Non-descent vaginal hysterectomy surgery associated with less complications and good prognosis

Background: Removal of the uterus through vagina when performed in a case without uterine descent or prolapse is known as “non-descent vaginal hysterectomy” or NDVH. Vaginal route is preferred as compared to laparoscopic and abdominal methods. The advantages of vaginal hysterectomy being fewer complications, less post-operative stay, cost effective, and useful in bulky uterus. Aims and Objectives: The aims of the study were as follows: (1) To study the intraoperative and post-operative complications encountered during NDVH and their management. (2) To assess the intraoperative blood loss, the operative time, and post-operative hospital stay. (3) To study and check the feasibility of vaginal route as the primary route for all hysterectomies in the absence of uterine prolapse. Materials and Methods: A total of 50 patients were included in the study. Detailed history was taken including obstetric history and menstrual history and clinical examination was performed. After taking written, informed consent and doing proper pre-operative preparation, the patient was posted for NDVH. Post-operative complications were noted. Patients were asked to come for follow-up after 15 days. Results: In 92% of cases operated, no intraoperative complications were found suggesting low morbidity associated with the procedure. Hemorrhage requiring blood transfusion was found in 4% of cases. Average operative time was 61.2 ± 27.89 min, average blood loss was 170 ± 81.44 ml, and average hospital stay was 5.94 ± 4.95 days. On histopathological examination, 40% were having leiomyoma and dysfunctional uterine bleeding was seen in 22% of cases. Pain was the most common complication seen in 30% of cases while vaginal discharge was seen in just 4% of cases. About 80% of patients were discharged on post-operative day 5. Conclusion: In 92% of NDVH cases, no intraoperative complications were found suggesting low morbidity associated with the procedure. The post-operative hospital stay was restricted to 5 days in 80% of cases which indicates early discharge of the patient. Post-operative complications such as vaginal discharge and fever were seen only in 4% of cases. NDVH should, therefore, be considered as the primary route for all hysterectomies unless contraindicated in the absence of prolapse.

HyperSeed: An End-to-End Method to Process Hyperspectral Images of Seeds

High-throughput, nondestructive, and precise measurement of seeds is critical for the evaluation of seed quality and the improvement of agricultural productions. To this end, we have developed a novel end-to-end platform named HyperSeed to provide hyperspectral information for seeds. As a test case, the hyperspectral images of rice seeds are obtained from a high-performance line-scan image spectrograph covering the spectral range from 600 to 1700 nm. The acquired images are processed via a graphical user interface (GUI)-based open-source software for background removal and seed segmentation. The output is generated in the form of a hyperspectral cube and curve for each seed. In our experiment, we presented the visual results of seed segmentation on different seed species. Moreover, we conducted a classification of seeds raised in heat stress and control environments using both traditional machine learning models and neural network models. The results show that the proposed 3D convolutional neural network (3D CNN) model has the highest accuracy, which is 97.5% in seed-based classification and 94.21% in pixel-based classification, compared to 80.0% in seed-based classification and 85.67% in seed-based classification from the support vector machine (SVM) model. Moreover, our pipeline enables systematic analysis of spectral curves and identification of wavelengths of biological interest.

Establishment of a simple method to evaluate mixing times in a plastic bag photobioreactor using image processing based on freeware tools

Objective Accurate determination of the mixing time in bioreactors is essential for the optimization of the productivity of bioprocesses. The aim of this work was to develop a simple optical method to determine the mixing time in a photobioreactor. The image processing method should be based on freeware tools, should not require programming skills, and thus could be used in education within high schools and in early stages of undergraduate programs. Results An optical method has been established to analyze images from recorded videos of mixing experiments. The steps are: 1. Extraction of a sequence of images from the video file; 2. Cropping of the pictures; 3. Background removal; and 4. Image analysis and mixing time evaluation based on quantification of pixel-to-pixel heterogeneity within a given area of interest. The novel method was generally able to track the dependency between aeration rate and mixing time within the investigated photobioreactor. In direct comparison, a pearson correlation coefficient of rho = 0.99 was obtained. Gas flow rates between 10 L h−1, and 300 L h−1 resulted from mixing times of between 48 and 14 s, respectively. This technique is applicable without programming skills and can be used in education with inexperienced user groups.

Defects Detection Algorithm of Harumanis Mango for Quality Assessment Using Colour Features Extraction

Visual defects detection is one of the main problems in the post-harvest processing caused a major production and economic losses in agricultural industry. Manual fruits detection become easy when it is done in small amount, but the result is not consistent which will generate issue in fruit grading. A new fruit quality assessment system is necessary in order to increase the accuracy of classification, more consistencies, efficient and cost effective that would enable the industry to grow accordingly. In this paper, a method based on colour feature extraction for the quality assessment of Harumanis mango is proposed and experimentally validated. This method, including image background removal, defects segmentation and recognition and finally quality classification using Support Vector Machine (SVM) was developed. The results show that the experimental hardware system is practical and feasible, and that the proposed algorithm of defects detection is effective.

Out of the Blue and into the Black: Preparation, Mounting, and Image Rendering of Complex, Chorate Dinoflagellate Cysts for Scanning Electron Microscopy

We describe an experimental approach for achieving an optimal black background for scanning electron photomicrographs of small samples with elaborate and intricate structures. Specimens of the highly ornate, 66-million-year-old chorate dinoflagellate cyst species Cannosphaeropsis franciscana were selected as the subject of this study. Photomicrographs collected following standard aluminum stub surface placement were compared to those taken of specimens mounted using a novel pin-and-pedestal method. This simplistic mounting technique minimizes the need for post-production image editing and extraneous background removal.

A Data-Centric Approach to Design and Analysis of a Surface-Inspection System Based on Deep Learning in the Plastic Injection Molding Industry

Manufacturers are eager to replace the human inspector with automatic inspection systems to improve the competitive advantage by means of quality. However, some manufacturers have failed to apply the traditional vision system because of constraints in data acquisition and feature extraction. In this paper, we propose an inspection system based on deep learning for a tampon applicator producer that uses the applicator’s structural characteristics for data acquisition and uses state-of-the-art models for object detection and instance segmentation, YOLOv4 and YOLACT for feature extraction, respectively. During the on-site trial test, we experienced some False-Positive (FP) cases and found a possible Type I error. We used a data-centric approach to solve the problem by using two different data pre-processing methods, the Background Removal (BR) and Contrast Limited Adaptive Histogram Equalization (CLAHE). We have experimented with analyzing the effect of the methods on the inspection with the self-created dataset. We found that CLAHE increased Recall by 0.1 at the image level, and both CLAHE and BR improved Precision by 0.04–0.06 at the bounding box level. These results support that the data-centric approach might improve the detection rate. However, the data pre-processing techniques deteriorated the metrics used to measure the overall performance, such as F1-score and Average Precision (AP), even though we empirically confirmed that the malfunctions improved. With the detailed analysis of the result, we have found some cases that revealed the ambiguity of the decisions caused by the inconsistency in data annotation. Our research alerts AI practitioners that validating the model based only on the metrics may lead to a wrong conclusion.

Establishment of a simple method to evaluate mixing times in a plastic bag photobioreactor using image processing based on freeware tools

Objective The aim of this work was to develop a simple optical method to determine the mixing time in a photobioreactor. The image processing method should be based on freeware tools and should not require programming skills. Results An optical method has been established to analyze images from recorded videos of mixing experiments. The basic steps are: 1. Extraction of a sequence of images from the video file; 2. Cropping of the pictures; 3. Background removal; and 4. Image analysis and mixing time evaluation based on quantification of pixel-to-pixel heterogeneity (standard deviation over pixel intensities) within a given area of interest. The novel method was generally able to track the dependency between aeration rate and mixing time within the investigated photobioreactor. In a direct comparison, a Pearson correlation coefficient of rho = 0.9957 was obtained. Gas flow rates between 10 L h−1, and 300 L h−1 resulted from mixing times of between 48 sec and 14 sec, respectively. This simple technique is applicable even without programming skills and can be used in education within high schools and in early stages of undergraduate programs.

Signal-to-Noise Ratio Enhancement by Accumulation of Signal and Noise along the Spectrum

This work presents a method for background removal and signal-to-noise ratio enhancement by an accumulation of signal and noise along analyzed spectrum. In this case, the signals are accumulated, and noise, due to its chaotic nature, is suppressed. The method is applied to analyze spectra obtained on DRON-6 diffractometer for study of the crystal structure of thin tin dioxide films produced by sol–gel technology and deposited on a glass substrate. The standard analysis of the crystallographic planes of the samples under study is practically impossible due to the high noise level and the negative influence of the background from the glass substrate. The proposed method transformed the initial spectrum, which cannot be analyzed, into an informative spectrum: the background signal from the substrate is correctly subtracted and the noise decreases by 10 times. To check for possible signal distortion due to accumulation signal along the spectrum, an analysis of simulated spectra was carried out. The onset of the transition of an amorphous state to a crystalline structure of SnO2 is investigated. The crystalline structure of SnO2 thin films depending on the annealing temperature is studied.

Multi-camera object tracking system

The article proposes a multi-camera tracking system for an object, implemented using computer vision technologies and allowing the video surveillance operator in real time to select an object that will be monitored by the system in future. It will be ready to give out the location of the object at any time. The solution to this problem is divided into three main stages: the detection stage, the tracking stage and the stage of interaction of several cameras. Methods of detection, tracking of objects and the interaction of several cameras have been investigated. To solve the problem of detection, the method of optical flow and the method of removing the background were investigated, to solve the problem of tracking — the method of matching key points and the correlation method, to solve the problem of interaction between several surveillance cameras — the method of the topological graph of a network of cameras. An approach is proposed for constructing a system that uses a combination of the background removal method, the correlation method and the method of the topological graph of a network of cameras. The stages of detection and tracking have been experimentally implemented, that is, the task of tracking an object within the coverage area of one video camera has been solved. The implemented system showed good results: a sufficiently high speed and accuracy with rare losses of the tracked object and with a slight decrease in the frame rate.

Dynamic Hand Gesture Recognition in In-Vehicle Environment Based on FMCW Radar and Transformer

Hand gesture recognition technology plays an important role in human-computer interaction and in-vehicle entertainment. Under in-vehicle conditions, it is a great challenge to design gesture recognition systems due to variable driving conditions, complex backgrounds, and diversified gestures. In this paper, we propose a gesture recognition system based on frequency-modulated continuous-wave (FMCW) radar and transformer for an in-vehicle environment. Firstly, the original range-Doppler maps (RDMs), range-azimuth maps (RAMs), and range-elevation maps (REMs) of the time sequence of each gesture are obtained by radar signal processing. Then we preprocess the obtained data frames by region of interest (ROI) extraction, vibration removal algorithm, background removal algorithm, and standardization. We propose a transformer-based radar gesture recognition network named RGTNet. It fully extracts and fuses the spatial-temporal information of radar feature maps to complete the classification of various gestures. The experimental results show that our method can better complete the eight gesture classification tasks in the in-vehicle environment. The recognition accuracy is 97.56%.