High-definition Images Research Articles

Comparison of percutaneous pedicle screw placement under O-arm navigation with traditional percutaneous pedicle screw placement in patients with thoracolumbar fractures without neurological symptoms

Objective: To investigate the accuracy and clinical efficacy of percutaneous pedicle screw placement under O-arm navigation and traditional fluoroscopy in patients with thoracolumbar fractures without neurological symptoms. Methods: From July 2016 to July 2018, 72 patients with thoracolumbar fractures in Peking University International Hospital without neurological symptoms were divided into two groups, group A and group B. In group A, 36 patients underwent the surgery of percutaneous pedicle screw implantation under traditional fluoroscopy and 168 pedicle screws were inserted. In group B, 36 patients underwent the surgery of percutaneous pedicle screw implantation under O-arm guided fluoroscopy and 164 pedicle screws were inserted by the same surgeon. The general condition, operation condition, radiation dose, fluoroscopy time of single screw, screw placement time and accuracy, visual analogue score (VAS) score, Oswestry dysfunction index (ODI), kyphosis Cobb's angle, anterior edge height of 1 week and 6 months after surgery were compared. The data were compared with paired t test between the two groups. Results: There was no significant differences between the two groups in general condition, intraoperative blood loss, length of hospital stay, VAS, ODI, kyphosis Cobb's angle, and anterior edge height of the injured vertebra (all P>0.05). The operation time was (99±14) min in group A and (75±10) min in group B, the average screw setting time was (15.8±2.6) min in group A and (11.8±3.3) min in group B, the fluoroscopy time of each screw was (38.0±2.0) s in group A and (28.5±2.8) s in group B, the radiation dose of each surgery was (563±163) cGy/cm(2) in group A and (378±70) cGy/cm(2) in group B; the above-mentioned data of group A were all superior to those in group B and the differences between the two groups were all statistically significant (t=8.48, 5.73, 16.30, 6.25, all P<0.05). Rampersaud grading in group A was better than group B, and the differences between the two groups was statistically significant(χ(2)=12.2, P<0.05). Conclusion: The O-arm navigation system could not only provide high-definition navigation images and achieve high-precision navigation operations, which is more accurate than traditional pedicle screws placement, but also contribute to the reconstruction of spinal stability and reduce radiation dose, pedicle screws placement and operating time.

High-Definition Optophysical Image Construction Using Mosaics of Pixelated Wrinkles.

Despite many efforts in structuring surfaces using mechanical instabilities, the practical application of these structures to advanced devices remains a challenging task due to the limited capability to control the local morphology. A platform that programs the orientation of mechanically anisotropic molecules is demonstrated; thus, the surface wrinkles, promoted by such instabilities, can be patterned in the desired manner. The optics based on a spatial light modulator assembles wrinkle pixels of a notably small dimension over a large area at fast fabrication speed. Furthermore, these pixelated wrinkles can be formed on curved geometries. The pixelated wrinkles can record images, which are naturally invisible, by mapping the gray level to the orientation of wrinkles. They can retrieve those images using the patterned optical phase retardation generated under the crossed polarizers. As a result, it is shown that the pixelated wrinkles enable new applications in optics such as image storage, informative labeling, and anti‐counterfeiting.

Validation of left ventricular volume and ejection fraction measurements by high-definition blood flow imaging: Comparisons with cardiac magnetic resonance imaging and contrast echocardiography.

We recently reported the efficacy of High-definition blood flow imaging (HDI) in the assessment of left ventricular (LV) function and demonstrated that the results are comparable to those obtained by contrast echocardiography (CE). The present study validates HDI in measurements of LV volumes and ejection fraction (EF) by simultaneous comparisons with CE and cardiac magnetic resonance imaging (CMR). Eighteen patients (age range 25-79years) with limited echocardiographic images had measurements of LV end-diastolic volume (EDV, mL), end-systolic volume (ESV, mL), and EF (%) by HDI, CE, and CMR. Using the three techniques, measurements of EDV, ESV, and EF correlated well with correlation coefficients (r) ranging from .91 to .98 in comparisons between HDI and CMR, and .89 to .97 in comparisons between CE and CMR. The limits of agreement for the inter-methods comparisons by Bland-Altman analysis (mean±1.96 SD) between HDI and CMR were 4.92±16.87% for EF, 21.53±32.18mL for EDV, and 10.69±36.12mL for ESV, between CE and CMR, the agreement limits were 2.48±18.52% (LVEF), 24.58±47.41mL (EDV), and 14.09±43.55mL (ESV). Measurements of LV volumes and EF by HDI and CE correlated well with CMR. Using CMR as the gold standard, the agreements in measurements of LV volumes were superior for HDI compared to CE. In measurements of EF, CE showed less mean difference when compared to HDI. HDI measurements compared well with those obtained by CMR.

Repeatability of Radiomic Features of Brown Adipose Tissue.

The aim of this study was to assess the repeatability of activated brown adipose tissue (BAT) radiomic features. To decipher radiomic features that may provide useful information on BAT, the impact of reconstruction methods and imaging modality choice was also evaluated. Methods: Twenty-seven healthy adults enrolled in this study. After a cooling procedure to activate BAT, volunteers underwent 18F-FDG imaging. Participants underwent repeat imaging using the same imaging protocols and a similar 18F-FDG dose within 14 d. Active BAT was segmented using the BARCIST 1.0 methods. Radiomic features were extracted from each region of interest on high-definition PET (HD PET), non-HD PET, and CT images. Lin's concordance correlation coefficient was used to estimate the repeatability of the extracted radiomic features. To determine whether BAT radiomic feature repeatability correlates with BAT SUVmax repeatability, participants were stratified based on the relative difference in SUVmax between sessions. Non-HD PET repeatable features were clustered together using hierarchical clustering, and the normalized dynamic range of each feature was computed to identify the most informative feature within each cluster. Results: Eighteen of the 27 volunteers had sufficient BAT activity for radiomic analysis. Sixty-six HD PET, 66 non-HD PET, and 6 CT features showed high repeatability (concordance correlation coefficient ≥ 0.80). Feature repeatability was significantly higher for PET than for CT, but there was no statistically significant difference between HD and non-HD PET in radiomic feature repeatability. The repeatability of radiomic features extracted from each modality and reconstruction method type followed the trend in SUVmax, as participants with lower relative differences in SUVmax between initial and repeated imaging sessions had higher radiomic feature repeatability. Hierarchical clustering of the high-repeatability PET features resulted in 10 highly correlated clusters (R2 ≥ 0.95). Seven features, including SUVmax, did not cluster with any other features. Conclusion: Several clusters of highly repeatable BAT radiomic features derived from 18F-FDG PET/CT appear to provide information regarding BAT activity distinct from SUVmax These features might be explored as quantitative imaging biomarkers of BAT activity in future studies.

Combined application of extended depth of field imaging, image stitching and polarized microscopy techniques in identification of Spatholobus suberectus

ObjectiveAs traditional techniques for microscopic identification of Chinese medicines currently lack objective and high-quality reference images, here we developed a systemic procedure to be used in microscopic identification of Chinese medicines, which would lead to more objective, effective and accurate identification process. MethodsSpatholobi Caulis (Jixueteng in Chinese) was used as the specimen in the development of such procedure. Jixueteng samples were microscopically examined in bright- and dark-field microscopy. Microscopic images were obtained by regular, EDF, and image stitching techniques. ResultsThe microscopic images of the characteristics in pulverized Jixueteng were captured, thanks to EDF imaging and image stitching techniques which allowed the detailed and full sighting of each characteristic to be obtained simultaneously. Different layers in anatomical transverse section, including cork, phelloderm, cortex, phloem, cambium, xylem and pith, were distinctively observed. Moreover, by comparing images of bright- and dark-field microscopy, birefringent and non- birefringent components could readily be distinguished. ConclusionWith application of the developed procedure, high-definition, panoramic and microscopic images were acquired, which could be used as the reference images for microscopic identification of Chinese medicines.

Telerobot: Failure Detection Using Imaging Technique for Piping Internal Surfaces

Pipelines are the energy lifelines of almost every activity of everyday life. It is a safe way of transporting water, gas and oil over long distances. It is also the most practical way to deliver oil and gas across countries as being an extremely safe and economically viable solution to transport energy. Cracking and corrosion on the external and/or internal surfaces of in-service pipes, reduces the integrity of the material and potentially reduces the service life of the transportation system and equipment. Defects in pipelines may have various forms and may be initiated by one or more mechanisms potentially resulting in corrosion and/or cracking. In this paper we propose a system that detects the internal cracks in pipelines through a telerobot which can be inserted into the pipelines and detects the internal Failures (cracks) through a special modern high resolution digital camera and image processing techniques. The telerobot is a programmable and can be controlled as per the requirements such as speed and direction of the telerobot and sensors using mobile application and can be connected to a computer and smart phone. The telerobot captures a high definition images and also captures the precise location. These images are transferred to a computing facility for the analyses and to detect cracks.

Development of a high-performance readout circuit for photoelectric detectors

A high-performance readout circuit for photoelectric detectors is developed in this paper to achieve high-speed low-noise image detection. Here, the W/L ratio of the first-stage P-type following transistor is reduced to decrease the parasitic capacitance of buses, and the bias voltage of the P-type following load transistor is minimized to increase the driving current. These changes increase the sampling frequency of the read-out circuit from its original 2 MHz to 6 MHz, thereby effectively improving the readout frequency of the long-line visible light CMOS detector. Four-sampling is used to achieve true correlated double-sampling and reduce the equivalent input noise of the device, thus, overcoming the original circuit’s non-true correlation cancellation. Testing revealed that the number of equivalent input noise electrons of the CMOS detector decreased from 100e to 50e (rms) when the integral time is 200 µs and the photosensitive area is 20 × 18 μm2. The device could work steadily at a sampling rate of 6 MHz, and its linearity and output swing exceed 99% and 2 V, respectively. Moreover, the sensitivity of the detector could meet the requirements of the system. The development of the proposed CMOS detector lays an important theoretical foundation and provides practical value for future research on ultra-high speed and high-definition image detection technologies.

Flounder-Net: An efficient CNN for crowd counting by aerial photography

Crowd counting on aerial images using the embedded system is a challenging task, due to high-definition images, low computing power, and limited memory. To tackle this task, we propose an efficient deep learning model named Flounder-Net structured like a flounder. In the Flounder-Net, a novel interleaved group convolution is proposed to eliminate the redundancy of network, and a rapid shrink of feature maps is employed to tackle the high-resolution problem. Since we would like to investigate the case of online aerial surveillance, we use the embedded system of a drone to run our algorithm. We also use the vision system of this drone to collect a set of high-definition aerial photographs as a benchmark. Extensive experiments on existing datasets and our aerial dataset show that Flounder-Net achieves FCN-level accuracy with three types of photograph devices: handheld cameras, surveillance cameras, and drone-based cameras. Additionally, Flounder-Net has 17× fewer parameters and 20× faster speed than FCN and allows an input image with arbitrary sizes.

Automatic recognition of surface cracks in bridges based on 2D-APES and mobile machine vision

Compared with the artificial crack detection method, the bridge crack recognition method based on computer vision has the advantages of high efficiency, easy operation and low cost. However, under the condition of moving (UAV) shooting, the crack images collected often have quality defects such as low definition, complex background, severe interference by light and noise. Especially when faced with small cracks in early development, some traditional crack detection algorithms with high requirements on crack images cannot be well adapted. In this paper, an automatic recognition technology for surface cracks of bridges is proposed, which is suitable for mobile machine vision detection. The core of the technology is to obtain high-precision two-dimensional spectrum estimation of crack images by using two-dimensional amplitude and phase estimation method (ab. 2D-APES), and then to enhance the crack information by filtering low-frequency information, so as to realize the automatic recognition of crack targets in images. An industrial-grade drone (DJI Jingwei M200V2) equipped with a high-definition zoom image acquisition system was used to acquire images of the bottom and sides of the bridge of the Minpu Bridge in Shanghai. After locating, magnifying and cutting the apparent crack image of concrete, and then using the above method, the crack automatic identification was realized. Results show that the high-precision non-parametric amplitude spectrum analysis method can adapt to the situation of poor image quality of the UAV, and thus provides a feasible solution for the automatic identification of concrete cracks based on mobile machine vision.

High-Quality Transmission of Cardiotocogram and Fetal Information Using a 5G System: Pilot Experiment.

BackgroundA cardiotocogram (CTG) is a device used to perceive the status of a fetus in utero in real time. There are a few reports of its use at home or during emergency transport.ObjectiveThe aim of this study was to test whether CTG and other perinatal information can be transmitted accurately using an experimental station with a 5G transmission system.MethodsIn the research institute, real-time fetal heart rate waveform data from the CTG device, high-definition video ultrasound images of the fetus, and high-definition video taken with a video camera on a single line were transmitted by 5G radio waves from the transmitting station to the receiving station.ResultsAll data were proven to be transmitted with a minimum delay of less than 1 second. The CTG waveform image quality was not inferior, and there was no interruption in transmission. Images of the transmitted ultrasound examination and video movie were fine and smooth.ConclusionsCTG and other information about the fetuses and pregnant women were successfully transmitted by a 5G system. This finding will lead to prompt and accurate medical treatment and improve the prognosis of newborns.

Wind Turbine Blade Defect Image Acquisition System

The detection of wind turbine blades in service is a difficult problem in wind power operation and maintenance. Wind farms in the quality assurance unit and daily inspection, regular detection of blade is with the aid of SLR camera, then the human recognition, low accuracy and low recognition efficiency. This paper puts forward a set wind turbine blade detection method based on based on artificial intelligence image recognition system. With the help of high definition camera array and image recognition software, a large number of image acquisition and rapid recognition processing are carried out for wind turbine blades in service, and finally the automatic detection of blade surface defects is realized. The feasibility and applicability of this method are verified through field detection, which can be promoted in the field of wind power.

Investigation and motion characteristics analysis of dangerous rock in high and steep slope based on UAV

The geological conditions in Southwest China are complex, and the dangerous rock hazards developed in the high and steep slopes has extremely high harmfulness and concealment. The traditional contact survey method is difficult to find out the geological hazard effectively under the limitation of complex and changeable terrain conditions. Unmanned aerial vehicle photogrammetric system has high flexibility and can obtain high-efficient, high precision and high resolution remote sensing images of geological disaster investigation area. By using the UAV photogrammetry system, the dangerous rock mass of the intake slope of Jinping secondary hydropower station is investigated. The working principle of UAV, the acquisition of high-definition image data and the construction of 3D model are discussed, and the feasibility of using the model data obtained by the system to investigate dangerous rock mass is demonstrated. Through repeated analysis and interpretation of the 3D real-scene model, the distribution characteristics of the dangerous rock hazard points of the intake slope are found out. On this basis, four sections are selected to simulate the movement track of unstable dangerous rock mass with Rocfall software, and the movement velocity, jump height and impact energy of different characteristic points of falling rock are calculated quantitatively with the formula.The research results provide an important reference value for the investigation of dangerous rock mass of high and steep slope in southwest China.

Silicon-on-insulator based multifunctional metasurface with simultaneous polarization and geometric phase controls.

Enabled with both magnetic resonance and geometric phase, dielectric nanobrick based metasurfaces have shown their unusual abilities to produce high-definition and high-efficiency holographic images. Herein, we further show that such a metasurface can not only project a holographic image in far field but also record a grayscale image right at the metasurface plane simultaneously, merely with a single-celled nanostructure design approach. Specifically, each nanobrick in a unit-cell of the metasurface acts as a half-wave plate and it can continuously rotate the polarization direction of incident linearly polarized light. Governed by Malus law, light intensity modulation is available with the help of a bulk-optic analyzer and a continuous grayscale image appears right at the metasurface plane. At the same time, the concept of orientation degeneracy of nanostructures can be utilized to generate a 4-step geometric phase, with which a holographic image is reconstructed in far field. We experimentally demonstrate this multifunctional meta-device by employing the widely used silicon-on-insulator (SOI) material and all results agree well with our theoretical prediction. With the novel features of easiness in design, high efficiency, broadband spectrum response, strong robustness, high security and high information density, the proposed SOI-based metasurfaces will have extensive applications in optical information security and multiplexing.

The XFM beamline at the Australian Synchrotron.

The X-ray fluorescence microscopy (XFM) beamline is an in-vacuum undulator-based X-ray fluorescence (XRF) microprobe beamline at the 3 GeV Australian Synchrotron. The beamline delivers hard X-rays in the 4-27 keV energy range, permitting K emission to Cd and L and M emission for all other heavier elements. With a practical low-energy detection cut-off of approximately 1.5 keV, low-Z detection is constrained to Si, with Al detectable under favourable circumstances. The beamline has two scanning stations: a Kirkpatrick-Baez mirror microprobe, which produces a focal spot of 2 µm × 2 µm FWHM, and a large-area scanning `milliprobe', which has the beam size defined by slits. Energy-dispersive detector systems include the Maia 384, Vortex-EM and Vortex-ME3 for XRF measurement, and the EIGER2 X 1 Mpixel array detector for scanning X-ray diffraction microscopy measurements. The beamline uses event-mode data acquisition that eliminates detector system time overheads, and motion control overheads are significantly reduced through the application of an efficient raster scanning algorithm. The minimal overheads, in conjunction with short dwell times per pixel, have allowed XFM to establish techniques such as full spectroscopic XANES fluorescence imaging, XRF tomography, fly scanning ptychography and high-definition XRF imaging over large areas. XFM provides diverse analysis capabilities in the fields of medicine, biology, geology, materials science and cultural heritage. This paper discusses the beamline status, scientific showcases and future upgrades.

Virtual audits of the urban streetscape: comparing the inter-rater reliability of GigaPan\xae to Google Street View

BackgroundAlthough previous research has highlighted the association between the built environment and individual health, methodological challenges in assessing the built environment remain. In particular, many researchers have demonstrated the high inter-rater reliability of assessing large or objective built environment features and the low inter-rater reliability of assessing small or subjective built environment features using Google Street View. New methods for auditing the built environment must be evaluated to understand if there are alternative tools through which researchers can assess all types of built environment features with high agreement. This paper investigates measures of inter-rater reliability of GigaPan®, a tool that assists with capturing high-definition panoramic images, relative to Google Street View.MethodsStreet segments (n = 614) in Pittsburgh, Pennsylvania in the United States were randomly selected to audit using GigaPan® and Google Street View. Each audit assessed features related to land use, traffic and safety, and public amenities. Inter-rater reliability statistics, including percent agreement, Cohen’s kappa, and the prevalence-adjusted bias-adjusted kappa (PABAK) were calculated for 106 street segments that were coded by two, different, human auditors.ResultsMost large-scale, objective features (e.g. bus stop presence or stop sign presence) demonstrated at least substantial inter-rater reliability for both methods, but significant differences emerged across finely detailed features (e.g. trash) and features at segment endpoints (e.g. sidewalk continuity). After adjusting for the effects of bias and prevalence, the inter-rater reliability estimates were consistently higher for almost all built environment features across GigaPan® and Google Street View.ConclusionGigaPan® is a reliable, alternative audit tool to Google Street View for studying the built environment. GigaPan® may be particularly well-suited for built environment projects with study settings in areas where Google Street View imagery is nonexistent or updated infrequently. The potential for enhanced, detailed imagery using GigaPan® will be most beneficial in studies in which current, time sensitive data are needed or microscale built environment features would be challenging to see in Google Street View. Furthermore, to better understand the effects of prevalence and bias in future reliability studies, researchers should consider using PABAK to supplement or expand upon Cohen’s kappa findings.

Peroral Cholangioscopy: How Technology and Imaging Have Changed ERCP.

Endoscopic retrograde cholangiopancreatography (ERCP) is the minimally invasive standard of care for the treatment of several biliary and pancreatic pathologies. One of the limitations of this technique is the lack of endoluminal vision within the biliary tree or Wirsung's duct. This limits the diagnostic accuracy of the procedure and reduces the effectiveness of many treatments. Technological progress and the use of increasingly ergonomic and high-definition imaging equipment have led to the dissemination of peroral cholangioscopy (POC). Thanks to the high quality of video image resolution, POC could well be a powerful tool used to characterize malignant biliary strictures. It could also allow targeted biopsies or local treatments, hence reducing the risk of complications and increasing outcomes. The technological improvement of the last generation of POC is opening new horizons in the treatment of biliopancreatic pathologies, thereby contributing to refine and enhance the ERCP management of several diseases in the near future.

Anatomical observation and clinical significance of rectosacral fascia in total mesorectal resection

Objective: To observe the anatomical architecture of rectosacral fascia and discuss the best plan for accurate peri-rectal dissection in laparoscopic/robotic total mesorectal resection (TME). Methods: A descriptive cohort study was carried out. A total of 127 patients with rectal cancer who underwent TME in the Department of Colorectal Surgery at the affiliated Union hospital of Fujian Medical University were included, patients' demographics with their pathological details and operation videos were collected for analysis. Another 20 high-definition images of post-TME surgical specimens were collected from our digital database. A total of 28 cadaveric models were examined at the Laboratory of Clinical Applied Anatomy, Fujian Medical University, to observe the anatomical details of rectosacral fascia. Results: (1) Anatomical observation showed that the pre-hypogastric fascia attaches to the proper fascia of the mesorectum in a horizontal arc posteriorly, forming the rectosacral fascia. If this fusion couldn't be identified and appropriately transected during posterior space dissection, it would be easy to destroy the proper fascia and dissect through the mesorectum resulting in residual mesorectum tissue. After the fascia transaction, the proper fascia of the mesorectum is still intact distally. The upper part of rectosacral fascia bilaterally re-separated again into the proper fascia and pre-hypogastric fascia. The pre-hypogastric fascia acts as a "fascia barrier" when dissecting the lateral space constantly from posterior to anterior. The right attachment of the rectosacral fascia was gradually transected. The pelvic plexus from the right S2-S4 was covered by the pre-hypogastric fascia which is considered the outer side layer of rectosacral fascia laterally. It was observed that the fascia continued with the anterior layer of the Denonvilliers' fascia, which has been transected during anterior space dissection. The proper fascia, which is the inner side layer of rectosacral fascia laterally, was still intact. The edge of the right rectosacral fascia attachment ran obliquely from the back and upward into the front direction. The left extension was similar to the right. (2) Cadaveric specimens: at the level of the lower edge of S4 vertebral body, the pre-hypogastric fascia fused with the proper fascia to form the rectosacral fascia. The right attachment margin of the rectosacral fascia was cut off step by step. The attachment margin of the rectosacral fascia went from the back and upward to the front downward direction. The right edge of rectosacral fascia attachment continued with the anterior layer of the Denonvilliers' fascia at the pre-rectal space and attached to the pre-hypogastric fascia laterally. The pelvic plexus sends out many tiny rectal branches on the anterolateral side, which pass through the transitional area between pre-hypogastric fascia and the anterior layer of the Denonvilliers' fascia to innervate the rectum. (3) TME specimens observation: the posterior attachment of rectosacral fascia was curved around the mesorectum with bilateral oblique attachments. The mesorectum was covered by fusion fascia below the posterior and bilateral attachment margin while it was covered only by the proper fascia above it. Conclusion: according to the morphological characteristics of rectosacral fascia, the rectosacral fascia should be dissected at the level of S4 vertebral body posterior to the rectum in an arc, shape and then enter the superior-levator space. Before dissecting the bilateral spaces, the anterior space of the rectum should be dissected first. The anterior layer of the Denonvilliers' fascia should be cut off into an inverted "U" shape, and then the lateral space should be dissected from anterior to posterior. Finally, the lateral attachment of rectosacral fascia was transected to ensure the integrity of the mesorectum without damaging the pelvic plexus branches and NVB.

Conglomerate petrology characterization using high-definition borehole electrical images in the Upper Urho Formation at well JL42, Zhongguai Uplift, Junggar Basin, China

Cores drilled from wells are significant resources for understanding the geologic characteristics of petroleum reservoirs. However, due to the high cost and long rig time involved, it is impossible to obtain cores from the entire sedimentary formation in a drilling well. Furthermore, core breakage limits the amount of information that can be obtained in the vertical deposition environment of deep-buried formations. Therefore, we have used ultrahigh-resolution and high-quality borehole electrical images obtained by a borehole electrical imaging tool, High-Definition Formation MicroImager (FMI-HD), to supplement “core” information and characterize the petrologic features, such as grain size and sedimentary structure, of conglomeratic formations in the Permian Upper Urho Formation at well JL42, Zhongguai Uplift, Junggar Basin, China. We have observed conglomeratic cores at 95.92 m in well JL42 and recorded various petrologic features of the core cylinders. In the cored interval, the FMI-HD images were compared with core photos in detail; grain size results from the FMI-HD images and cores were very similar. However, there were major differences in the structural results due to core interruption. In addition, the high-resolution depositional facies of the Upper Urho Formation at well JL42 were dissected in terms of the distributive fluvial system, not the fan-delta system, using vertical grain size features derived from FMI-HD images. Boulders, cobbles, coarse pebbles, and fine pebbles were developed in thick gravelly channels in the lower proximal facies, whereas fine pebbles and granules were developed in thin channels in the upper medial facies. Therefore, FMI-HD images can be efficiently used to supplement cores and sedimentary information, which provides important insights on the paleogeology of conglomeratic formations and in turn on the exploration potential of petroleum systems.

The application of deep learning based diagnostic system to cervical squamous intraepithelial lesions recognition in colposcopy images

Background Deep learning has presented considerable potential and is gaining more importance in computer assisted diagnosis. As the gold standard for pathologically diagnosing cervical intraepithelial lesions and invasive cervical cancer, colposcopy-guided biopsy faces challenges in improving accuracy and efficiency worldwide, especially in developing countries. To ease the heavy burden of cervical cancer screening, it is urgent to establish a scientific, accurate and efficient method for assisting diagnosis and biopsy. Methods The data were collected to establish three deep-learning-based models. For every case, one saline image, one acetic image, one iodine image and the corresponding clinical information, including age, the results of human papillomavirus testing and cytology, type of transformation zone, and pathologic diagnosis, were collected. The dataset was proportionally divided into three subsets including the training set, the test set and the validation set, at a ratio of 8:1:1. The validation set was used to evaluate model performance. After model establishment, an independent dataset of high-definition images was collected to further evaluate the model performance. In addition, the comparison of diagnostic accuracy between colposcopists and models weas performed. Results The sensitivity, specificity and accuracy of the classification model to differentiate negative cases from positive cases were 85.38%, 82.62% and 84.10% respectively, with an AUC of 0.93. The recall and DICE of the segmentation model to segment suspicious lesions in acetic images were 84.73% and 61.64%, with an average accuracy of 95.59%. Furthermore, 84.67% of high-grade lesions were detected by the acetic detection model. Compared to colposcopists, the diagnostic system performed better in ordinary colposcopy images but slightly unsatisfactory in high-definition images. Implications The deep learning-based diagnostic system could help assist colposcopy diagnosis and biopsy for HSILs.

Experimental Demonstration of an Anti-Shake Hyperspectral Imager of High Spatial Resolution and Low Cost

Environmental and internal factors can degrade the performance of a traditional hyperspectral imager. Here, we combine a self-developed hyperspectral imager with a calibration camera to improve its performance with our algorithm. The calibration camera is utilized to reduce the effect of the camera shake and provide high-definition splicing image in hyperspectral cube. The spectrum in the hyperspectral cube is provided by the hyperspectral imager. It can obtain high-definition images in hand-held or UAV scanning modes. In our experiment, the horizontal resolution of the image with calibration is improved from 9.7 mm to 1 mm, and the vertical spatial resolution is improved from 1 mm to 0.5 mm. Additionally, by using “Structure from Motion with Multi-View Stereo” (SfM-MVS), the system can carry out three-dimensional reconstruction. The images are fused together and transformed into a multi-dimensional image with depth and spectrum. Our experiments show that it can be used in environmental monitoring and face Anti-spoofing. Our system is highly stable and performs well when mounted on a UAV (without any gimbal) for remote sensing. The low complexity and low cost open possibilities for large-scale on-site and distributed hyperspectral imaging.