MRI-Based Radiomics Analysis of Levator Ani Muscle for Predicting Urine Incontinence after Robot-Assisted Radical Prostatectomy.

BACKGROUND: The exact role of the levator ani (LA) muscle in male continence remains unclear, and so this study aims to shed light on the topic by characterizing MRI-derived radiomic features of LA muscle and their association with postoperative incontinence in men undergoing prostatectomy. METHOD: In this retrospective study, 140 patients who underwent robot-assisted radical prostatectomy (RARP) for prostate cancer using preoperative MRI were identified. A biomarker discovery approach based on the optimal biomarker (OBM) method was used to extract features from MRI images, including morphological, intensity-based, and texture-based features of the LA muscle, along with clinical variables. Mathematical models were created using subsets of features and were evaluated based on their ability to predict continence outcomes. RESULTS: Univariate analysis showed that the best discriminators between continent and incontinent patients were patients age and features related to LA muscle texture. The proposed feature selection approach found that the best classifier used six features: age, LA muscle texture properties, and the ratio between LA size descriptors. This configuration produced a classification accuracy of 0.84 with a sensitivity of 0.90, specificity of 0.75, and an area under the ROC curve of 0.89. CONCLUSION: This study found that certain patient factors, such as increased age and specific texture properties of the LA muscle, can increase the odds of incontinence after RARP. The results showed that the proposed approach was highly effective and could distinguish and predict continents from incontinent patients with high accuracy.

Periprostatic Adipose Tissue MRI Radiomics-Derived Features Associated with Clinically Significant Prostate Cancer.

Background: Altered systemic and cellular lipid metabolism plays a pivotal role in the pathogenesis of prostate cancer (PCa). In this study, we aimed to characterize T1-magnetic resonance imaging (MRI)-derived radiomic parameters of periprostatic adipose tissue (PPAT) associated with clinically significant PCa (Gleason score ≥7 [3 + 4]) in a cohort of men who underwent robot-assisted prostatectomy. Methods: Preoperative MRI scans of 98 patients were identified. The volume of interest was defined by identifying an annular shell-like region on each MRI slice to include all surgically resectable visceral adipose tissue. An optimal biomarker method was used to identify features from 7631 intensity- and texture-based properties that maximized the classification of patients into clinically significant PCa and indolent tumors at the final pathology analysis. Results: Six highest ranked optimal features were derived, which demonstrated a sensitivity, specificity, and accuracy of association with the presence of clinically significant PCa, and area under a receiver operating characteristic curve of 0.95, 0.39 0.82, and 0.82, respectively. Conclusion: A highly independent set of PPAT features derived from MRI scans that predict patients with clinically significant PCa was developed and tested. With future external validation, these features may provide a more precise scientific basis for deciding to omit biopsies in patients with borderline prostate-specific antigen kinetics and multiparametric MRI readings and help in the decision of enrolling patients into active surveillance.

Satellite imagery dataset of manure application on pasture fields.

Applying manure to pasture fields is a very common method of fertilization. However, rainfall can cause the manure to leach into water bodies near the field, contaminating the water and damaging the environment and the animals living in it, ultimately affecting human life. This paper presents a dataset consisting of images of 30 plots after manure application, verified by on-site investigations. This involved visiting 38 different plots, of which 8 were discarded because they were not suitable, either because of their small size, the lack of a specific manure application date, or the images being too cloudy in that period. The imagery is collected through Google Earth Engine using the satellite Sentinel-2, which offers 13 hyperspectral bands in the range of ultraviolet and near-infrared wavelengths including the visible spectrum. From these 13 bands, the most common hyperspectral indices in the literature for precision agriculture are calculated and added into the images as channels. 51 hyperspectral indices are calculated, summing up to a total of 64 channels per image when adding the raw bands from Sentinel-2. No normalization has been performed on any of the channels. The data can be used for further research of automatic classification of manure application to control its use and prevent contamination.

Evaluation of Dust Deposition on Parabolic Trough Collectors in the Visible and Infrared Spectrum.

Solar energy is mostly harnessed in arid areas where a high concentration of atmospheric dust represents a major environmental degradation factor. Gravitationally settled particles and other solid particles on the surface of the photovoltaic panels or thermal collectors greatly reduce the absorbed solar energy. Therefore, frequent cleaning schedules are required, consuming high quantities of water in regions where water precipitation is rare. The efficiency of this cleaning maintenance is greatly improved when methods to estimate the degree of cleanness are introduced. This work focuses on the need for better detecting the degradation created by dust deposition, considering experimental data based on different air pollutants, and analyzing the resulting thermal and visible signatures under different operating environments. Experiments are performed using six different types of pollutants applied to the surface of parabolic trough collectors while varying the pollutant density. The resulting reflectivity in the visible and infrared spectrum is calculated and compared. Results indicate that the pollutants can be distinguished, although the reflectivity greatly depends on the combination of the particle size of the pollutant and the applied amount, with greater impact from pollutants with small particles.

Surface Defect System for Long Product Manufacturing Using Differential Topographic Images.

Current industrial products must meet quality requirements defined by international standards. Most commercial surface inspection systems give qualitative detections after a long, cumbersome and very expensive configuration process made by the seller company. In this paper, a new surface defect detection method is proposed based on 3D laser reconstruction. The method compares the long products, scan by scan, with their desired shape and produces differential topographic images of the surface at very high speeds. This work proposes a novel method where the values of the pixels in the images have a direct translation to real-world dimensions, which enables a detection based on the tolerances defined by international standards. These images are processed using computer vision techniques to detect defects and filter erroneous detections using both statistical distributions and a multilayer perceptron. Moreover, a systematic configuration procedure is proposed that is repeatable and can be performed by the manufacturer. The method has been tested using train track rails, which reports better results than two photometric systems including one commercial system, in both defect detection and erroneous detection rate. The method has been validated using a surface inspection rail pattern showing excellent performance.

Nondestructive Evaluation of Carbon Fiber Bicycle Frames Using Infrared Thermography.

Bicycle frames made of carbon fibre are extremely popular for high-performance cycling due to the stiffness-to-weight ratio, which enables greater power transfer. However, products manufactured using carbon fibre are sensitive to impact damage. Therefore, intelligent nondestructive evaluation is a required step to prevent failures and ensure a secure usage of the bicycle. This work proposes an inspection method based on active thermography, a proven technique successfully applied to other materials. Different configurations for the inspection are tested, including power and heating time. Moreover, experiments are applied to a real bicycle frame with generated impact damage of different energies. Tests show excellent results, detecting the generated damage during the inspection. When the results are combined with advanced image post-processing methods, the SNR is greatly increased, and the size and localization of the defects are clearly visible in the images.

Infrared Thermography Sensor for Temperature and Speed Measurement of Moving Material.

Infrared thermography offers significant advantages in monitoring the temperature of objects over time, but crucial aspects need to be addressed. Movements between the infrared camera and the inspected material seriously affect the accuracy of the calculated temperature. These movements can be the consequence of solid objects that are moved, molten metal poured, material on a conveyor belt, or just vibrations. This work proposes a solution for monitoring the temperature of material in these scenarios. In this work both real movements and vibrations are treated equally, proposing a unified solution for both problems. The three key steps of the proposed procedure are image rectification, motion estimation and motion compensation. Image rectification calculates a front-parallel projection of the image that simplifies the estimation and compensation of the movement. Motion estimation describes the movement using a mathematical model, and estimates the coefficients using robust methods adapted to infrared images. Motion is finally compensated for in order to produce the correct temperature time history of the monitored material regardless of the movement. The result is a robust sensor for temperature of moving material that can also be used to measure the speed of the material. Different experiments are carried out to validate the proposed method in laboratory and real environments. Results show excellent performance.

Driver Distraction Using Visual-Based Sensors and Algorithms.

Driver distraction, defined as the diversion of attention away from activities critical for safe driving toward a competing activity, is increasingly recognized as a significant source of injuries and fatalities on the roadway. Additionally, the trend towards increasing the use of in-vehicle information systems is critical because they induce visual, biomechanical and cognitive distraction and may affect driving performance in qualitatively different ways. Non-intrusive methods are strongly preferred for monitoring distraction, and vision-based systems have appeared to be attractive for both drivers and researchers. Biomechanical, visual and cognitive distractions are the most commonly detected types in video-based algorithms. Many distraction detection systems only use a single visual cue and therefore, they may be easily disturbed when occlusion or illumination changes appear. Moreover, the combination of these visual cues is a key and challenging aspect in the development of robust distraction detection systems. These visual cues can be extracted mainly by using face monitoring systems but they should be completed with more visual cues (e.g., hands or body information) or even, distraction detection from specific actions (e.g., phone usage). Additionally, these algorithms should be included in an embedded device or system inside a car. This is not a trivial task and several requirements must be taken into account: reliability, real-time performance, low cost, small size, low power consumption, flexibility and short time-to-market. The key points for the development and implementation of sensors to carry out the detection of distraction will also be reviewed. This paper shows a review of the role of computer vision technology applied to the development of monitoring systems to detect distraction. Some key points considered as both future work and challenges ahead yet to be solved will also be addressed.

Robot Guidance Using Machine Vision Techniques in Industrial Environments: A Comparative Review.

In the factory of the future, most of the operations will be done by autonomous robots that need visual feedback to move around the working space avoiding obstacles, to work collaboratively with humans, to identify and locate the working parts, to complete the information provided by other sensors to improve their positioning accuracy, etc. Different vision techniques, such as photogrammetry, stereo vision, structured light, time of flight and laser triangulation, among others, are widely used for inspection and quality control processes in the industry and now for robot guidance. Choosing which type of vision system to use is highly dependent on the parts that need to be located or measured. Thus, in this paper a comparative review of different machine vision techniques for robot guidance is presented. This work analyzes accuracy, range and weight of the sensors, safety, processing time and environmental influences. Researchers and developers can take it as a background information for their future works.

Structured-light sensor using two laser stripes for 3D reconstruction without vibrations.

3D reconstruction based on laser light projection is a well-known method that generally provides accurate results. However, when this method is used for inspection in uncontrolled environments, it is greatly affected by vibrations. This paper presents a structured-light sensor based on two laser stripes that provides a 3D reconstruction without vibrations. Using more than one laser stripe provides redundant information than is used to compensate for the vibrations. This work also proposes an accurate calibration process for the sensor based on standard calibration plates. A series of experiments are performed to evaluate the proposed method using a mechanical device that simulates vibrations. Results show excellent performance, with very good accuracy.

Infrared thermography for temperature measurement and non-destructive testing.

The intensity of the infrared radiation emitted by objects is mainly a function of their temperature. In infrared thermography, this feature is used for multiple purposes: as a health indicator in medical applications, as a sign of malfunction in mechanical and electrical maintenance or as an indicator of heat loss in buildings. This paper presents a review of infrared thermography especially focused on two applications: temperature measurement and non-destructive testing, two of the main fields where infrared thermography-based sensors are used. A general introduction to infrared thermography and the common procedures for temperature measurement and non-destructive testing are presented. Furthermore, developments in these fields and recent advances are reviewed.

On-line flatness measurement in the steelmaking industry.

Shape is a key characteristic to determine the quality of outgoing flat-rolled products in the steel industry. It is greatly influenced by flatness, a feature to describe how the surface of a rolled product approaches a plane. Flatness is of the utmost importance in steelmaking, since it is used by most downstream processes and customers for the acceptance or rejection of rolled products. Flatness sensors compute flatness measurements based on comparing the length of several longitudinal fibers of the surface of the product under inspection. Two main different approaches are commonly used. On the one hand, most mechanical sensors measure the tensile stress across the width of the rolled product, while manufacturing and estimating the fiber lengths from this stress. On the other hand, optical sensors measure the length of the fibers by means of light patterns projected onto the product surface. In this paper, we review the techniques and the main sensors used in the steelmaking industry to measure and quantify flatness defects in steel plates, sheets and strips. Most of these techniques and sensors can be used in other industries involving rolling mills or continuous production lines, such as aluminum, copper and paper, to name a few. Encompassed in the special issue, State-of-the-Art Sensors Technology in Spain 2013, this paper also reviews the most important flatness sensors designed and developed for the steelmaking industry in Spain.

Monitoring sintering burn-through point using infrared thermography.

Sintering is a complex industrial process that applies heat to fine particles of iron ore and other materials to produce sinter, a solidified porous material used in blast furnaces. The sintering process needs to be carefully adjusted, so that the combustion zone reaches the bottom of the material just before the discharge end. This is known as the burn-through point. Many different parameters need to be finely tuned, including the speed and the quantities of the materials mixed. However, in order to achieve good results, sintering control requires precise feedback to adjust these parameters. This work presents a sensor to monitor the sintering burn-through point based on infrared thermography. The proposed procedure is based on the acquisition of infrared images at the end of the sintering process. At this position, infrared images contain the cross-section temperatures of the mixture. The objective of this work is to process this information to extract relevant features about the sintering process. The proposed procedure is based on four steps: key frame detection, region of interest detection, segmentation and feature extraction. The results indicate that the proposed procedure is very robust and reliable, providing features that can be used effectively to control the sintering process.

Vision-based sensor for early detection of periodical defects in web materials.

During the production of web materials such as plastic, textiles or metal, where there are rolls involved in the production process, periodically generated defects may occur. If one of these rolls has some kind of flaw, it can generate a defect on the material surface each time it completes a full turn. This can cause the generation of a large number of surface defects, greatly degrading the product quality. For this reason, it is necessary to have a system that can detect these situations as soon as possible. This paper presents a vision-based sensor for the early detection of this kind of defects. It can be adapted to be used in the inspection of any web material, even when the input data are very noisy. To assess its performance, the sensor system was used to detect periodical defects in hot steel strips. A total of 36 strips produced in ArcelorMittal Avilés factory were used for this purpose, 18 to determine the optimal configuration of the proposed sensor using a full-factorial experimental design and the other 18 to verify the validity of the results. Next, they were compared with those provided by a commercial system used worldwide, showing a clear improvement.