Structure Of Human Body Research Articles

ZoomNAS: Searching for Whole-Body Human Pose Estimation in the Wild.

This paper investigates the task of 2D whole-body human pose estimation, which aims to localize dense landmarks on the entire human body including body, feet, face, and hands. We propose a single-network approach, termed ZoomNet, to take into account the hierarchical structure of the full human body and solve the scale variation of different body parts. We further propose a neural architecture search framework, termed ZoomNAS, to promote both the accuracy and efficiency of whole-body pose estimation. ZoomNAS jointly searches the model architecture and the connections between different sub-modules, and automatically allocates computational complexity for searched sub-modules. To train and evaluate ZoomNAS, we introduce the first large-scale 2D human whole-body dataset, namely COCO-WholeBody V1.0, which annotates 133 keypoints for in-the-wild images. Extensive experiments demonstrate the effectiveness of ZoomNAS and the significance of COCO-WholeBody V1.0.

Emotional Involvement and Attitude of First Year Medical Students towards Cadaveric Dissection: A Study from Andhra Pradesh, India

Introduction: Teaching anatomy in medical colleges has been conventionally based on use of human cadaveric specimens, either whole body specimens for dissection or individual specimens. Cadavers are to be held in high esteem and regarded as the first teacher of a medical student as cadaveric dissection allows students to grasp the three dimensional anatomy and skill development. Aim: To know the physical and psychological effects experienced by students while doing cadaveric dissection and also to know the attitude of the medical students towards dissection in learning anatomy. Materials and Methods: A descriptive cross-sectional study was conducted among the 181 first year medical students in a Government Medical College, Andhra Pradesh, India, during the month of May 2021. The study was undertaken after two months of cadaveric dissection classes and the responses were the cumulative subjective effect of all the classes. Data was collected using a predesigned, prestructured and pretested questionnaire, entered in MS Excel and descriptive statistics like simple frequencies, percentages were used. Chi-square test was used to statistically analyse the data. Results: Total 181 students participated in this study (out of 250 first year medical students). Nearly, 88% of the students were older than 18 years of age. Nearly, 2/3rd of the students were females (65.7%). Out of 181 participants, 152 (84%) experienced psychological symptoms while doing dissection. Out of 152 students, who experienced psychological symptoms, 40.8% experienced excitement followed by anxiety 22.4%, fear 17.8% stress 16.4%. Among those who experienced excitement nearly 70% were females. Sweating was the most common physical symptom experienced by the participants. Among the study participants 98.3% students had sense of gratitude to people who donated their body and 96.1% had sympathy and respect for the cadaver. A 20.4% want to donate body for dissection. While assessing the attitude, 97.2% students agreed that cadaveric dissection is important in the curriculum, 97% agreed that dissection is required for understanding the structure of human body. Conclusion: Student-cadaver encounter is of paramount importance in medical education. Computer assisted and multimedia methods should be complementary but not a substitute to dissection. Introducing cadaver oath has resulted in students reflecting about organ donation and body donation, showing respect to the dead body.

Automatic body region localization in 3D-CT images based on the improved YOLO model

Automatic body region localization in medical three-dimensional (3D)-CT images is a critical step of computerized body-wide Automatic Anatomy Recognition (AAR) system, which can be applied for radiotherapy planning and interest slices retrieving. Currently, the complex internal structure of human body and time consuming computation are the main challenges for the localization. Therefore, this paper introduces and improves the YOLO-v3 model into the body region localization for these problems. First, seven categories of body regions in a CT volume image I are defined based on the modification version of our previous work. Second, an improved YOLO-v3 model is trained to classify each axial slice into one of the seven categories. Then, the effectiveness of the proposed method is evaluated on 3D-CT images that collected from 220 subjects. The experimental results demonstrate that the slice localizing error is less than 3 NoS (Number of slices), which is competitive to the state-of-the-art methods. Beyond this, our method is simple and computationally efficient owing to its less training time, and the average computational time for localizing a volume CT images is about 3 second, which shows potential for a further application.

Human body structure extraction of anime characters based on deep learning

With the popularity of social networking services and smartphones, photo processing applications have become widely used, and there is a growing interest in more advanced photo processing techniques. In the field of image generation, methods based on adversarial generative networks (GANs) have shown particularly good results. We discussed the anime characters’ body structure extraction methods based on generative adversarial networks (GANs). This research is expected to be applied in the field of drawing that can be used as a tool to significantly reduce learning period or provide a new study method for drawing beginners.

A Review on Meshing Techniques in Biomedicine

Engineering has a wide range of applications where more detailed and reliable data are needed, one of which is biomedicine. One of the aims of meshing is to use the Finite Element Approach to solve the problem. By analysing and segmenting raw medical imaging data, meshing aids in a better and more precise understanding of the organs and structures of human body. The main goal of this paper is to collect and review the various available methods in meshing. Also, a comparison study of different meshing techniques that are available in biomedicine is performed.

A Hybrid Deep Learning Model for Recognizing Actions of Distracted Drivers.

With the rapid spreading of in-vehicle information systems such as smartphones, navigation systems, and radios, the number of traffic accidents caused by driver distractions shows an increasing trend. Timely identification and warning are deemed to be crucial for distracted driving and the establishment of driver assistance systems is of great value. However, almost all research on the recognition of the driver’s distracted actions using computer vision methods neglected the importance of temporal information for action recognition. This paper proposes a hybrid deep learning model for recognizing the actions of distracted drivers. Specifically, we used OpenPose to obtain skeleton information of the human body and then constructed the vector angle and modulus ratio of the human body structure as features to describe the driver’s actions, thereby realizing the fusion of deep network features and artificial features, which improve the information density of spatial features. The K-means clustering algorithm was used to preselect the original frames, and the method of inter-frame comparison was used to obtain the final keyframe sequence by comparing the Euclidean distance between manually constructed vectors representing frames and the vector representing the cluster center. Finally, we constructed a two-layer long short-term memory neural network to obtain more effective spatiotemporal features, and one softmax layer to identify the distracted driver’s action. The experimental results based on the collected dataset prove the effectiveness of this framework, and it can provide a theoretical basis for the establishment of vehicle distraction warning systems.

Diagnostic ultrasound imaging of the lung: A simulation approach based on propagation and reverberation in the human body

Although ultrasound cannot penetrate a tissue/air interface, it images the lung with high diagnostic accuracy. Lung ultrasound imaging relies on the interpretation of "artifacts," which arise from the complex reverberation physics occurring at the lung surface but appear deep inside the lung. This physics is more complex and less understood than conventional B-mode imaging in which the signal directly reflected by the target is used to generate an image. Here, to establish a more direct relationship between the underlying acoustics and lung imaging, simulations are used. The simulations model ultrasound propagation and reverberation in the human abdomen and at the tissue/air interfaces of the lung in a way that allows for direct measurements of acoustic pressure inside the human body and various anatomical structures, something that is not feasible clinically or experimentally. It is shown that the B-mode images beamformed from these acoustical simulations reproduce primary clinical features that are used in diagnostic lung imaging, i.e., A-lines and B-lines, with a clear relationship to known underlying anatomical structures. Both the oblique and parasagittal views are successfully modeled with the latter producing the characteristic "bat sign," arising from the ribs and intercostal part of the pleura. These simulations also establish a quantitative link between the percentage of fluid in exudative regions and the appearance of B-lines, suggesting that the B-mode may be used as a quantitative imaging modality.

Combined soft tissue plastics in treatment of the leg infected necrotic lesions

Anatomical features of the leg create prerequisites for the occurrence of severe damage to bone-soft structures with the further development of infection-necrotic complications and osteoielitus. A difficult problem is the development of infected soft tissue defects. Objective. To study the effectiveness of the use of plastic surgical technologies using skin-fascial and muscular patches based on angiosomal concept by Taylor & Palmer. Methods. Treatment results analysis of 3 patients with necrotic defects of the leg soft tissues. All patients initially received high-energy different sites fractures of the leg bones and they were given metaloostheosynthesis using plates. In all cases, treatment was complicated by the occurrence of trophic disorders with infected full-layer defects of soft tissues that did not heal. Results. According to the angiosomal Taylor’s & Palmer’s theory, the human body is divided into 40 three-dimensional zones that combine skin with subordinate fiber and muscles, and have clear limits of blood supply to one nourishing artery. Full-haired soft-blooded patches, taking into account areas of angiosomes, are supplied throughout the plane and to the full depth, which guarantees much better results at the transplant site. The use of traditional plastics technologies in study group patients, on previous treatment did not lead to positive results, and the use of combined plastics based on the angiosomes concept allowed to obtain 100 % positive results, with complete healing of the foci of infection and the absence of relapses. Conclusions. A new stage in the development of plastic surgery, based on the angiosomes theory of human body structure by the blood supply to Taylor & Palmer, is promising for use in traumatology orthopaedics. The experience of using angiosomal patches for plastics of infected defects of the leg soft tissues has proved the high efficiency of this technology, which confirms the expediency of continuing research into the angiosomal theory in the treatment of such pathology another sites. Retrospective analysis of the etiology and pathogenesis for the leg tissues post-traumatic infected defects can be used to correct fracture treatment tactics in order to avoid the development of such complications.

Early concepts of nutrition, digestion, diseases of the gastrointestinal tract and their treatment: Ancient Egypt and Ancient Rome

The Egyptian concept of medicine was complex and related to a widespread religious belief that combined the worship of gods and the medical arts. The healing properties of food, and especially mother’s milk, were well‑known and endowed with divine qualities. Half‑female‑half‑cow Hathor was usually depicted with cow horns and the sun between them. Since medicine and magic were tightly linked, the omens, facts, conscious and unconscious assumptions merged with a mystical mosaic that formed a volatile but honorable system that is currently regarded as a medical art. Supernatural powers were taken into account, and the meaning of art was associated with the powers attributed to the deities. Despite their obvious social and religious‑political experience, the Egyptians had limited knowledge of the internal structure of human body, paying considerable attention to magic, mysticism and afterlife. They deeply believed that most of the diseases originated in the intestines due to their «contaminated» contents. The main problem in understanding diseases and developing their treatment in ancient Egypt was the restrictions associated with the prohibition of body’s desecration. This was based on the assumption that if the shape of the body is not preserved at the time of resurrection, the soul can be lost in void. Thus, the ancient Egyptians were especially concerned with the preservation of body, believing that desecration by animals or worms could also lead to the complete loss of remains for the soul.
 In the society of Ancient Rome, illuminated only by the flame of fire and the thirst for knowledge, the enjoyment of food and the continuation of the family were of great importance. Unsurprisingly, the ancients respected the sensations of eating. Thus, such exquisite dishes as lark tongue, black caviar, ostrich brain, Falernian wines at the time of Emperor Heliogabalus evoked a unique complex of sensations during eating. Examples of ancient Roman medical tools, including mirrors, found in the house of a surgeon from Pompeii (72 — 62 BC), prove the early tendency to visualize human insides. The qualification of the ancient masters of medical tools is confirmed by the fact that the principles used two thousand years ago have changed slightly.
 Thus, there were initial concepts of nutrition, digestion, diseases of the digestive tract, and even the rudiments of diagnosing these diseases in Ancient Egypt and Ancient Rome. They served as the basis for the further development of gastroenterological science.

ResNet-50 vs VGG-19 vs training from scratch: A comparative analysis of the segmentation and classification of Pneumonia from chest X-ray images

In medical imaging, segmentation plays a vital role towards the interpretation of X-ray images where salient features are extracted with the help of image segmentation. Without undergoing surgery, clinicians employ various modalities ranging from X-rays and CT-Scans to ultrasonography, and other imaging techniques to visualise and examine interior human body organ and structures. To ensure appropriate convergence, training a deep convolutional neural network (CNN) from scratch is tough since it requires more computational time, a big amount of labelled training data and a considerable degree of experience. Fine-tuning a CNN that has been pre-trained using, for instance, a huge set of labelled medical datasets, is a viable alternative. In this paper, a comparative study was done using pre-trained models such as VGG-19 and ResNet-50 as against training from scratch. To reduce overfitting, data augmentation and dropout regularization was used. With a recall of 92.03%, our analysis showed that the pre-trained models with proper finetuning was comparable with Iyke-Net, a CNN trained from scratch.

Cardiac Magnetic Resonance Images Superresolution via Multichannel Residual Attention Networks.

The deep neural network has achieved good results in medical image superresolution. However, due to the medical equipment limitations and the complexity of the human body structure, it is difficult to reconstruct clear cardiac magnetic resonance (CMR) superresolution images. To reconstruct clearer CMR images, we propose a CMR image superresolution (SR) algorithm based on multichannel residual attention networks (MCRN), which uses the idea of residual learning to alleviate the difficulty of training and fully explore the feature information of the image and uses the back-projection learning mechanism to learn the interdependence between high-resolution images and low-resolution images. Furthermore, the MCRN model introduces an attention mechanism to dynamically allocate each feature map with different attention resources to discover more high-frequency information and learn the dependency between each channel of the feature map. Extensive benchmark evaluation shows that compared with state-of-the-art image SR methods, our MCRN algorithm not only improves the objective index significantly but also provides richer texture information for the reconstructed CMR images, and our MCRN algorithm is better than the Bicubic algorithm in evaluating the information entropy and average gradient of the reconstructed image quality.

Unity and separation of lifting-thrusting and twirling reinforcing-reducing manipulation

To analyze the collaborative use and separation reasons of lifting-thrusting and twirling reinforcing and reducing manipulation. Lifting-thrusting manipulation and twirling manipulation are two important contents of acupuncture methods. In traditional acupuncture and moxibustion, the two methods were used in reinforcing and reducing concert, which was mainly related to the therapeutic thought guided by the qi-blood theory and the influence of the human body structure on the technique manipulation. After the Republic of China, the separation of lifting-thrusting manipulation and twirling manipulation gradually appeared. It was related to the widespread use of "scientific acupuncture method" in later generations and the integration of neuroscience into the acupuncture treatment system.

A Feasibility Study on Smart Mattresses to Improve Sleep Quality.

Good sleep quality is essential, especially for clinical users. Sleep disorders not only impair the success rate of treatment but also delay recovery. They can seriously interfere with treatment outcomes and even endanger a user's life. In this study, we created a smart mattress containing 10 × 18 air packs and control units. Each air pack contains a set of pressure and height sensors and two air valves. Each row control unit can detect and adjust the pressure and height of each air bag in the row. When the bed body is turned on, it automatically initializes, adjusts the state of each air bag to the same height and pressure, and enters a slow scanning state. When perceived objects or people are lying on the bed, the bed automatically perceives the human body structure and body pressure matrix, increases the scanning speed for more timely and accurate measurements of the digital matrix and forming pressure by matrix-normalized processing, and then uses local pressure variance detection to automatically adjust to the sleeping position of the human body and thus achieve a uniform force distribution and a comfortable state. Finally, pressure matrix binarization was used to match sleeping position templates to identify the best template for automatic recognition of the sleeping position. The experimental results show that the sleeping position recognition method has high accuracy, recall, and precision. Our mattress is designed with interfaces for external devices. In future research, the smart mattress can connect to an auxiliary part of a smart ecosystem consisting of a smart pill box, a smart lighting system, and a microclimate system, which is expected to yield a more comprehensive intelligent ward to explore the possibility of improving sleep quality.

Image Tracking and Detection of Standing Posture of Moving Human Body Based on The Recognition Algorithm of Human Body Structure

Aiming at the problem of human motion posture and recognition in low-quality deep images, the three-step search algorithm can be adopted by using the human body structure posture recognition algorithm. This paper firstly explains the significance of human standing posture image tracking detection, and at the same time carries out depth image acquisition and tracking calculation in combination with the experiment of moving human posture image. In the aspect of the tracking algorithm based on the depth image, the complex estimation problem is transformed into a simple classification problem by predicting the position of human bone points based on the image, which has made a breakthrough in the research on the tracking algorithm of human motion and posture.

Research on Individualized Phantom Based on 3D Printing for Radiotherapy Dose Verification

Dose verification is carried out on the individualized three-dimensional phantom based on 3D printing technology, which simulates the anatomical structure of human body, contour shape, tumor anatomical structure and other dangerous organs to the greatest extent, and produces a reasonable and effective dose validation phantom. According to the need to obtain effective patient data, import Mimics software to reconstruct the parts of the body and its surrounding tissues and organs that need to be measured, and make them into three-dimensional shell components. The 3D printing is used to assemble and fill the equivalent tissue, and then the body phantom is made. The phantom was scanned by CT and the data was transmitted to TPS system. The previously completed treatment plan was transplanted to the phantom. The phantom was placed according to the patient's location information, irradiated and measured data. The three-dimensional shell assembly is completely reconstructed according to the patient's data, and the contour difference is not significant. The shell is filled with tissue radiation equivalent material whose CT value is the same as the average CT value of the shell volume. The CT image data show that the radiation equivalence of the phantom is similar to the actual tissue of the patient, and the equivalent dose distribution conforms to the conventional treatment range. It can provide a reliable means of dose verification for the accurate design of intensity modulated radiation therapy.

Facilitating Student Understanding through Incorporating Digital Images and 3D-Printed Models in a Human Anatomy Course

Combining classical educational methods with interactive three-dimensional (3D) visualization technology has great power to support and provide students with a unique opportunity to use them in the study process, training, and/or simulation of different medical procedures in terms of a Human Anatomy course. In 2016, Rīga Stradiņš University (RSU) offered students the 3D Virtual Dissection Table “Anatomage” with possibilities of virtual dissection and digital images at the Department of Morphology. The first 3D models were printed in 2018 and a new printing course was integrated into the Human Anatomy curriculum. This study was focused on the interaction of students with digital images, 3D models, and their combinations. The incorporation and use of digital technologies offered students great tools for their creativity, increased the level of knowledge and skills, and gave them a possibility to study human body structures and to develop relationships between basic and clinical studies.

Massive-scale complicated human action recognition: Theory and applications

Recognizing various human actions in video is a challenging task, which is also one of the key tasks in computer vision. It has received extensive attention from AI researchers Bakker et al. (2003), Bruderlin and Williams (1995), Cardle et al. (2003), Carlsson (1996, 1999), Clausen and Kurth (2004). It has important applications in human behavior analysis, artificial intelligence, and video surveillance. Compared with still image classification, the time component of video provides important clues for recognition, so multiple human actions can be recognized based on motion information. In addition, video provides natural data enhancement for individual images. For motion recognition from videos, appearance and temporal dynamics are two key and complementary cues. In this work, we formulate a human motion recognition framework based on 2D spatial feature fusion of Kinect bone data. This method utilizes the human body structure and spatial geometry to represent human body structure and extract features. Meanwhile, it combines the active action and auxiliary action features of two spatial dimensions by layering, and leverages the pervasively used support vector machine and hidden Markov model to classify human body structure. Noticeably, it is difficult to extract its information due to the limitations of background clutter, viewpoint change, scale change, different lighting conditions and camera movement. In this way, while learning the classification information of human behavioral categories, designing effective representations is the key to deal with these challenges. In this work, a method for human motion recognition in video based on ResNext network is proposed. Based on our proposed ResNeXt network, using the data of RGB and optical flow, we can extract more appearance characteristics and temporal features of human actions, so as to better achieve the classification of actions. The utilization of video time segmentation method can capture the long range of time in video, in order to make better use of the longer range of time information in video. Comprehensive experimental results have shown that the proposed method improves the performance of UCF101 and HMDB51 motion recognition data sets to a certain extent.

STUDY OF GIT RELATED KOSHTHANGA W.S.R. TO PAKWASHAYA

Human anatomy is the science where human body structures are designed to enable complete physiological action thus establishing homeostasis of the human body. Acharya Sushruta had a keen observation about the human body reflecting that without the absolute knowledge of Rachana Sharir. Chikitsak cannot be considered an expert. In Ayurveda, the part of G.I.T. is mentioned in Koshthanga by various Acharya. These Koshthanga are Aamashaya, Pakwashaya, Purishdhara, Uttarguda, Adharguda, Kshudrantra etc. which are situated within the koshtha. In modern anatomy, G.I.T. or Alimentary canal includes all the structures between the mouth and anus, forming a continuous passageway that includes the main organ of digestion, namely the stomach small intestine and large intestine, each part of the Gastric intestinal tract is adapted to its specific function. The 'oesophagus' function primarily to conduct food rapidly from the pharynx to the stomach mixing along with the digestive juic- es, carrying out partial digestion and then propelling the food into the duodenum is the function of the stomach small intestine is designed for complete digestion and absorption of nutrients. Absorption of water and electrolyte from the chyme to form solid faeces is the function of the large intestine. Pakwashaya is the main organ related to the site of Vata Dosha, Purishvaha srotas, Purishdhara kala, Koshthanga and Aashaya. Pakwashaya plays an important role in formation of urine and digestion of food. Keywords: Pakwashaya, Purish

The decreasing prevalence of the thyroid ima artery: A systematic review and machine learning assisted meta-analysis

IntroductionThyroid ima artery is a variant artery found on the anterior surface of the trachea. The aim of this meta-analysis was to obtain pooled prevalence data of the thyroid ima artery and discuss its clinical importance especially for tracheostomy. MethodsA systematic literature search was performed through five electronic databases until May 2021. A set of inclusion and exclusion criteria based on AQUA guidelines were used to select relevant studies. Meta-analysis, subgroup analyses, meta-regression, and tests for publication bias were performed. Factors that influence the prevalence of the thyroid ima artery were detected using simple and interpretable machine learning (linear regression and K means). ResultsThirty-six studies with a total of 4335 subjects met the inclusion criteria. The prevalence of the thyroid ima artery was 3.8% (95% CI: 0.027−0.049, I2=56.2%). Machine learning identified age, region and year of publication as potential covariates. Subgroup analysis showed that the prevalence of the thyroid ima artery was 4.5 times higher in fetuses (14.8%) than adults (3.3%) (z=−6.76, p<0.01). There was a significant negative correlation between the adult prevalence of the thyroid ima artery and the year of publication (Pearson’s r=−0.354, p=0.040) thereby suggesting a decline in thyroid ima artery prevalence over time. This artery, if present, may originate from the brachiocephalic trunk (74%), right common carotid artery (9.6%), arch of aorta (7.7%), right internal thoracic artery (4.8%), left common carotid artery (1.9%) and left internal thoracic artery (1.9%). ConclusionIn addition to evidence-based synthesis of the thyroid ima artery, this study is the first ever study to report the decreasing prevalence over time of a human body structure in the postnatal life. Knowledge of the thyroid ima artery is of vital importance for surgeons to avoid accidental hemorrhage during tracheostomy.

Extended-Reality Technologies: An Overview of Emerging Applications in Medical Education and Clinical Care.

Extended-Reality Technologies: An Overview of Emerging Applications in Medical Education and Clinical Care.