Volumetric feature points integration with bio-structure-informed guidance for deformable multi-modal CT image registration.

Objective.Medical image registration represents a fundamental challenge in medical image processing. Specifically, CT-CBCT registration has significant implications in the context of image-guided radiation therapy (IGRT). However, traditional iterative methods often require considerable computational time. Deep learning based methods, especially when dealing with low contrast organs, are frequently entangled in local optimal solutions.Approach.To address these limitations, we introduce a registration method based on volumetric feature points integration with bio-structure-informed guidance. Surface point cloud is generated from segmentation labels during the training stage, with both the surface-registered point pairs and voxel feature point pairs co-guiding the training process, thereby achieving higher registration accuracy.Main results.Our findings have been validated on paired CT-CBCT datasets. In comparison with other deep learning registration methods, our approach has improved the precision by 6%, reaching a state-of-the-art status.Significance.The integration of voxel feature points and bio-structure feature points to guide the training of the medical image registration network has achieved promising results. This provides a meaningful direction for further research in medical image registration and IGRT.

Differential Deep Convolutional Neural Network Model for Brain Tumor Classification.

The classification of brain tumors is a difficult task in the field of medical image analysis. Improving algorithms and machine learning technology helps radiologists to easily diagnose the tumor without surgical intervention. In recent years, deep learning techniques have made excellent progress in the field of medical image processing and analysis. However, there are many difficulties in classifying brain tumors using magnetic resonance imaging; first, the difficulty of brain structure and the intertwining of tissues in it; and secondly, the difficulty of classifying brain tumors due to the high density nature of the brain. We propose a differential deep convolutional neural network model (differential deep-CNN) to classify different types of brain tumor, including abnormal and normal magnetic resonance (MR) images. Using differential operators in the differential deep-CNN architecture, we derived the additional differential feature maps in the original CNN feature maps. The derivation process led to an improvement in the performance of the proposed approach in accordance with the results of the evaluation parameters used. The advantage of the differential deep-CNN model is an analysis of a pixel directional pattern of images using contrast calculations and its high ability to classify a large database of images with high accuracy and without technical problems. Therefore, the proposed approach gives an excellent overall performance. To test and train the performance of this model, we used a dataset consisting of 25,000 brain magnetic resonance imaging (MRI) images, which includes abnormal and normal images. The experimental results showed that the proposed model achieved an accuracy of 99.25%. This study demonstrates that the proposed differential deep-CNN model can be used to facilitate the automatic classification of brain tumors.

A Malaysian Medical Non-Governmental Organization's (NGO) Experience in the Emergency Response for COVID-19, Using the Whole-of-Society Collaborative Concept.

Non-governmental organizations (NGOs) are one of the important players during a pandemic, including the Islamic Medical Association of Malaysia (IMAM) Response and Relief Team (IMARET). During the coronavirus disease (COVID-19) pandemic, IMARET played a key role in assisting health relief efforts in Malaysia. We are sharing this experience as a medical NGO's response to the pandemic. This report presents data from the March 18 to June 10, 2020, retrieved from IMARET's database with approval from the Executive Committee and the IMARET COVID-19 Task Force. We report that IMARET's task force consists of 30 people, mostly medical doctors. Supplies distributed included personal protective equipment with other medical equipment, such as portable ultrasounds and ventilators. IMARET engaged with 33 collaborators and 92 partners and funders. There were 135 volunteers with the majority being medical volunteers. IMARET raised more than RM $3 million (US $740 000) garnering support from over 40 000 donors in 85 days. In conclusion, NGOs play a significant role that effectively enhance and complement the consolidated works by the authorities and public in the effort to overcome COVID-19 challenges.

Realizing an Effective COVID-19 Diagnosis System Based on Machine Learning and IoT in Smart Hospital Environment.

The aim of this study is to propose a model based on machine learning (ML) and Internet of Things (IoT) to diagnose patients with COVID-19 in smart hospitals. In this sense, it was emphasized that by the representation for the role of ML models and IoT relevant technologies in smart hospital environment. The accuracy rate of diagnosis (classification) based on laboratory findings can be improved via light ML models. Three ML models, namely, naive Bayes (NB), Random Forest (RF), and support vector machine (SVM), were trained and tested on the basis of laboratory datasets. Three main methodological scenarios of COVID-19 diagnoses, such as diagnoses based on original and normalized datasets and those based on feature selection, were presented. Compared with benchmark studies, our proposed SVM model obtained the most substantial diagnosis performance (up to 95%). The proposed model based on ML and IoT can be served as a clinical decision support system. Furthermore, the outcomes could reduce the workload for doctors, tackle the issue of patient overcrowding, and reduce mortality rate during the COVID-19 pandemic.

Study protocol for a double-blind, randomised placebo-controlled trial evaluating clinical effects of platelet-rich plasma injection for acute grade-2 hamstring tear among high performance athletes.

INTRODUCTION: Hamstring injury among athletes often results in significant morbidity. Currently, there are controversies regarding the clinical use of platelet-rich plasma (PRP) for the treatment of acute hamstring injury. METHODS AND ANALYSIS: This study is a single-centre double-blind randomised placebo-controlled trial. Sixty-eight patients will be randomised to receive under ultrasound guidance either a single injection of leucocyte-rich PRP (LR-PRP) or normal saline. All patients will undergo a standardised hamstring rehabilitation programme under the supervision of a sports physiotherapist. Outcome data will be collected before intervention (baseline), and thereafter on a weekly basis. The primary outcome measure is the duration to return-to-play. It is defined as the duration (in days) from the date on which the injury occurred until the patients were pain-free, able to perform the active knee extension test and have regained hamstring muscle strength. Secondary outcome measures include assessment of pain intensity and the effect of pain on to day-to-day functions using the self-reported Brief Pain Inventory-Short Form questionnaire. Both the primary and secondary outcomes were assessed at baseline and thereafter once a week until return to play. Also, hamstring injury recurrence within the first 6 months after recovery will be monitored via telephone. The results of this study will provide insights into the effect of LR-PRP in muscle and may help to identify the best PRP application protocol for muscle injuries. ETHICS AND DISSEMINATION: Ethics approval were obtained from the Medical Research Ethics Committee of the University of Malaya Medical Centre. Results of this trial will be submitted for publication in a peer-reviewed journal. TRIAL REGISTRATION NUMBER: ISRCTN76844299.

New Approach for Securing and Dating Valuable Printed Documents.

This work deals with using a novel approach for securing and dating printed documents, which will detect any forging crime present. In this respect, the coded dots matrices (machine identification code (MIC)) for the used printers are extracted via a binary system of base 2 (0, 1). The UV ink used in the printing process is prepared from novel fluorescence compounds together with polyvinyl alcohol. Different Xerox models of color laser printers are used for printing the document designs. The data obtained reveal that the investigated approach is succeeded in specifying the date of the printing process together with translating the embedded data of the printer to visible information, which can be tracked under a UV lamp. This innovative approach will assist workers in examining the questioned document by specifying the authorized date and position of printed documents from the MIC.

Comparative DFT Computational Studies with Experimental Investigations for Novel Synthesized Fluorescent Pyrazoline Derivatives.

A novel series of pyrazoline derivatives were synthesized and their spectral properties were characterized via FT-IR, 1H, and 13C NMR. The electronic transitions and fluorescence properties were tracked via UV-Vis and emission spectrometry. The density functional theory (DFT) calculations have been also computed to get spot onto the geometry, electronic transitions and spectroscopic properties theoretically that has been compared with the encountered experimental ones. Moreover, the dipole moment, optimized energy, HOMO - LUMO energies and band gaps were calculated for novel candidates pyrazoline derivatives with highly fluorescence quantum yield.

Synthesis, quantitative structure-property relationship study of novel fluorescence active 2-pyrazolines and application.

A variety of fluorescence-active fluorinated pyrazolines 13-33 was synthesized in good yields through cyclocondensation reaction of propenones 1-9 with aryl hydrazines 10-12. Some of the synthesized compounds provided promising fluorescence properties with quantum yield (Φ) higher than that of quinine sulfate (standard reference). Quantitative structure-property relationship studies were undertaken supporting the exhibited fluorescence properties and estimating the parameters governing properties. Five synthesized fluorescence-active pyrazolines (13, 15, 18, 19 and 23) with variable Φ were selected for treating two types of paper sheets (Fabriano and Bible paper). These investigated fluorescence compounds, especially compounds 19 and 23, provide improvements in strength properties of paper sheets. Based on the observed performance they can be used as markers in security documents.

Antioxidant vitamins and glucose-6-phosphate dehydrogenase deficiency in full-term neonates.

OBJECTIVE: The mechanism by which glucose-6-phosphate dehydrogenase (G6PD) deficiency causes neonatal hyperbilirubinemia is not completely understood. However, the genetic disorder G6PD deficiency predisposes red blood cells to oxidative stress. The aim of this study was to establish the relationship between plasma antioxidant vitamin (E and C) levels and the development of hyperbilirubinemia in full-term neonates with deficient G6PD. METHODS: A total of 196 live birth neonates of healthy mothers were included in this study. Twelve of them were deficient in G6PD. In addition to demographic data, serum total bilirubin, hemoglobin, hematocrit, and vitamin E and C levels were measured on the first day after birth. RESULTS: Neonates with G6PD deficiency (n=7) who did not develop hyperbilirubinemia (mean serum bilirubin level of 70.8+/-23 micromol/l, median 71.8) and neonates with G6PD deficiency (n=4) who developed hyperbilirubinemia (mean serum bilirubin level of 226.7+/-79 micromol/l, median 233.4) on the first day of life had similar gestational weights and age. The second group, however, had lower hemoglobin and hematocrit as well as plasma vitamin C and E levels. None of these results showed significant difference. CONCLUSION: The results of the present study indicate that red blood cell hemolysis as a result of inadequate antioxidants system in G6PD-deficient neonates is not the only contributing factor for hyperbilirubinemia.

Antioxidant vitamins and hyperbilirubinemia in neonates.

OBJECTIVE: Low antioxidant system may contribute to the severity of neonatal hyperbilirubinemia. The aim of this research was to explore the relationship between plasma vitamin E and C levels and the severity of hyperbilirubinemia in full-term neonates with normal glucose 6-phosphate dehydrogenase (G6PD) activities. METHODS: A total of 130 full-term healthy live birth neonates of healthy mothers with normal G6PD activity were included in this study. In addition to routine blood analysis, plasma total bilirubin, vitamin E and C levels and G6PD activity were measured on the first day of life. None of the neonates was ABO incompatible or anemic. RESULTS: Neonates who did not develop hyperbilirubinemia (n=119) had a mean plasma bilirubin level of 65+/-24 micromol/l (median 58.1), while neonates who developed significant hyperbilirubinemia (n=11) had a mean plasma bilirubin level of 238+/-56 micromol/l (median 246.2) on the first day of life. Mean plasma vitamin C levels of neonates who developed hyperbilirubinemia were significantly lower than those who did not develop hyperbilirubinemia (87+/-22 micromol/l (median 89.4) vs. 132+/-36 micromol/l (median 127.7), respectively, P=0.0001). Similar results were observed for plasma vitamin E levels in neonates who did or did not develop hyperbilirubinemia (7.5+/-2 micromol/l (median 6.3) vs. 10.4+/-5 micromol/l (median 9.1), respectively, P=0.001). Hemoglobin and hematocrit were significantly lower in neonates who developed hyperbilirubinemia (P=0.0002 and P=0.0003, respectively), although gestational age and birth weight for the two groups showed no significant difference. CONCLUSION: The results of the present work indicate that low level of plasma vitamins C and E are associated with significant hyperbilirubinemia in full-term neonates.