Digital X-ray Imaging Research Articles

Detection of turner syndrome using hand X-ray using anchor based links segmentation method.

Turner Syndrome (TS) is a chromosomal disorder, wherein the female's growth is impacted. Immature ovaries, low stature, and heart abnormalities are a range of developmental and medical issues due to TS. The condition of TS might be detected prior to birth, throughout infancy or in the early years of life. The diagnosis of TS in girls with modest symptoms and indications is sometimes deferred until they reach adolescence or become young adults. This study presents an algorithm to segment the hand digital X-ray image in children with TS. In medical image and computer vision examination, image segmentation is demanding, and very crucial. Prevailing segmentation algorithms even now suffer from common segmentation issues including under-segmentation, over-segmentation, and spurious or non-closed edges, regardless of the several years of studies. In this paper, Anchor Based Link (ABL) segmentation approach is proposed to detect TS based on fourth Metacarpal bone from left hand X-ray images. The detection of TS is demonstrated based upon the comparison of proposed approach with existing watershed segmentation and Gaussian-Mixture-Model-based Hidden-Markov-Random-Field (GMM-HMRF) method. The proposed approach attains better segmentation based on the ratio of height and width of left fourth finger that is analyzed for normal children and children having TS with the help of edge pixel present in the metacarpal bone that has been segmented. The suggested method is verified on fifty (50) sample X-ray hand images of carpal bones, providing 0.60 ± 0.02 as an average Dice coefficient.

The Relationship Between Lateral Femoral Condyle Index and Noncontact Anterior Cruciate Ligament Rupture.

PurposeThe purpose of this study was to examine the relationship between distal femoral morphology and noncontact anterior cruciate ligament (ACL) rupture and the differences between digital X-ray imaging systems (DR) and magnetic resonance imaging (MRI) to evaluate distal femoral morphology.MethodsA retrospective case-control study was performed on 120 patients. Two age- and sex-matched cohorts (each n = 60) were analyzed: primary ACL ruptures and a control group consisting of isolated meniscal tears. The lateral femoral condyle index (LFCI) was measured by DR and by MRI to quantify femoral sphericity. Differences among two groups were compared, and diagnostic performance of the risk factors was assessed. In addition, differences between DR and MRI to evaluate LFCI were examined.ResultsThe LFCI by MRI was smaller in the knees with primary ACL rupture (median, 0.71; range, 0.62–0.78) than that of the control group (median, 0.77; range, 0.66–0.85) (p < 0.01). The LFCI was also significantly smaller in the knees with primary ACL rupture (median, 0.72; range, 0.63–0.77) than that of the control group (median, 0.79; range, 0.65–0.84) (p < 0.01) by DR. A cutoff of 0.74 of MRI yielded a sensitivity of 77% and a specificity of 78% to predict an ACL rupture, and of 0.75 of DR yield a sensitivity of 87% and a specificity of 77% to predict an ACL rupture.ConclusionThis study showed that a decreased LFCI is associated with an ACL rupture, and both DR and MRI measurements can effectively predict the risk of ACL rupture. This helps expand the scope of the application of the LFCI and helps clinicians identify susceptible individuals who may benefit from targeted ACL rupture prevention counseling and intervention.

Effects of insertion torque values on the marginal bone loss of dental implants installed in sheep mandibles

The aim of the present in vivo study was to analyze and compare the effects on the crestal bone healing of two different implant macrogeometries installed in fresh socket areas and in normal bone areas with different insertion torque values. Two implant macrogeometries were used in the present study, DuoCone implant (DC) and Maestro implant (MAE), forming four groups: group DCws, in which the implants were installed in healing bone (without a socket); group DCfs, in which the implants were installed in post-extraction areas (fresh sockets); group MAEws, in which the implants were installed in healing bone (without a socket); group MAEfs, in which the implants were installed in post-extraction areas (fresh sockets). After 30 and 90 days of implantations in the bilateral mandibles of 10 sheep, eighty implants were evaluated through digital X-ray images and histologic slices. The crestal bone position in relation to the implant platform shoulder was measured and compared. The measured insertion torque was 47.2 ± 4.69 Ncm for the DCws group, 43.4 ± 4.87 Ncm for the DCfs group, 29.3 ± 3.16 Ncm for the MAEws group, and 27.7 ± 4.41 Ncm for the MAEfs group. The radiographic mesio-distal and histological bucco-lingual analyses showed significantly greater vertical bone loss in the implants installed with high torque (DC groups) in comparison to the implants installed with a low torque (MAE groups) (p < 0.05), at both evaluation times. In general, low insertion torque values (Maestro implants) showed better results of MBL when compared to implants installed with higher torque values (Duo Cone implants). Moreover, our results showed that the implants installed in the sites without sockets showed a less MBL in comparison with the implants installed in sites of fresh sockets.

Analysis of the Application Value of X-Ray Digital Tomographic Fusion Technique in Urinary System Diseases.

Objective To explore the application value of the X-ray digital tomographic fusion technique in the diagnosis of urinary system diseases. Methods 500 patients with suspected urinary diseases in our hospital were examined by three methods: X-ray digital tomographic fusion imaging (DTS), intravenous pyelography (IVP), and abdominal plain film (KUB), and the image quality before and after tomographic fusion was objectively evaluated. The image quality could be divided into three grades: excellent, good, and poor. Results The image excellent rate of DTS (88%) was higher than that of IVP (27.5%). The sensitivity of DTS in the diagnosis of renal cyst and space occupying of the bladder was higher than that of IVP (P < 0.05). The accuracy rate of DTS in the diagnosis of urinary calculi was 93.33%, higher than 63.3% of KUB (P < 0.001). The accuracy rate of DTS in the diagnosis of ureteral stricture was 90%, higher than 65% of IVP (P=0.03). The accuracy of DTS in the diagnosis of hydronephrosis was higher than that of IVP and KUB (P < 0.05). Conclusion In the examination of urinary system-related diseases, high-definition images can be obtained by timely using sectional fusion technology. Compared with conventional IVP, space occupying lesions such as the bladder and kidney can be displayed more clearly with the help of the tomographic fusion technique, which is helpful to improve the possibility of finding lesions and is of great significance in clinical application.

Machine Learning Techniques for Human Age and Gender Identification Based on Teeth X-Ray Images.

The use of digital medical images is increasing with advanced computational power that has immensely contributed to developing more sophisticated machine learning techniques. Determination of age and gender of individuals was manually performed by forensic experts by their professional skills, which may take a few days to generate results. A fully automated system was developed that identifies the gender of humans and age based on digital images of teeth. Since teeth are a strong and unique part of the human body that exhibits least subject to risk in natural structure and remains unchanged for a longer duration, the process of identification of gender- and age-related information from human beings is systematically carried out by analyzing OPG (orthopantomogram) images. A total of 1142 digital X-ray images of teeth were obtained from dental colleges from the population of the middle-east part of Karnataka state in India. 80% of the digital images were considered for training purposes, and the remaining 20% of teeth images were for the testing cases. The proposed gender and age determination system finds its application widely in the forensic field to predict results quickly and accurately. The prediction system was carried out using Multiclass SVM (MSVM) classifier algorithm for age estimation and LIBSVM classifier for gender prediction, and 96% of accuracy was achieved from the system.

An Improved Neural Network Method for Forearm Bone Imaging Segmentation

In this paper, we propose several improved neural networks and training strategy using data augmentation to segment human radius accurately and efficiently. This method can provide pixel-level segmentation accuracy through the low-level features of the neural network, and automatically distinguish the classification of radius. The versatility and applicability can be effectively improved by learning and training digital X-ray images obtained from digital X-ray imaging systems of different manufacturers.

Study of Keypoints Detectors and Descriptors Performance on X-Ray Images Compared to the Visible Light Spectrum Images

In this work, we study the performance of wide-used keypoints detection and description algorithms: Scale-Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF), Oriented FAST and Rotated BRIEF (ORB), Binary Robust Invariant Scalable Keypoints(BRISK), Accelerated KAZE(AKAZE), which were originally developed for images taken in visible light but widely applied in the fields where images are taken in a different spectrum. We compare the quality of algorithms and their robustness to various image transformations. The algorithms&#x2019; performance is tested on two image sets in the different spectra: digital X-Ray images and images taken in the visible spectrum. Each dataset captures complex scenes with many objects and partial occlusions. Geometrical transformations (rotation, shearing, scaling), linear color transformations, Gaussian blur are applied to the images. Then the detection and description algorithms are tested on the original and transformed images. The repeatability and number of corresponding points are calculated to assess detection algorithms. The ratio of correctly matched descriptors together with the ratio of the distances between the query descriptor, the nearest descriptor, and the second matched descriptor is computed to evaluate descriptors&#x2019; quality. The algorithms showed different behavior on different spectra. SURF demonstrated to be the best X-ray keypoint detector and for the visible spectrum, it shares first place with AKAZE detector. SIFT is the best descriptor in both spectra. The strong and weak points of each algorithm are discussed in the paper.

CheXImageNet: a novel architecture for accurate classification of Covid-19 with chest x-ray digital images using deep convolutional neural networks.

Many countries around the world have been influenced by Covid-19 which is a serious virus as it gets transmitted by human communication. Although, its syndrome is quite similar to the ordinary flu. The critical step involved in Covid-19 is the initial screening or testing of the infected patients. As there are no special detection tools, the demand for such diagnostic tools has been increasing continuously. So, it is eminently admissible to find out positive cases of this disease at the earliest so that the spreading of this dangerous virus can be controlled. Although, some methods for the detection of Covid-19 patients are available, which are performed upon respiratory based samples and among them, a critical approach for treatment is radiologic imaging or X-ray imaging. The latest conclusions obtained from X-ray digital imaging based algorithms and techniques recommend that such type of digital images may consist of significant facts regarding the SARS-CoV-2 virus. The utilization of Deep Neural Networks based methodologies clubbed with digital radiological imaging has been proved useful for accurately identifying this disease. This could also be adjuvant in conquering the problem of dearth of competent physicians in far-flung areas. In this paper, a CheXImageNet model has been introduced for detecting Covid-19 disease by using digital images of Chest X-ray with the help of an openly accessible dataset. Experiments for both binary class and multi-class have been performed in this work for benchmarking the effectiveness of the proposed work. An accuracy of 100% is reported for both binary classification (having cases of Covid-19 and Normal X-Ray) and classification for three classes (including cases of Covid-19, Normal X-Ray and, cases of Pneumonia disease) respectively.

Radiological Imaging of Nail Disorders (PART II) - Radiological Features of Nail Disease.

We have seen that radiological techniques like digital x-ray, high-frequency ultrasonography (USG), computed tomography (CT), and magnetic resonance imaging (MRI) have their unique roles in assessing a complex anatomical structure like the nail unit. Broadly speaking, USG and MRI help evaluate soft tissue components well; while, radiographs and CT scans help assess bony lesions better. In the second part of this review, salient radiological features of various nail disorders, as seen on these modalities are detailed. The radiological features mostly play a supportive role and help rule out differential diagnoses. However, in some diseases like retronychia and some nail tumors, radiological findings help clinch the diagnosis. The diagnostic features as well as the investigative modality of choice for a particular disease are highlighted based on the best level of evidence (LoE) available. This narrative review includes both infectious and non-infectious nail unit diseases, with special emphasis on nail unit tumors.

Evaluation of AEC Consistency in Digital X-ray Imaging Systems

The Japan Network for Research and Information on Medical Exposures (J-RIME) established the diagnostic reference level (DRL) and is advancing optimization of radiation protection. We believe that the difference in the imaging dose between facilities may be due to the fact that automatic exposure control (AEC) adjustment is not unified among manufacturers. The consistency of AEC is specified in JIS 4751-2-54, but it is not applicable to digital X-ray imaging systems because it is for optical density of analog X-ray imaging systems. This article evaluates the consistency of AEC in digital X-ray imaging systems. The AEC consistency was compared with the AEC-estimated dose from the air kerma (KAEC) using the phosphor-based imaging plate placed at the back of the AEC detector. We measured the AEC tube voltage and subject thickness characteristics (tracking) of four types of digital X-ray imaging systems at three facilities. In the test of tube voltage characteristics, the average KAEC values at all tube voltages were 2.37±0.04 µGy for A system, 7.30±1.44 µGy for B system, 3.53±0.13 µGy for C system, and 5.70±0.18 µGy for D system. The relative errors were +2.6 to -1.8% for A system, +25.3 to -22.6% for B system, +5.2 to -1.4% for C system, and +2.5 to -4.4% for D system. In the subject thickness characteristics test, the average KAEC values for all Al thicknesses were 2.34±0.02 µGy for A system, 5.95±0.23 µGy for B system, 4.25±1.12 µGy for C system, and 5.03±1.27 µGy for D system. The relative errors were +1.0 to -0.9% for A system, +4.1 to -5.0% for B system, +40.5 to -28.1% for C system, and +19.7 to -42.9% for D system.

Imaging Analysis of Trabecular Bone Texture Based on the Initial Slope of Variogram of Ultra-Distal Radius Digital X-Ray Imaging: Effects on Bone Mineral Density and Age

Background: When applied to trabecular bone X-ray images, a method for analyzing trabecular bone texture based on the initial slope of variogram (ISV) was used to assess the trabecular bone health. Methodology: Data from more than two hundred subjects were retrospectively studied. For each subject, a DXA (GE Lunar Prodigy) scan of the forearm was performed, and bone mineral density (BMD) value was measured at the location of ultra-distal radius, X-ray digital image of the same forearm was taken on the same day, and ISV value over the same location of ultra-distal radius was calculated. Pearson’s correlation coefficients were calculated to examine the correlation between BMD and ISV of the trabecular bones located at the same ultra-distal radius. ISV values changed with subjects’ age were also reported. Results: The results show that ISV value was highly correlated with the DXA-measured BMD of the same trabecular bone located at the ultra-distal radius. The correlation coefficient between ISV and BMD with the 95% confident was 0.79 ± 0.09. They also demonstrated that the age-related changes in trabecular bone health and differentiated age patterns in males and females, respectively. The results showed that the decrease in BMD was accompanied by a decrease in the initial slope of variogram (ISV). Conclusions: This study suggests that ISV might be used to quantitatively evaluate trabecular health for osteoporosis and bone disease diagnosis.

Assessment of Brassicaceae Seeds Quality by X-ray Analysis

A serious problem of vegetable production is the quality of sown seeds. In this regard, assessment of seed quality before sowing and storage is of great practical interest. The modern level of scientific research requires the use of instrumental automated methods of seed quality evaluation, allowing to obtain more information and in a shorter time. The material for the study was a variety of samples from the collection of Brassica oleracea L., var. capitata, Raphanus sativus L., var. radicula, and Lepidium sativum L. seeds from the Federal Scientific Center of Vegetable Breeding and the Timofeev Selection Station. Digital X-ray images of seeds were obtained using a mobile X-ray diagnostic device PRDU-02. Automatic analysis of digital X-ray images was performed in the software “VideoTesT-Morphology 5.2.” The following latent defects of cabbage seeds of economic importance were revealed and identified: irregular darkening, significant “patterning” with deep separation of embryo parts, “angularity of seeds” leading to the loss of their viability. Automatic analysis of digital X-ray images of seeds confirmed the informativeness of brightness indices of digital X-ray images, as well as shape indices. Their connection with sowing qualities of the studied seeds was established.

Pneumoconiosis computer aided diagnosis system based on X-rays and deep learning

PurposeThe objective of this study is to construct a computer aided diagnosis system for normal people and pneumoconiosis using X-raysand deep learning algorithms.Materials and methods1760 anonymous digital X-ray images of real patients between January 2017 and June 2020 were collected for this experiment. In order to concentrate the feature extraction ability of the model more on the lung region and restrain the influence of external background factors, a two-stage pipeline from coarse to fine was established. First, the U-Net model was used to extract the lung regions on each sides of the collection images. Second, the ResNet-34 model with transfer learning strategy was implemented to learn the image features extracted in the lung region to achieve accurate classification of pneumoconiosis patients and normal people.ResultsAmong the 1760 cases collected, the accuracy and the area under curve of the classification model were 92.46% and 89% respectively.ConclusionThe successful application of deep learning in the diagnosis of pneumoconiosis further demonstrates the potential of medical artificial intelligence and proves the effectiveness of our proposed algorithm. However, when we further classified pneumoconiosis patients and normal subjects into four categories, we found that the overall accuracy decreased to 70.1%. We will use the CT modality in future studies to provide more details of lung regions.

Do Weight-Bearing Knee Digital Radiographs Help to Track the Severity of OA?

Weight-bearing radiographs are preferred for joint space width (JSW) assessment in OA, sometimes non-weight-bearing radiographs are also done. This study aims to evaluate (1) The knee JSW in weight-bearing (WB) and non-weight-bearing (NWB) X-ray images. (2) Quadriceps angle (Q angle) at weight-bearing and non-weight-bearing positions. Patients above 50years old with symptoms (knee pain, functional limitations, and crepitus) from April 2019 to November 2019 were included in the study. Expert exclude patients with post-surgical evaluation, trauma, and infection. JSW and Q angle measurements with respect to weight-bearing and non-weight-bearing positions were made by the same medical expert to avoid inter-observer variation. Medial knee JSW varies from 0.49 to 5.75mm in weight-bearing radiograph and 0.53mm to 6.16mm in non-weight-bearing radiograph. Q angle varies from 8.72° to 14.58° in weight-bearing position and 10.13° to 14.92° in non-weight-bearing position. Q angle (< 11.72°) and medial JSW (< 3.725mm) were found to be significantly associated with the rapid progression of knee varus OA (p < 0.001). NWB digital X-ray images overestimate early and underestimate severe OA. There is a possibility of increasing tibia internal rotation and reduction of joint space width in a standing position (WB) as the phase of knee OA diagnosis. These findings show that weight-bearing knee joint radiographs are helpful to track the progression of knee varus OA and have strong clinical usage than non-weight-bearing radiographs. Patients whose Q angle and knee JSW measures are below the limitations need more attention.

Research on latent defect detection technology of high voltage cable

As a component of the Internet of things, high-voltage cables are the power supply infrastructure for the modern development of cities. The operation experience shows that the high-voltage cable has been broken down many times, due to the defective operation. At present, due to the limitation of detection technology, the research on detection and identification of defects in high-voltage cables is progressing slowly. Therefore, a new DR technology based on X-ray digital imaging is proposed in this paper to realize real-time detection of defects in the semi-conductive buffer layer of high-voltage cables, and intelligent detection of DR images of high-voltage cables by using image depth processing technology to realize intelligent identification of defects in the buffer layer of power cables. The results show that using the new DR technique proposed in this paper, the accurate and intuitive DR image of high-voltage cable can be obtained quickly, and the intelligent identification of defects can be realized.

RAD_IQ: A free software for characterization of digital X-ray imaging devices based on the novel IEC 62220-1-1:2015 International Standard

Characterization of digital X-ray imaging devices is very important because it can be used to measure and compare the performance of detectors used in Diagnostic Radiology. This characterization is usually made through the calculation of Modulation Transfer Function (MTF), Noise Power Spectrum (NPS) and Detective Quantum Efficiency (DQE). These parameters, especially the DQE, are very important because they quantify the effect of spatial resolution, contrast and noise on Radiographic image quality (IQ). The IEC 62220-1-1:2015 International Standard provides comprehensive guidelines how to capture and analyze X-ray images to characterize digital X-ray detectors. A novel, fast and free MATLAB-based software was developed, named RAD_IQ, to calculate the Signal Transfer Property (STP), perform Noise Component Analysis (NCA), and calculate the parameters MTF, NPS & DQE of X-ray detectors based on the novel IEC 62220-1-1:2015 International Standard for General Radiography and IEC 62220-1-1:2007 for Digital Mammography. Our results were validated against well-established software products used for quantitative image analysis of digital X-ray detectors. The calculated parameters were within 5% difference compared to available software products. The conclusion of our study was that RAD_IQ can be easily used from Medical Physicists, Biomedical Engineers and researchers without any programming experience to characterize the performance of digital X-ray detectors used in Diagnostic Radiology.

A New Endangered Species of Senna (Leguminosae) from the Atlantic Forest of Bahia, Brazil, Supported by X-ray Analysis of Leaflets

Abstract— Senna (Leguminosae, Cassiinae) is a speciose genus widely distributed throughout tropical and subtropical regions of the world. During taxonomic studies of Senna sect. Chamaefistula ser. Bacillares, a new endemic and endangered species from the Atlantic Forest of Bahia, Brazil was discovered. The new species, Senna bahiensis, is compared with its morphologically similar species Senna gardneri, including x-ray analysis comparison of their leaflet venation patterns. The use of high resolution x-ray digital images provided the decisive information, being a promising technique to be used in systematic studies.

Visual Evaluation of Image Quality of a Low Dose 2D/3D Slot Scanner Imaging System Compared to Two Conventional Digital Radiography X-ray Imaging Systems.

The purpose of this study was to assess the image quality of the low dose 2D/3D slot scanner (LDSS) imaging system compared to conventional digital radiography (DR) imaging systems. Visual image quality was assessed using the visual grading analysis (VGA) method. This method is a subjective approach that uses a human observer to evaluate and optimise radiographic images for different imaging technologies. Methods and materials: ten posterior-anterior (PA) and ten lateral (LAT) images of a chest anthropomorphic phantoms and a knee phantom were acquired by an LDSS imaging system and two conventional DR imaging systems. The images were shown in random order to three (chest) radiologists and three experienced (knee) radiographers, who scored the images against a number of criteria. Inter- and intraobserver agreement was assessed using Fleiss’ kappa and weighted kappa. Results: the statistical comparison of the agreement between the observers showed good interobserver agreement, with Fleiss’ kappa coefficients of 0.27–0.63 and 0.23–0.45 for the chest and knee protocols, respectively. Comparison of intraobserver agreement also showed good agreement with weighted kappa coefficients of 0.27–0.63 and 0.23–0.45 for the chest and knee protocols, respectively. The LDSS imaging system achieved significantly higher VGA image quality compared to the DR imaging systems in the AP and LAT chest protocols (p < 0.001). However, the LDSS imaging system achieved lower image quality than one DR system (p ≤ 0.016) and equivalent image quality to the other DR systems (p ≤ 0.27) in the knee protocol. The LDSS imaging system achieved effective dose savings of 33–52% for the chest protocol and 30–35% for the knee protocol compared with DR systems. Conclusions: this work has shown that the LDSS imaging system has the potential to acquire chest and knee images at diagnostic quality and at a lower effective dose than DR systems.

A deep learning approach for detecting pneumonia in chest X-rays

Pneumonia causes the death of many children every year and constitutes a certain proportion of the world population. Chest X-rays are primarily used to diagnose this disease, but even for a trained radiologist, chest X-rays are not easy to interpret. In this study, a model for pneumonia detection trained on digital chest X-ray images is presented to assist radiologists in their decision-making processes. The study is carried out on the Phyton platform by using deep learning models, which have been widely preferred recently. In this study, a deep learning framework for pneumonia classification with four different CNN models is proposed. Three of them are pre-trained models, MobileNet, ResNet and AlexNet and the other is the recommended CNN Model. These models are evaluated by comparing them with each other according to their performance. The experimental performance of the proposed deep learning framework is evaluated on the basis of precision, recall and f1-score. The models achieved accuracy values of 93%, 97%, 97% and 86%, respectively. It is clear that the proposed ResNet model achieves the highest results compared to the others.

Kyphosis types of the spine cervical-thoracic junction

Introduction. The strengthening of thoracic kyphosis and forward head posture is one of the urgent problems of modern man. Such changes are most often detected for elderly and senile people. However, today these features are also detected for young people. Digital radiography can objectively assess the position of the cervical and thoracic vertebrae. However, the criteria for reliably registering the position of the vertebrae of the cervicalthoracic junction have not yet been developed.The aim of the study — to develop a method for assessing the position of the vertebrae of the cervical-thoracic junction according to digital radiographs; to develop a typology of the vertebra positions of the cervical-thoracic junction; to study the frequency of vertebral position types for the cervical-thoracic junction for different age groups.Materials and methods. Spine X-ray images in the sagittal plane for 141 adult patients with dorsopathies were studied. The selection of patients was random and there were four age groups: 32 persons aged 21 to 45, 32 persons aged 46 to 59, 50 persons aged 60 to 74 and 21 persons aged 75 to 88 year-old. The study was conducted on PC screen, without the patient′s presence. A single digital X-ray image of the spine for each patient in the sagittal plane was obtained. On the combined digital radiograph, the occipital vertical was drawn along all parts of the spine, starting from the external hillock of the occipital bone downwards, and the anteroposterior CV–TV axes of the vertebrae (r axes) were applied. At the points of intersection of the axes with the occipital vertical, the perpendiculars to the axis were restored, and the angles between the perpendiculars and the vertical — the angles of the anteroposterior axes of the vertebrae (r angles) — were measured. Statistical analysis was performed using the MS Offi ce Excel 2007 and Statistica 12 software packages.Results. It was found that the values of the anteroposterior axe angles r of CVII–TIII vertebrae can serve as criteria for determining the spatial position of the cervical-thoracic junction vertebrae. There are 4 types of the shape of the cervical-thoracic junction. Type I is a straightened kyphosis («giraffe neck»); type II is physiological («harmonious»); type III — enhanced kyphosis («bear withers»); type IV–hyperkyphosis («buffalo hump»). Types III and IV are accompanied by a forward displacement of the head. Straightened cervical-thoracic junction kyphosis — type I — was diagnosed in 21 (15 %) people, 52 (37 %) patients were assigned to type II, another 48 (34 %) patients had type III, and 20 (14 %) patients had type IV cervical-thoracic junction kyphosis. In young patients aged 21 to 45, as well as in middle-aged patients aged 46 to 59, the most common type was the harmonious type II of cervical-thoracic junction, in elderly patients aged 60 to 74 — type III and close to it in frequency was type III. In elderly patients aged 75 to 88, the IV type of the position of the vertebrae of the cervical-thoracic junction prevailed in frequency.Conclusion. The proposed diagnostic method allows to register the type of the vertebra positions in cervicalthoracic junction for each patient. Four position types of the cervical-thoracic junction vertebrae were determined: straightened kyphosis «giraffe neck», physiological kyphosis «harmonious», enhanced kyphosis «bear withers» and hyperkyphosis «buffalo hump». Increased kyphosis and hyperkyphosis are accompanied by a forward head posture.