割比例与颜色明度变化对身材认知的影响规律,结合感性工学的基本原理、方法与认知行为学的技术对消费者在服装设计中对于身材认知的感性评价进行量化分析,通过大量基础调研制成108张实验刺激图片,以年轻消费群体为主要调查对象,采集67份实验数据。研究结果表明:服装分割比例和颜色明度对于服装的显瘦感、喜好感呈现规律基本一致;最深明度的颜色显瘦感、喜好感最高,但在次深明度时的显瘦感、喜好感并未次高,所有的感知评分也未符合大众传统认知的“颜色明度越深、显瘦感越高”的规律;未出现极端化评分的样本,认知情感表征不显著。研究成果有助于提升产品的开发效果,调节消费者对身体的满意度,并为服装艺术设计、服装消费者与服装品牌提供一定的参考。