A Clinically Explainable AI-Based Grading System for Age-Related Macular Degeneration Using Optical Coherence Tomography.

We propose an automated, explainable artificial intelligence (xAI) system for age-related macular degeneration (AMD) diagnosis. Mimicking the physician's perceptions, the proposed xAI system is capable of deriving clinically meaningful features from optical coherence tomography (OCT) B-scan images to differentiate between a normal retina, different grades of AMD (early, intermediate, geographic atrophy (GA), inactive wet or active neovascular disease [exudative or wet AMD]), and non-AMD diseases. Particularly, we extract retinal OCT-based clinical imaging markers that are correlated with the progression of AMD, which include: (i) subretinal tissue, sub-retinal pigment epithelial tissue, intraretinal fluid, subretinal fluid, and choroidal hypertransmission detection using a DeepLabV3+ network; (ii) detection of merged retina layers using a novel convolutional neural network model; (iii) drusen detection based on 2D curvature analysis; (iv) estimation of retinal layers' thickness, and first-order and higher-order reflectivity features. Those clinical features are used to grade a retinal OCT in a hierarchical decision tree process. The first step looks for severe disruption of retinal layers' indicative of advanced AMD. These cases are analyzed further to diagnose GA, inactive wet AMD, active wet AMD, and non-AMD diseases. Less severe cases are analyzed using a different pipeline to identify OCT with AMD-specific pathology, which is graded as intermediate-stage or early-stage AMD. The remainder is classified as either being a normal retina or having other non-AMD pathology. The proposed system in the multi-way classification task, evaluated on 1285 OCT images, achieved 90.82% accuracy. These promising results demonstrated the capability to automatically distinguish between normal eyes and all AMD grades in addition to non-AMD diseases.

Evaluation of the Cytological Changes of the Oral Mucosa Among Smokers in Al Madinah Al Munawara Using Argyrophilic Nucleolar Organizer Region (AgNOR) Counts and Papanicolaus Stain.

Objective To evaluate the cytological changes of the oral mucosa among smokers using Argyrophilic nucleolar organizer region (AgNOR) counts and Papanicolaou (Pap) staining. Methodology The oral mucosal exfoliate smears of 500 individuals (200 nonsmokers and 300 smokers) aged between 18 and 80 years were prepared in Al Madinah. The AgNOR count and Pap stain were used to generate a cytogenic smear to assess the presence of cytological changes suggestive of atypia, inflammation, dysplasia, keratinization, and proliferative activity of epithelial cells. Results Smokers have a considerably higher number of AgNORs per nucleus than nonsmokers (1.99 3.53 vs. 0.42 1.22). There were inflammatory changes in 127 (42.3%) of the cases and 40 (20%) of the controls. Multinucleated cells and atypia were found in 33 (11%) and 14 (4.5%) of the cases but not in the controls. The results indicate higher proliferative activity in smoking patients compared to nonsmoking patients, even in the absence of clinical lesions. Conclusion To detect the effects of smoking on the oral mucosa, Pap staining alone is insufficient. Combining Pap staining with the AgNOR technique produces the desired results.

A reduced distribution of the modified Weibull distribution and its applications to medical and engineering data.

In this work, we suggest a reduced distribution with two parameters of the modified Weibull distribution to avoid some estimation difficulties. The hazard rate function of the reduced distribution exhibits decreasing, increasing or bathtub shape. The suggested reduced distribution can be applied to many problems of modelling lifetime data. Some statistical properties of the proposed distribution have been discussed. The maximum likelihood is employed to estimate the model parameters. The Fisher information matrix is derived and then applied to construct confidence intervals for parameters. A simulation is conducted to illustrate the performance of maximum likelihood estimation. Four sets of real data are tested to prove the proposed distribution advantages. According to the statistical criteria, the proposed distribution fits the tested data better than some well-known two-and three-parameter distributions.

The impact of adolescent nicotine exposure on alcohol use during adulthood: The role of neuropeptides.

Nicotine and alcohol abuse and co-dependence represent major public health crises. Indeed, previous research has shown that the prevalence of alcoholism is higher in smokers than in non-smokers. Adolescence is a susceptible period of life for the initiation of nicotine and alcohol use and the development of nicotine-alcohol codependence. However, there is a limited number of pharmacotherapeutic agents to treat addiction to nicotine or alcohol alone. Notably, there is no effective medication to treat this comorbid disorder. This chapter aims to review the early nicotine use and its impact on subsequent alcohol abuse during adolescence and adulthood as well as the role of neuropeptides in this comorbid disorder. The preclinical and clinical findings discussed in this chapter will advance our understanding of this comorbid disorder's neurobiology and lay a foundation for developing novel pharmacotherapies to treat nicotine and alcohol codependence.

A multiparametric MRI-based CAD system for accurate diagnosis of bladder cancer staging.

Appropriate treatment of bladder cancer (BC) is widely based on accurate and early BC staging. In this paper, a multiparametric computer-aided diagnostic (MP-CAD) system is developed to differentiate between BC staging, especially T1 and T2 stages, using T2-weighted (T2W) magnetic resonance imaging (MRI) and diffusion-weighted (DW) MRI. Our framework starts with the segmentation of the bladder wall (BW) and localization of the whole BC volume (Vt) and its extent inside the wall (Vw). Our segmentation framework is based on a fully connected convolution neural network (CNN) and utilized an adaptive shape model followed by estimating a set of functional, texture, and morphological features. The functional features are derived from the cumulative distribution function (CDF) of the apparent diffusion coefficient. Texture features are radiomic features estimated from T2W-MRI, and morphological features are used to describe the tumors' geometric. Due to the significant texture difference between the wall and bladder lumen cells, Vt is parcelled into a set of nested equidistance surfaces (i.e., iso-surfaces). Finally, features are estimated for individual iso-surfaces, which are then augmented and used to train and test machine learning (ML) classifier based on neural networks. The system has been evaluated using 42 data sets, and a leave-one-subject-out approach is employed. The overall accuracy, sensitivity, specificity, and area under the receiver operating characteristics (ROC) curve (AUC) are 95.24%, 95.24%, 95.24%, and 0.9864, respectively. The advantage of fusion multiparametric iso-features is highlighted by comparing the diagnostic accuracy of individual MRI modality, which is confirmed by the ROC analysis. Moreover, the accuracy of our pipeline is compared against other statistical ML classifiers (i.e., random forest (RF) and support vector machine (SVM)). Our CAD system is also compared with other techniques (e.g., end-to-end convolution neural networks (i.e., ResNet50).

Precise higher-order reflectivity and morphology models for early diagnosis of diabetic retinopathy using OCT images.

This study proposes a novel computer assisted diagnostic (CAD) system for early diagnosis of diabetic retinopathy (DR) using optical coherence tomography (OCT) B-scans. The CAD system is based on fusing novel OCT markers that describe both the morphology/anatomy and the reflectivity of retinal layers to improve DR diagnosis. This system separates retinal layers automatically using a segmentation approach based on an adaptive appearance and their prior shape information. High-order morphological and novel reflectivity markers are extracted from individual segmented layers. Namely, the morphological markers are layer thickness and tortuosity while the reflectivity markers are the 1st-order reflectivity of the layer in addition to local and global high-order reflectivity based on Markov-Gibbs random field (MGRF) and gray-level co-occurrence matrix (GLCM), respectively. The extracted image-derived markers are represented using cumulative distribution function (CDF) descriptors. The constructed CDFs are then described using their statistical measures, i.e., the 10th through 90th percentiles with a 10% increment. For individual layer classification, each extracted descriptor of a given layer is fed to a support vector machine (SVM) classifier with a linear kernel. The results of the four classifiers are then fused using a backpropagation neural network (BNN) to diagnose each retinal layer. For global subject diagnosis, classification outputs (probabilities) of the twelve layers are fused using another BNN to make the final diagnosis of the B-scan. This system is validated and tested on 130 patients, with two scans for both eyes (i.e. 260 OCT images), with a balanced number of normal and DR subjects using different validation metrics: 2-folds, 4-folds, 10-folds, and leave-one-subject-out (LOSO) cross-validation approaches. The performance of the proposed system was evaluated using sensitivity, specificity, F1-score, and accuracy metrics. The system's performance after the fusion of these different markers showed better performance compared with individual markers and other machine learning fusion methods. Namely, it achieved [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text], respectively, using the LOSO cross-validation technique. The reported results, based on the integration of morphology and reflectivity markers and by using state-of-the-art machine learning classifications, demonstrate the ability of the proposed system to diagnose the DR early.

Syrian hamster embryo (SHE) assay (pH 6.7) coupled with infrared spectroscopy and chemometrics towards toxicological assessment.

The Syrian hamster embryo (SHE) assay (pH 6.7) is an in vitro candidate to replace in vivo carcinogenicity tests. However, the conventional method of visual scoring of foci (non-transformed vs. transformed colonies) can be time-consuming and is open to subjectivity. Infrared (IR) spectroscopy has the potential to provide objective assessment of such SHE colonies with the added advantage of potentially providing mechanistic information. In this study, SHE cells were treated with one of eight different chemical regimens, allowed in culture to attach and form foci on IR-reflective glass slides; these were subsequently interrogated by attenuated total reflection (ATR) Fourier-transform IR (FTIR) spectroscopy. Derived mid-IR spectra (n = 13,406) were subjected to chemometric analysis focusing primarily on the extraction of biochemical information related to test agent treatment and/or morphological transformation. The use of ATR-FTIR spectroscopy with chemometrics to analyze the SHE assay is a novel approach to toxicological assessment.

Wear of human enamel and nano-filled composite resin denture teeth under different loading forces.

To evaluate and correlate the two-body wear of human enamel and nano-filled composite resin teeth with the loading forces used in a dual-axis chewing simulator. Three groups of human enamel and three of nano-filled composite resin teeth were tested in a chewing simulator. Zirconia ceramic balls were used as antagonists. The teeth were tested with three different loading forces (20, 49 and 78 N). Wear was analysed by measuring the volume and vertical substance loss using a laser scanner after 300000 chewing cycles. Data were statistically analysed using two-way anova followed by the Scheffé test (P < or = 0.05). Spearman correlation test was used to determine whether there was a relationship between the loading force and the degree to which the human enamel and composite resin had worn. An increase in the loading force significantly increased the wear of composite resin and of human enamel. The effect of the loading force on the wear was statistically significant at the 0.001 level. Human enamel showed a lower volume and vertical substance loss than composite resin under loading forces of 20 and 49 N and lower vertical loss under loading force of 78 N. The correlation between the volume loss and loading force was statistically significant (r = 0.616, P < 0.001). Nano-filled composite resin and human enamel exhibited different amount of wear under different loading forces. In general, human enamel showed less vertical substance loss than nano-filled composite resin.

EARLY ASSESSMENT OF RENAL TRANSPLANTS USING BOLD-MRI: PROMISING RESULTS.

Non-invasive evaluation of renal transplant function is essential to minimize and manage renal rejection. A computer-assisted diagnostic (CAD) system was developed to evaluate kidney function post-transplantation. The developed CAD system utilizes the amount of blood-oxygenation extracted from 3D (2D + time) blood oxygen level-dependent magnetic resonance imaging (BOLD-MRI) to estimate renal function. BOLD-MRI scans were acquired at five different echo-times (2, 7, 12, 17, and 22) ms from 15 transplant patients. The developed CAD system first segments kidneys using the level-sets method followed by estimation of the amount of deoxyhemoglobin, also known as apparent relaxation rate (R2*). These R2* estimates were used as discriminatory features (global features (mean R2*) and local features (pixel-wise R2*)) to train and test state-of-the-art machine learning classifiers to differentiate between non-rejection (NR) and acute renal rejection. Using a leave-one-out cross-validation approach along with an artificial neural network (ANN) classifier, the CAD system demonstrated 93.3% accuracy, 100% sensitivity, and 90% specificity in distinguishing AR from non-rejection . These preliminary results demonstrate the efficacy of the CAD system to detect renal allograft status non-invasively.

Surgical site infections after trauma laparotomy. An observational study from a major trauma center in Saudi Arabia.

OBJECTIVES: To determine the incidence of surgical site infection (SSI) after trauma laparotomy and evaluate variables on presentation to the emergency department (ED) associated with the development of SSI. Methods: A retrospective cohort study was undertaken of patients presenting directly from the scene who underwent trauma laparotomy between January 2016 and December 2017. The primary outcome variable was SSI, as defined by the Centers for Disease Control and Prevention guideline. A univariate assessment with demographics, vital signs, and acute management was reported. Results: A total of 70 patients were included for data analysis. Of these, 9 (12.9%; 95% confidence interval (CI): 6.9-22.7%) patients developed SSI, including 5 patients with bowel injury (small bowel; n=3, colonic injuries; n=2). Most cases were diagnosed after 7 days in the hospital. All patients developed superficial incisional (skin and subcutaneous tissue) SSI. No predetermined variables, including bowel injury (p=0.08) or duration of surgery (p=0.09), demonstrated a statistically significant association with the development of SSI. Conclusion: Rates of SSI after trauma laparotomy were similar to previous reports from other centers. Surgical site infection after trauma laparotomy was diagnosed at a delayed time point after surgery, and patient demographics, injury characteristics, and acute surgical management did not appear to be associated with subsequent diagnosis of SSI.

The ability of different materials to reproduce accurate records of interocclusal relationships in the vertical dimension.

Restorations made on incorrectly mounted casts might require considerable intra-oral adjustments to correct the occlusion or might even necessitate a remake of the restoration. The aim of this study was to evaluate interocclusal recording materials for their ability to reproduce accurate vertical interocclusal relationships after a storage time of 1 and 48 h, respectively. A custom-made apparatus was used to simulate the maxilla and mandible. Eight interocclusal records were made in each of the following groups: G1: Aluwax (aluminium wax), G2: Beauty Pink wax (hydrocarbon wax compound), G3: Futar D, G4: Futar D Fast, G5: Futar Scan (G3-G5: vinyl polysiloxane), G6: Ramitec (polyether). The vertical discrepancies were measured by an inductive displacement transducer connected to a carrier frequency amplifier after storage of the records for two periods of 1 and 48 h. Two-way anova was used for statistical analysis. The mean vertical discrepancies in mum (1/48 h) for G1 (31/35) and G2 (35/38) were statistically significantly higher than for the other groups G3 (8/10), G4 (11/12), G5 (6/8) and G6 (5/8) (P < or = 0.05). There were no statistically significant differences between the elastomers tested. The effect of storage on the vertical discrepancies was statistically significant (P < 0.001). Vinyl polysiloxane and polyether interocclusal records can be used to relate working casts during mounting procedures without significant vertical displacement of the casts.

Quantitative analysis of radiophosphate uptakes in asymptomatic porous-coated hip endoprostheses.

A quantitative analysis of the uptake of radiophosphate adjacent to the femoral component of a porous-coated cementless prosthesis was undertaken in asymptomatic patients in order to establish normal temporal changes. The group consisted of 55 patients with 62 arthroplasties of 1.6-49-mo duration. Ratios of the stem, stem tip, greater trochanter, lesser trochanter and calcar, and normal femur to the reference sacroiliac joint were obtained, as well as tip-to-stem, and stem-to-normal femur in unilateral arthroplasties. The ratios remained stable at 12 months and beyond, except for the tip and lesser trochanter. Tip-to-stem and tip-to-sacroiliac joint ratios decreased by 24% and 33%, respectively, between 12 and 49 mo. There was also a decrease in the relative uptakes at the lesser trochanter and calcar in the same time interval. Evidence is given that different designs of prostheses may not have the same normal temporal uptakes of radiophosphate.

Pain in the thigh following total hip replacement with a porous-coated anatomic prosthesis for osteoarthrosis. A five-year follow-up study.

We performed a study to determine the prevalence, severity, and natural history of pain in the thigh in patients who had a total hip replacement with a porous-coated anatomic prosthesis and to determine if there was an association between the radiographic findings and the pain in the thigh. We previously reported the results in these patients two years after the operation. The present study included ninety-four patients (101 total hip replacements) who had been followed for a minimum of five years--six of the original group of patients had died from unrelated causes, two had had a revision, and one had been lost to follow-up. The patients were assessed prospectively with use of the Harris hip score and a visual-analog scale for pain in the thigh. Two of us, who were blinded to the clinical result, reviewed the radiographs retrospectively for the morphology of the proximal aspect of the femur; distal fit; metaphyseal fill; alignment of the stem; shedding of beads; distal cortical hypertrophy; pedestal formation; cancellous condensations at the distal end of the porous ingrowth surface; and the presence, extent, and location of radiolucent lines around the femoral component. At five years, pain in the thigh was found in association with twenty-seven hips (27 per cent). The pain was new in fourteen thighs (14 per cent), unchanged (from that at the two-year follow-up examination) in eight (8 per cent), increased in four (4 per cent), and decreased in one (1 per cent). Pain in the thigh was most strongly associated with a poor Harris hip score and the presence of loose beads.

Porous-coated acetabular component. Quantitative assessment of normal radiophosphate uptake as a function of implant age.

A computer-assisted quantitative analysis was undertaken of normal radiophosphate bone uptake adjacent to the porous-coated acetabular component in asymptomatic patients. Implants ranged from 1.6 to 49 months of age. In 62 hips, it was found that implants newer than 12 months of age had uptakes that were significantly greater than those 12 months or older. Between 12 and 49 months, there was no correlation with age, indicating a stabilization of the remodeling process.

Characterisation of DNA methylation status using spectroscopy (mid-IR versus Raman) with multivariate analysis.

Methylation status plays important roles in the regulation of gene expression and significantly influences the dynamics, bending and flexibility of DNA. The aim of this study was to determine whether attenuated total reflection Fourier-transform infrared (ATR-FTIR) or Raman spectroscopy with subsequent multivariate analysis could determine methylation patterning in oligonucleotides variously containing 5-methylcytosine, cytosine and guanine bases. Applied to Low-E reflective glass slides, 10 independent spectral acquisitions were acquired per oligonucleotide sample. Resultant spectra were baseline-corrected and vector normalised over the 1750 cm(-1) -760 cm(-1) (for ATR-FTIR spectroscopy) or the 1750 cm(-1) -600 cm(-1) (for Raman spectroscopy) regions. Data were then analysed using principal component analysis (PCA) coupled with linear discriminant analysis (LDA). Exploiting this approach, biomolecular signatures enabling sensitive and specific discrimination of methylation patterning were derived. For DNA sequence and methylation analysis, this approach has the potential to be an important tool, especially when material is scarce.

Prognostic significance of histopathological parameters in sentinel nodes of melanoma patients.

AIMS: The presence of micrometastases in the sentinel lymph node (SLN) is an important prognostic parameter for melanoma patients. The aim was to determine the prognostic relevance of histopathological characteristics of micrometastases in the SLN, which has not been adequately addressed thus far. METHODS AND RESULTS: In 169 melanoma patients with positive SLN, histopathological features of the SLN were correlated with overall survival (OS) and relapse-free survival (RFS). Tumour burden, expansion of melanoma cells in the periphery (infiltration of capsule) and towards the centre of the SLN [tumour penetrative depth (TPN)] were of prognostic significance for OS and RFS on univariate analysis. Multivariate analysis revealed three independent significant parameters which predict a poor prognosis: presence of infiltration of the SLN capsule, TPN > or = 2 mm and size of the largest tumour deposit > or = 30 cells. CONCLUSIONS: Histopathological analysis of SLN allows the identification of patients with a poor prognosis depending on the location of melanoma cells and tumour burden.

Sentinel node biopsy in melanoma delays recurrence but does not change melanoma-related survival: a retrospective analysis of 673 patients.

BACKGROUND: The status of the sentinel lymph node (SLN) is an important parameter to predict the prognosis of melanoma patients but it is a matter of debate if removal of micrometastases by SLN biopsy (SLNB) influences the prognosis of melanoma patients. OBJECTIVES: We sought to investigate the impact of SLNB in melanoma patients with regard to recurrence-free survival, overall survival and metastatic pathways. PATIENTS AND METHODS: We studied, retrospectively, 673 melanoma patients with a primary melanoma (tumour thickness > or = 1 mm) and without clinical evidence of metastases at the time of melanoma diagnosis. In 377 patients the melanoma was removed without SLNB between January 1995 and March 2000 (pre-SLNB group). In 296 patients the melanoma was removed with SLNB between April 2000 and March 2003 (SLNB group). Otherwise, both groups received identical surgical treatment of the primary melanoma and initial staging procedures performed by the same team of physicians. Follow-up recommendations were also identical in both groups. RESULTS: Both groups showed no significant differences with regard to characteristics of the primary melanoma, sex and age. By Kaplan-Meier analyses, melanoma-related overall survival was comparable in both groups. However, recurrence-free survival was increased in pre-SLNB patients due to significantly fewer regional lymph node metastases, whereas frequencies of locoregional cutaneous and distant metastases were comparable in both groups. CONCLUSIONS: SLNB advances the detection of regional lymph node metastases and therefore avoids nodal recurrences but does not influence metastatic behaviour of melanoma cells and does not protect patients from melanoma-related death caused by distant metastases. Thus, our retrospective data favour the marker hypothesis for melanoma metastasation. To elucidate further if subgroups of patients benefit from SLNB, prospective randomized studies with long-term follow-up are needed.

Disposition of intravenous theophylline in asthmatic children: Bayesian approach vs direct pharmacokinetic calculations.

Fifteen children (mean age +/- SD: 6.4 +/- 3.4, range: 2-12 years) with an acute asthma attack were treated by an intravenous dosage regimen of theophylline (30 min loading infusion of 6 mg/kg body weight followed by a constant infusion of 1 mg/kg, twice for 6 hr each). Three blood samples were drawn (each 15 min after the bolus infusion and after the two infusion periods of 6 hr). Plasma clearance (CL), apparent volume of distribution (Vd) and elimination half-life (t1/2) were estimated by the Bayesian approach using either only the first peak level (Bay 1) or all three monitored concentrations (Bay 3). These values were compared to the parameters calculated by a standard pharmacokinetic procedure (SC). Therapeutic steady state plasma levels around 12 micrograms/ml were rapidly achieved, and the pharmacokinetic parameters (CL = 1.1-1.5 ml/min/kg, Vd = 0.44-0.50 l/kg, t1/2 = 3.5-5.4 hr) differed slightly between the 3 methods applied. There was a significant linear correlation between the Bayesian-derived and SC-derived pharmacokinetic parameters. However the method Bay 1 seems to overestimate the elimination rate of theophylline more than Bay 3 does. In conclusion, Bayesian-based therapeutic plasma level monitoring (Bay 3 are better than Bay 1) can be utilized for individualized pharmacokinetic calculations and proper dosage predictions of theophylline in pediatric patients.