An Efficient Deep Learning Mechanism for the Recognition of Olive Trees in Jouf Region.

Olive trees grow all over the world in reasonably moderate and dry climates, making them fortunate and medicinal. Pesticides are required to improve crop quality and productivity. Olive trees have had important cultural and economic significance since the early pre-Roman era. In 2019, Al-Jouf region in a Kingdom of Saudi Arabia's north achieved global prominence by breaking a Guinness World Record for having more number of olive trees in a world. Unmanned aerial systems (UAS) were increasingly being used in aerial sensing activities. However, sensing data must be processed further before it can be used. This processing necessitates a huge amount of computational power as well as the time until transmission. Accurately measuring the biovolume of trees is an initial step in monitoring their effectiveness in olive output and health. To overcome these issues, we initially formed a large scale of olive database for deep learning technology and applications. The collection comprises 250 RGB photos captured throughout Al-Jouf, KSA. This paper employs among the greatest efficient deep learning occurrence segmentation techniques (Mask Regional-CNN) with photos from unmanned aerial vehicles (UAVs) to calculate the biovolume of single olive trees. Then, using satellite imagery, we present an actual deep learning method (SwinTU-net) for identifying and counting of olive trees. SwinTU-net is a U-net-like network that includes encoding, decoding, and skipping links. SwinTU-net's essential unit for learning locally and globally semantic features is the Swin Transformer blocks. Then, we tested the method on photos with several wavelength channels (red, greenish, blues, and infrared region) and vegetation indexes (NDVI and GNDVI). The effectiveness of RGB images is evaluated at the two spatial rulings: 3 cm/pixel and 13 cm/pixel, whereas NDVI and GNDV images have only been evaluated at 13 cm/pixel. As a result of integrating all datasets of GNDVI and NDVI, all generated mask regional-CNN-based systems performed well in segmenting tree crowns (F1-measure from 95.0 to 98.0 percent). Based on ground truth readings in a group of trees, a calculated biovolume was 82 percent accurate. These findings support all usage of NDVI and GNDVI spectrum indices in UAV pictures to accurately estimate the biovolume of distributed trees including olive trees.

Machine Learning Approach for Autonomous Detection and Classification of COVID-19 Virus.

As people all over the world are vulnerable to be affected by the COVID-19 virus, the automatic detection of such a virus is an important concern. The paper aims to detect and classify corona virus using machine learning. To spot and identify corona virus in CT-Lung screening and Computer-Aided diagnosis (CAD) system is projected to distinguish and classifies the COVID-19. By utilizing the clinical specimens obtained from the corona-infected patients with the help of some machine learning techniques like Decision Tree, Support Vector Machine, K-means clustering, and Radial Basis Function. While some specialists believe that the RT-PCR test is the best option for diagnosing Covid-19 patients, others believe that CT scans of the lungs can be more accurate in diagnosing corona virus infection, as well as being less expensive than the PCR test. The clinical specimens include serum specimens, respiratory secretions, and whole blood specimens. Overall, 15 factors are measured from these specimens as the result of the previous clinical examinations. The proposed CAD system consists of four phases starting with the CT lungs screening collection, followed by a pre-processing stage to enhance the appearance of the ground glass opacities (GGOs) nodules as they originally lock hazy with fainting contrast. A modified K-means algorithm will be used to detect and segment these regions. Finally, the use of detected, infected areas that obtained in the detection phase with a scale of 50×50 and perform segmentation of the solid false positives that seem to be GGOs as inputs and targets for the machine learning classifiers, here a support vector machine (SVM) and Radial basis function (RBF) has been utilized. Moreover, a GUI application is developed which avoids the confusion of the doctors for getting the exact results by giving the 15 input factors obtained from the clinical specimens.

Analyzing the Patient Behavior for Improving the Medical Treatment Using Smart Healthcare and IoT-Based Deep Belief Network.

Patient behavioral analysis is a critical component in treating patients with a variety of issues, with head trauma, neurological disease, and mental illness. The analysis of the patient's behavior aids in establishing the disease's core cause. Patient behavioral analysis has a number of contests that are much more problematic in traditional healthcare. With the advancement of smart healthcare, patient behavior may be simply analyzed. A new generation of information technologies, particularly the Internet of Things (IoT), is being utilized to transform the traditional healthcare system in a variety of ways. The Internet of Things (IoT) in healthcare is a crucial role in offering improved medical facilities to people as well as assisting doctors and hospitals. The proposed system comprises of a variety of medical equipment, such as mobile-based apps and sensors, which is useful in collecting and monitoring the medical information and health data of patient and interact to the doctor via network connected devices. This research may provide key information on the impact of smart healthcare and the Internet of Things in patient beavior and treatment. Patient data are exchanged via the Internet, where it is viewed and analyzed using machine learning algorithms. The deep belief neural network evaluates the patient's particulars from health data in order to determine the patient's exact health state. The developed system proved the average error rate of about 0.04 and ensured accuracy about 99% in analyzing the patient behavior.

An Effective Data Science Technique for IoT-Assisted Healthcare Monitoring System with a Rapid Adoption of Cloud Computing.

Patients are required to be observed and treated continually in some emergency situations. However, due to time constraints, visiting the hospital to execute such tasks is challenging. This can be achieved using a remote healthcare monitoring system. The proposed system introduces an effective data science technique for IoT supported healthcare monitoring system with the rapid adoption of cloud computing that enhances the efficiency of data processing and the accessibility of data in the cloud. Many IoT sensors are employed, which collect real healthcare data. These data are retained in the cloud for the processing of data science. In the Healthcare Monitoring-Data Science Technique (HM-DST), initially, an altered data science technique is introduced. This algorithm is known as the Improved Pigeon Optimization (IPO) algorithm, which is employed for grouping the stored data in the cloud, which helps in improving the prediction rate. Next, the optimum feature selection technique for extraction and selection of features is illustrated. A Backtracking Search-Based Deep Neural Network (BS-DNN) is utilized for classifying human healthcare. The proposed system's performance is finally examined with various healthcare datasets of real time and the variations are observed with the available smart healthcare systems for monitoring.

Source Localization of EEG Brainwaves Activities via Mother Wavelets Families for SWT Decomposition.

A Brain-Computer Interface (BCI) is a system used to communicate with an external world through the brain activity. The brain activity is measured by electroencephalography (EEG) signal and then processed by a BCI system. EEG source reconstruction could be a way to improve the accuracy of EEG classification in EEG based brain-computer interface (BCI). The source localization of the human brain activities can be an important resource for the recognition of the cognitive state, medical disorders, and a better understanding of the brain in general. In this study, we have compared 51 mother wavelets taken from 7 different wavelet families, which are applied to a Stationary Wavelet Transform (SWT) decomposition of an EEG signal. This process includes Haar, Symlets, Daubechies, Coiflets, Discrete Meyer, Biorthogonal, and reverse Biorthogonal wavelet families in extracting five different brainwave subbands for source localization. For this process, we used the Independent Component Analysis (ICA) for feature extraction followed by the Boundary Element Model (BEM) and the Equivalent Current Dipole (ECD) for the forward and inverse problem solutions. The evaluation results in investigating the optimal mother wavelet for source localization eventually identified the sym20 mother wavelet as the best choice followed by bior6.8 and coif5.

Machine Algorithm for Heartbeat Monitoring and Arrhythmia Detection Based on ECG Systems.

Cardiac arrhythmia is an illness in which a heartbeat is erratic, either too slow or too rapid. It happens as a result of faulty electrical impulses that coordinate the heartbeats. Sudden cardiac death can occur as a result of certain serious arrhythmia disorders. As a result, the primary goal of electrocardiogram (ECG) investigation is to reliably perceive arrhythmias as life-threatening to provide a suitable therapy and save lives. ECG signals are waveforms that denote the electrical movement of the human heart (P, QRS, and T). The duration, structure, and distances between various peaks of each waveform are utilized to identify heart problems. The signals' autoregressive (AR) analysis is then used to obtain a specific selection of signal features, the parameters of the AR signal model. Groups of retrieved AR characteristics for three various ECG kinds are cleanly separated in the training dataset, providing high connection classification and heart problem diagnosis to each ECG signal within the training dataset. A new technique based on two-event-related moving averages (TERMAs) and fractional Fourier transform (FFT) algorithms is suggested to better evaluate ECG signals. This study could help researchers examine the current state-of-the-art approaches employed in the detection of arrhythmia situations. The characteristic of our suggested machine learning approach is cross-database training and testing with improved characteristics.

Feasibility of freehand MRI/US cognitive fusion transperineal biopsy of the prostate in local anaesthesia as in-office procedure-experience with 400 patients.

BACKGROUND: Transrectal (TR) ultrasound-guided prostate biopsy is one of the most commonly performed urologic procedures worldwide. The major drawback of this approach is the associated risk for infectious complications. Sepsis rates are increasing due to rising antibiotic resistance, representing a global issue. The transperineal (TP) approach for prostate biopsy has recently been adopted at many centres as an alternative to the TR biopsy, and it was shown to be associated with a lower risk for sepsis. The aim of this study was to assess safety and tolerability of TP prostate biopsy performed in local anaesthesia. METHODS: We retrospectively analysed data of patients who had undergone office-based TP prostate biopsy in local anaesthesia, performed by a single surgeon between January 2015 and May 2019. We evaluated the patients' acceptance of the procedure by a pain score, as well as its safety and diagnostic performance. RESULTS: Four hundred patients were included. Median age was 66 years [range, 49-86]. Median prostate-specific antigen (PSA) concentration was 6.4 ng/ml [range, 0.3-1400], median PSA density was 0.15 ng/ml2 [range, 0-31.1] and median prostate volume was 40 ml [range, 6-150]. A total of 118 (29.5%) and 105 (26.2%) patients had orally received two and one doses of 500 mg fluoroquinolone, respectively, and 177 (44.3%) patients did not receive any antibiotic prophylaxis. No infectious complications occurred. Median pain score was 2.0 (range, 0-8). Overall cancer detection rate was 64.5% (258/400). CONCLUSIONS: Freehand TP prostate biopsy in local anaesthesia is a safe, effective and well-tolerated outpatient procedure with a high cancer detection rate. The elimination of infectious complications and its high accuracy make this technique a feasible alternative to the TR approach for the urological office. We assume that the single puncture and our trocar-like access sheath introduction technique diminish tissue trauma and bacterial exposition, and thus contribute to these promising results.

Ultrasound-based tumor movement compensation during navigated laparoscopic liver interventions.

BACKGROUND: Image-guided navigation aims to provide better orientation and accuracy in laparoscopic interventions. However, the ability of the navigation system to reflect anatomical changes and maintain high accuracy during the procedure is crucial. This is particularly challenging in soft organs such as the liver, where surgical manipulation causes significant tumor movements. We propose a fast approach to obtain an accurate estimation of the tumor position throughout the procedure. METHODS: Initially, a three-dimensional (3D) ultrasound image is reconstructed and the tumor is segmented. During surgery, the position of the tumor is updated based on newly acquired tracked ultrasound images. The initial segmentation of the tumor is used to automatically detect the tumor and update its position in the navigation system. Two experiments were conducted. First, a controlled phantom motion using a robot was performed to validate the tracking accuracy. Second, a needle navigation scenario based on pseudotumors injected into ex vivo porcine liver was studied. RESULT: In the robot-based evaluation, the approach estimated the target location with an accuracy of 0.4 ± 0.3 mm. The mean navigation error in the needle experiment was 1.2 ± 0.6 mm, and the algorithm compensated for tumor shifts up to 38 mm in an average time of 1 s. CONCLUSION: We demonstrated a navigation approach based on tracked laparoscopic ultrasound (LUS), and focused on the neighborhood of the tumor. Our experimental results indicate that this approach can be used to quickly and accurately compensate for tumor movements caused by surgical manipulation during laparoscopic interventions. The proposed approach has the advantage of being based on the routinely used LUS; however, it upgrades its functionality to estimate the tumor position in 3D. Hence, the approach is repeatable throughout surgery, and enables high navigation accuracy to be maintained.

Laparoscopic navigated liver resection: technical aspects and clinical practice in benign liver tumors.

Laparoscopic liver resection has been performed mostly in centers with an extended expertise in both hepatobiliary and laparoscopic surgery and only in highly selected patients. In order to overcome the obstacles of this technique through improved intraoperative visualization we developed a laparoscopic navigation system (LapAssistent) to register pre-operatively reconstructed three-dimensional CT or MRI scans within the intra-operative field. After experimental development of the navigation system, we commenced with the clinical use of navigation-assisted laparoscopic liver surgery in January 2010. In this paper we report the technical aspects of the navigation system and the clinical use in one patient with a large benign adenoma. Preoperative planning data were calculated by Fraunhofer MeVis Bremen, Germany. After calibration of the system including camera, laparoscopic instruments, and the intraoperative ultrasound scanner we registered the surface of the liver. Applying the navigated ultrasound the preoperatively planned resection plane was then overlain with the patient's liver. The laparoscopic navigation system could be used under sterile conditions and it was possible to register and visualize the preoperatively planned resection plane. These first results now have to be validated and certified in a larger patient collective. A nationwide prospective multicenter study (ProNavic I) has been conducted and launched.

Interdisciplinary evidence-based recommendations for the follow-up of testicular cancer patients: a joint effort.

Detailed recommendations for the treatment of testicular cancer exist and due to the stringent application of the standard therapies, most patients can nowadays be cured. Moreover in the treatment of early stage disease, active surveillance is now a cornerstone of treatment. Hence there is a clear need for recommendations regarding the long term follow-up of these young patients. These have to be safe, feasible and the intensity of procedures have to reflect the known risk of recurrence. Different proposals have been published but they differ widely especially in terms of frequency and modality of imaging. In the last few years, new evidence has become available regarding the relapse pattern of different disease stages of testicular cancer, the use of imaging in follow-up and the risks of excessive radiation due to imaging, in particular with CT scans. In this article, an interdisciplinary, multinational working group has reviewed the evidence and based on this has formulated practical recommendations for the follow-up of patients with testicular cancer.

Primary T1G3 bladder cancer: organ preserving approach or immediate cystectomy?

PURPOSE: In this retrospective nonrandomized study we compared the long-term outcome in patients with newly diagnosed stage T1G3 bladder cancer treated with transurethral resection and bacillus Calmette-Guerin or immediate cystectomy. MATERIALS AND METHODS: Of 121 patients with a median age of 67 years (range 36 to 88) diagnosed with primary T1G3 bladder cancer between 1976 and 1999, 92 were treated by transureteral resection with additional intravesical bacillus Calmette-Guerin and 29 were treated with immediate cystectomy. RESULTS: Of the 92 patients treated with an organ preserving approach 29 remained disease-free, local recurrence developed in 33 (36%) and progression developed in 30 (33%) at a median followup of 6.9 years (range 0.6 to 16.5). Of these 92 patients 27 (29%) underwent deferred cystectomy at a median of 12.9 months (range 4.8 to 136), of whom 10 (37%) with a median postoperative followup of 19 months (range 2 to 173) died of progressive disease with a median survival of 13 months (range 3 to 34) after cystectomy. The majority of patients who died of progressive disease refused cystectomy, were referred too late for cystectomy, were inoperable or had upper urinary tract disease. Six of the 29 patients (21%) undergoing immediate cystectomy had progression at a median of 13.2 months (range 5.5 to 37). Overall and tumor specific survival at 5 years in patients treated with an organ preserving approach was 69% and 80%, and in those treated with immediate cystectomy it was 54% and 69%, respectively. CONCLUSIONS: The results of this analysis demonstrate that the concept of an organ preserving approach is acceptable and spares the bladder in approximately half of the patients with primary T1G3 bladder cancer. Of the patients 30% require deferred cystectomy, making meticulous, close followup mandatory.

A retrospective analysis of 153 patients treated with or without intravesical bacillus Calmette-Guerin for primary stage T1 grade 3 bladder cancer: recurrence, progression and survival.

PURPOSE: We retrospectively evaluated the long-term outcome in patients with newly diagnosed stage T1 grade 3 bladder cancer treated with transurethral resection with or without intravesical bacillus Calmette-Guerin (BCG). MATERIALS AND METHODS: Of 153 patients with a median age of 67 years (range 36 to 88) and a male-to-female ratio of 4:1 we treated 92 with transurethral bladder resection and additional BCG, and 61 with transurethral bladder resection alone. BCG was administered intravesically as 120 mg. BCG Pasteur F dissolved in 50 ml. saline, retained for up to 2 hours weekly for 6 weeks and repeated as necessary. RESULTS: Median followup was 5.3 years (range 0.4 to 18.2). Disease recurred in 70% of the patients treated with BCG and in 75% treated with transurethral resection alone. Median time to recurrence was 38 and 22 months for BCG and resection alone (p = 0.19). Tumor progressed in 33% of patients with BCG and in 36% with resection alone. Deferred cystectomy was performed in 29% of the patients with BCG and in 31% with resection alone. Overall and disease specific survival did not differ significantly. CONCLUSIONS: Our results suggest that intravesical BCG therapy after transurethral bladder resection for stage T1 grade 3 bladder cancer may delay the time to recurrence and cystectomy but it does not substantially alter the final outcome. Our findings reflect the rule of 30% for stage T1 grade 3 cancer, namely approximately 30% of patients never have recurrence, 30% ultimately die of metastatic disease and 30% require deferred cystectomy.