Novel concept-based image captioning models using LSTM and multi-encoder transformer architecture.

Captioning an image involves using a combination of vision and language models to describe the image in an expressive and concise sentence. Successful captioning task requires extracting as much information as possible from the corresponding image. One of these key pieces of information is the topic to which the image belongs. The state-of-the-art methods used topic modeling depending only on caption text in order to extract these topics. The problem with extracting the topics using topic modeling only on caption text is that it lacks the consideration of the image's semantic information. Instead, concept modeling extracts the concepts directly from the images in addition to considering the corresponding caption text. Concept modeling can be used in image captioning to extremely capture the image contexts and benefit from it to produce more accurate descriptions. In this paper, novel image captioning models are proposed by utilizing the concept modeling technique. The first concept-based model is proposed by utilizing LSTM as a decoder while the second model is proposed in association with new multi-encoder transformer architecture. Standard metrics have been used to evaluate the proposed models using Microsoft COCO and Flickr30K datasets. The proposed models outperformed the related work methods with reduced computational complexity.

Novel eco-friendly [1,2,4]triazolo[3,4-a]isoquinoline chalcone derivatives efficiency against fungal deterioration of ancient Egyptian mummy cartonnage, Egypt.

Fungal deterioration is one of the major factors that significantly contribute to mummy cartonnage damage. Isolation and molecular identification of thirteen fungal species contributing to the deterioration of ancient Egyptian mummy cartonnage located in El-Lahun regions, Fayoum government, Egypt was performed. The most dominant deteriorated fungal species are Aspergillus flavus (25.70%), Aspergillus terreus (16.76%), followed by A. niger (13.97%). A newly synthesized series of tetrahydro-[1,2,4]triazolo[3,4-a]isoquinoline chalcone derivatives were synthesized and evaluated for their antifungal activities in vitro against the isolated deteriorated fungal species (Aspergillus flavus, A. niger, A. terreus, Athelia bombacina, Aureobasidium iranianum, Byssochlamys spectabilis, Cladosporium cladosporioides, C. ramotenellum, Penicillium crustosum, P. polonicum, Talaromyces atroroseus, T. minioluteus and T. purpureogenus). The most efficient chalcone derivatives are new chalcone derivative numbers 9 with minimum inhibitory concentration (MIC) ranging from 1 to 3 mg/mL followed by chalcone derivatives number 5 with MIC ranging from 1 to 4 mg/mL.

A novel melanoma prediction model for imbalanced data using optimized SqueezeNet by bald eagle search optimization.

Skin lesion classification plays a crucial role in diagnosing various gene and related local medical cases in the field of dermoscopy. In this paper, a new model for the classification of skin lesions as either normal or melanoma is presented. The proposed melanoma prediction model was evaluated on a large publicly available dataset called ISIC 2020. The main challenge of this dataset is severe class imbalance. This paper proposes an approach to overcome this problem using a random over-sampling method followed by data augmentation. Moreover, a new hybrid version of a convolutional neural network architecture and bald eagle search (BES) optimization is proposed. The BES algorithm is used to find the optimal values of the hyperparameters of a SqueezeNet architecture. The proposed melanoma skin cancer prediction model obtained an overall accuracy of 98.37%, specificity of 96.47%, sensitivity of 100%, f-score of 98.40%, and area under the curve of 99%. The experimental results showed the robustness and efficiency of the proposed model compared with VGG19, GoogleNet, and ResNet50. Additionally, the results showed that the proposed model was very competitive compared with the state of the art.

Real-time multiple spatiotemporal action localization and prediction approach using deep learning.

Detecting the locations of multiple actions in videos and classifying them in real-time are challenging problems termed "action localization and prediction" problem. Convolutional neural networks (ConvNets) have achieved great success for action localization and prediction in still images. A major advance occurred when the AlexNet architecture was introduced in the ImageNet competition. ConvNets have since achieved state-of-the-art performances across a wide variety of machine vision tasks, including object detection, image segmentation, image classification, facial recognition, human pose estimation, and tracking. However, few works exist that address action localization and prediction in videos. The current action localization research primarily focuses on the classification of temporally trimmed videos in which only one action occurs per frame. Moreover, nearly all the current approaches work only offline and are too slow to be useful in real-world environments. In this work, we propose a fast and accurate deep-learning approach to perform real-time action localization and prediction. The proposed approach uses convolutional neural networks to localize multiple actions and predict their classes in real time. This approach starts by using appearance and motion detection networks (known as "you only look once" (YOLO) networks) to localize and classify actions from RGB frames and optical flow frames using a two-stream model. We then propose a fusion step that increases the localization accuracy of the proposed approach. Moreover, we generate an action tube based on frame level detection. The frame by frame processing introduces an early action detection and prediction with top performance in terms of detection speed and precision. The experimental results demonstrate this superiority of our proposed approach in terms of both processing time and accuracy compared to recent offline and online action localization and prediction approaches on the challenging UCF-101-24 and J-HMDB-21 benchmarks.

Novel methotrexate soft nanocarrier/fractional erbium YAG laser combination for clinical treatment of plaque psoriasis.

Psoriasis is a commonly encountered chronic dermatological disease, presenting with inflammatory symptoms in patients. Systemic treatment of psoriasis is associated with several adverse effects, therefore the development of a customized topical treatment modality for psoriasis would be an interesting alternative to systemic delivery. The therapeutic modality explored in this article was the comparative treatment of psoriatic patients using nanoparticulated methotrexate in the form of jojoba oil-based microemulsion with or without fractional erbium YAG laser. Assessment parameters included follow-up photography for up to 8 weeks of treatment, estimation of the psoriasis severity [TES (thickness, erythema, scales)] score, and histopathological skin evaluation. The prepared methotrexate microemulsion was clinically beneficial and safe in treatment of psoriasis vulgaris. The concomitant use of the fractional laser provided improvement in the psoriatic plaques within shorter time duration (3 weeks compared to 8 weeks of treatment), presenting an alternative topical treatment modality for psoriasis vulgaris.

Medical Education Journal Club: Two years' experience at King Saud University.

OBJECTIVE: Medical Education Journal Club is an evidence-based approach to teach and learn critical appraisal techniques on available literature. This study evaluates the implementation and experience of two academic years of Journal club at Medical Education Department, King Saud University. METHODS: We started JC in 2015 at medical education department, KSU. An invitation with a published paper and event poster were sent 2 weeks prior of the session to participants. A traditional one-group posttest design with open item survey were conducted at the end of every session. RESULTS: A total of 12 sessions were conducted in total. The average attendance of 26 (Male: 42/79, 53.1%) and (Female: 31/79, 39.2%) with mix of professors, associate and assistant professors. The MEJC had a positive effect on participant's session expectations (45/79, 92.4%), and had increased their knowledge of the field (73/79, 92.4%). It was observed that the attendance of event depends on the speaker for the event. The sessions have also arisen the need of trainings and other scientific activities. CONCLUSIONS: MEJC is an educational activity that can play important aspect in providing high quality healthcare teachings. We conclude that the success and consistency of MEJC depends on speaker. It commensurate the audience interest to attend and learn. While proper advertisement of event, and regular attendance also plays a vital role in this regard.

Medical students' perception of the learning environment at King Saud University Medical College, Saudi Arabia, using DREEM Inventory.

BACKGROUND: The students' perception of the learning environment is an important aspect for evaluation and improvement of the educational program. The College of Medicine at King Saud University (KSU) reformed its curriculum in 2009 from a traditional to a system-oriented hybrid curriculum. OBJECTIVE: The objective of the present study was to determine the perception of the second batch (reformed curriculum) of medical graduates about the educational environment at the College of Medicine, KSU, using the Dundee Ready Education Environment Measure (DREEM) scale. METHODS: The fifth year medical students were asked to evaluate the educational program after graduation in May 2014. The questionnaire was distributed to the graduate students electronically. The DREEM questionnaire consisted of 50 items based on Likert's scale; and five domains, namely, students' perceptions of learning, perceptions of teachers, academic self-perceptions, perceptions of atmosphere, and social self-perceptions. Data were analyzed using SPSS. RESULTS: A total of 62 students participated in the study. The score for students' perception of learning among medical students ranged from 2.93 to 3.64 (overall mean score: 40.17). The score for students' perception of teachers ranged from 2.85 to 4.01 (overall mean score: 33.35). The score for students' academic self-perceptions ranged from 3.15 to 4.06 (overall mean score: 28.4). The score for students' perception of atmosphere ranged from 2.27 to 3.91 (overall mean score: 41.32). The score for students' social self-perceptions ranged from 2.85 to 4.33 (overall mean score: 24.33). The general perceptions of the students in all five sub-scales were positive. CONCLUSION: The overall student's perception about the educational environment was satisfactory. This study was important to evaluate the students' perception of the learning environment among medical graduates of the reformed curriculum and provided guidance on areas of improvement in the curriculum.

Evaluation of the improvement effect of laser acupuncture biostimulation in asthmatic children by exhaled inflammatory biomarker level of nitric oxide.

Variable therapy of asthma is not sufficient yet to achieve good asthma control. Therapy decision requires serial investigations. Low-level laser acupuncture is a suitable non-invasive modality of complementary medicine. The exhaled breath condensate (EBC) is easy and useful to evaluate the efficacy of drugs or novel therapy. This study aimed to evaluate the effectiveness of low-level laser biostimulation of acupuncture points on asthma improvement in children. Forty-eight asthmatic children were subdivided into case (laser) group, which received 12 direct contact low-power laser acupuncture sessions (three sessions/week) on specific traditional Chinese acupuncture points for bronchial asthma, and control asthmatic group, which received sham laser acupuncture on the same acupoints and number of sessions of the case (laser) group. Low-power Multichannel Aculas-AM laser (grade II) of wave length 780 nm, output power 800 mw, and beam spot size 0.1 cm2 with continuous mode was used. Eighteen acupoints were stimulated for 2 min, giving energy of 9.6 J/cm2/acupoint. The total session time was 3 min. Both groups were evaluated pre- and post-laser acupuncture intervention by recording levels of asthma control, pulmonary function, and EBC nitric oxide. In the case (laser) group, 91.7 % of patients experienced an improvement in the level of asthma control versus 25 % in the control group (p < 0.001). This was associated with a significant decrease of the breath condensate FENO concentration (p < 0.001) and significant increase of spirometry parameters (p < 0.001) in the case (laser) group. Application of laser acupuncture treatment given with conventional therapy can effectively improve bronchial asthma more than prescription of medications alone could.

Use of cross-institutional progress test as a predictor of performance in a new medical college.

BACKGROUND: The progress test was initiated by Qassim University in 2000 as a tool to evaluate the educational process among Saudi medical colleges. Princess Nourah Bint Abdul Rahman University (PNU) College of Medicine is a new medical college established in 2012 that implemented the same innovative reformed curriculum of King Saud University College of Medicine. OBJECTIVES: The objective of this study was to use the progress test to evaluate the rate of knowledge acquisition among a new medical school compared to other long-established medical schools in Saudi Arabia. MATERIALS AND METHODS: As part of an ongoing strategy, the progress test was administered before the end of the academic year. Students in PNU were enrolled for 2 years in the progress test. We compared the mean progress test scores for PNU students compared to students at comparable stages in other medical schools in Saudi Arabia. RESULTS: The results showed that the rate of knowledge acquisition was similar in students at PNU to students in other well-established medical schools in Saudi Arabia. CONCLUSION: The present study showed that the interinstitutional progress test demonstrated that the level of acquisition of knowledge and performance of students in a new medical school was similar to other medical colleges in Saudi Arabia.

Effects of aminoguanidine, a potent nitric oxide synthase inhibitor, on myocardial and organ structure in a rat model of hemorrhagic shock.

BACKGROUND: Nitric oxide (NO) has been shown to increase following hemorrhagic shock (HS). Peroxynitrite is produced by the reaction of NO with reactive oxygen species, leads to nitrosative stress mediated organ injury. We examined the protective effects of a potent inhibitor of NO synthase, aminoguanidine (AG), on myocardial and multiple organ structure in a rat model of HS. MATERIALS AND METHODS: Male Sprague Dawley rats (300-350 g) were assigned to 3 experimental groups (n = 6 per group): (1) Normotensive rats (N), (2) HS rats and (3) HS rats treated with AG (HS-AG). Rats were hemorrhaged over 60 min to reach a mean arterial blood pressure of 40 mmHg. Rats were treated with 1 ml of 60 mg/kg AG intra-arterially after 60 min HS. Resuscitation was performed in vivo by the reinfusion of the shed blood for 30 min to restore normo-tension. Biopsy samples were taken for light and electron microscopy. RESULTS: Histological examination of hemorrhagic shocked untreated rats revealed structural damage. Less histological damage was observed in multiple organs in AG-treated rats. AG-treatment decreased the number of inflammatory cells and mitochondrial swollen in myocardial cells. CONCLUSION: AG treatment reduced microscopic damage and injury in multiple organs in a HS model in rats.

Is serum level of methylated RASSF1A valuable in diagnosing hepatocellular carcinoma in patients with chronic viral hepatitis C?

BACKGROUND AND STUDY AIMS: The detection of the promoter hypermethylation of RASSF1A in serum DNA could be a valuable biomarker for early detection of preneoplastic lesions and early cancer development among high-risk populations who are at a high risk of hepatocellular carcinoma (HCC). Therefore, we aimed determining the serum level of methylated RASSF1A sequence in patients with chronic hepatitis C viral infection and to evaluate the predictive value of it as a diagnostic marker for HCC in patients with chronic hepatitis C viral infection. PATIENTS AND METHODS: Serum levels of methylated RASSF1A were detected and measured using real-time PCR after digestion with a methylation-sensitive restriction enzyme in 40 patients with chronic HCV infection, 40 patients with HCC (on top of HCV) and 20 controls. RESULTS: Methylated RASSF1A was detected in 10% of the controls, 62.5% of HCV group and in 90% of HCC group. Chronic HCV patients had insignificantly higher levels than the controls. The levels were significantly higher in patients with HCC compared to the controls (p=0.0001) and chronic HCV patients (p=0.001). By logistic regression analysis, the serum methylated RASSF1A was found to differentiate HCC patients from healthy controls with an AUROC of 0.83nmol/L, and an overall predictive accuracy of 77.5%. It was able to differentiate patients with HCC from those with chronic HCV infection alone with an AUROC of 0.733 and an overall predictive accuracy of 72.5%. CONCLUSION: The mean serum levels of methylated RASSF1A could be of value for early diagnosis of HCC especially in high risk patients with HCV infection.

Treatment with dipyridamole improves cardiac function and prevent injury in a rat model of hemorrhage.

Hemorrhagic shock is a leading cause of death despite the improvement in emergency services. One reason is that the resuscitation policies are designed to reestablish tissue perfusion, but not to prevent the inflammatory response to shock that cause myocardial dysfunction and injury. Dipyridamole is a platelet inhibitor that promotes anti-inflammatory effects. The present study investigated the therapeutic value of treatment with dipyridamole before resuscitation from hemorrhagic shock on myocardial injury and protection. Male Sprague-Dawley rats were assigned to 3 experimental groups (n=6 per group): 1) hemorrhage, 2) hemorrhage treated with dipyridamole, and 3) sham hemorrhage. Rats were hemorrhaged over 60min to reach a mean arterial blood pressure of 40mmHg. After 60min hemorrhagic shock, rats were treated or not by injection of 1mL of (20µg/L) dipyridamole intra-arterially. Resuscitation was made in vivo by reinfusion of the shed blood to restore norm tension for 30min. Arterial blood samples were collected for measurements of TNF-α. Left ventricular generated pressure and +dP/dtmax was significantly higher in dipyridamole treated rats compared to the untreated group. Myocardial biopsy samples were taken for light and electron microscopy. Dipyridamole decreased the number of inflammatory cells and mitochondrial swollen. Dipyridamole also decreased the plasma levels of TNF-α. Our results demonstrate that treatment with dipyridamole before in vivo resuscitation of hemorrhagic shock protect the myocardium against post-resuscitation myocardial dysfunction by decreasing the inflammatory response to shock.

Na(+)-H(+) exchange blockade, using amiloride, decreases the inflammatory response following hemorrhagic shock and resuscitation in rats.

Na(+)-H(+) exchanger activation on resuscitation following hemorrhagic shock has been shown to result in myocardial injury and dysfunction. Amiloride, an inhibitor of the Na(+)-H(+) exchanger has been shown to protect the myocardium against reperfusion injury in the ischemic hearts. However, the mechanism of protection remains unclear. Na(+)-H(+) exchanger blockers have been implicated in the regulation of inflammatory responses and chemokine production. The present study investigated the therapeutic anti-inflammatory value of amiloride on myocardial contractile function in post-resuscitation following hemorrhagic shock in rats. Male Sprague-Dawley rats were assigned into 3 groups: 1) hemorrhage, 2) hemorrhage treated with amiloride, and 3) sham hemorrhage (n=6 per group). Rats were hemorrhaged over 60min to reach a mean arterial blood pressure of 40mmHg. After 60min of hemorrhagic shock, rats were treated or not by injection of 1ml of 100µM amiloride (0.027mg/ml) intra-arterially. Resuscitation was made in vivo by reinfusion of the shed blood to restore norm tension for 30min. Left ventricular contractile function was measured in the isolated hearts following hemorrhage and in vivo resuscitation using the Langendorff apparatus. Arterial blood samples were collected from all groups at the end of the experimental period (90min) for cytokine measurements (TNF-α). Amiloride decreased the inflammatory response to hemorrhagic shock and resuscitation by lowering the levels of TNF. These results indicate that amiloride protects the myocardium by down regulating the inflammatory response to hemorrhagic shock and resuscitation.

Lipoproteina(a) is a feature of the presence, diffuseness, and severity of coronary artery disease in Saudi population.

OBJECTIVES: To study lipoprotein(a) [Lp(a)] levels in Saudi patients with angiographically defined coronary artery disease and to see its relationship with its severity and diffuseness. METHODS: This cross sectional study was carried out at King Khalid University Hospital, Riyadh, Saudi Arabia in 2006-2007. One hundred and forty-seven individuals with coronary artery disease (CAD) and 49 healthy individuals matched for age and body mass index were studied. Among CAD patients, 133 underwent angiography. Blood samples were analyzed for total cholesterol (TC), triglycerides (TG), low density lipoprotein (LDL) and high density lipoprotein (HDL) and Lp(a). RESULTS: Coronary artery disease patients had higher Lp(a) levels than controls (25.78 +/- 25.09 mg/dl versus 14.57 +/- 11.81 mg/dl, p=0.0030). Patients without stenosis (10.97 +/- 8.06 mg/dl) and one vessel involvement (19.67 +/- 17.33 mg/dl) had significantly lower levels of Lp(a) compared to double (31.88 +/- 32.17 mg/dl) and triple (29.70 +/- 28.12 mg/dl) vessel disease. Lipoprotein(a) levels correlated significantly with coronary vessel score (r=0.234, p=0.033) and Gensini score (r=0.256, p=0.02). Smoking (odds ratio [OR]: 1.86; 95% confidence interval [CI]: 1.020-2.510; p=0.04), TG levels (OR: 2.04; 95% CI: 1.251-4.932; p=0.03) and Lp(a) levels (OR: 1.56; 95% CI: 1.033-3.687; p=0.025) significantly predicted CAD severity. High risk levels of Lp(a) >/= 30 mg/dL were present in 66.7% of CAD patients. CONCLUSION: Lipoprotein(a) levels are significantly higher in Saudi patients with CAD compared to healthy individuals, and are associated with more severe and diffuse blockage of the coronary vessels.